CN116952263A - Path prediction method, device, equipment and readable storage medium - Google Patents
Path prediction method, device, equipment and readable storage medium Download PDFInfo
- Publication number
- CN116952263A CN116952263A CN202310690071.8A CN202310690071A CN116952263A CN 116952263 A CN116952263 A CN 116952263A CN 202310690071 A CN202310690071 A CN 202310690071A CN 116952263 A CN116952263 A CN 116952263A
- Authority
- CN
- China
- Prior art keywords
- path
- driver
- vehicle
- front path
- intersection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3484—Personalized, e.g. from learned user behaviour or user-defined profiles
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/26—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00 specially adapted for navigation in a road network
- G01C21/34—Route searching; Route guidance
- G01C21/3453—Special cost functions, i.e. other than distance or default speed limit of road segments
- G01C21/3492—Special cost functions, i.e. other than distance or default speed limit of road segments employing speed data or traffic data, e.g. real-time or historical
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Social Psychology (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
本发明提供一种路径预测方法、装置、设备及可读存储介质。该方法包括：当路网预测树拓展至路口且没有导航信息时，根据驾驶员驾驶车辆经过的历史路程数据确定前方路径驾驶员是否驾驶车辆行驶过；若前方路径驾驶员未驾驶车辆行驶过，则判定驾驶员的驾驶习惯，得到判定结果；基于判定结果以及判定结果对应的前方路径信息得到最大可能性路径。通过本发明，对于未行驶过的前方路径，基于驾驶员的驾驶习惯以及对应的前方路径信息来预测最大可能性路径，使得得到的最大可能性路径更加符合预期，提高了路径预测的准确率。
The invention provides a path prediction method, device, equipment and readable storage medium. The method includes: when the road network prediction tree is extended to an intersection and there is no navigation information, determine whether the driver of the forward path has driven the vehicle based on the historical distance data of the driver's vehicle; if the driver of the forward path has not driven the vehicle, Then the driver's driving habits are determined and the determination result is obtained; the maximum possible path is obtained based on the determination result and the forward path information corresponding to the determination result. Through the present invention, for untraveled forward paths, the most likely path is predicted based on the driver's driving habits and the corresponding forward path information, so that the obtained most likely path is more in line with expectations and improves the accuracy of path prediction.
Description
Technical Field
The present invention relates to the field of intelligent driving technologies, and in particular, to a path prediction method, apparatus, device, and readable storage medium.
Background
EHP (electronic horizon provider) is a product or service that provides vehicles with over-the-horizon road traffic information, and EHP is based primarily on road network prediction trees for path expansion. The road network prediction tree is used as the basis of beyond visual range information, and the road network topological structure of a certain area range in front of the vehicle can be described through the tree-shaped data structure, so that the road network prediction tree can be expanded and provided for the vehicle in the vehicle driving process by the EHP, and the basis is provided for intelligent driving decision and control of the vehicle. Road network prediction trees typically include MPP (mostprobblepath) and non-MPP.
In the prior art, an electronic horizon system calculates the traveling possibility of different paths mainly through historical path selection indexes, path turning angle indexes and road grade indexes, so that the path with the highest possibility is selected. Because the road is complex and the driving habits of drivers are different, the driving possibility of different paths is calculated only by the historical path selection index, the path turning angle index and the road grade index, the selected path with the highest possibility cannot be ensured to be the most applicable path, and the accuracy rate of path prediction is lower.
Disclosure of Invention
The invention mainly aims to provide a path prediction method, a device, equipment and a readable storage medium, aiming at improving the accuracy of path prediction.
In a first aspect, the present invention provides a path prediction method, the path prediction method comprising:
when the road network prediction tree is expanded to the intersection and navigation information is not available, determining whether a driver of a front path drives the vehicle to travel according to historical path data of the driver driving the vehicle;
if the front path driver does not drive the vehicle to run through, judging the driving habit of the driver to obtain a judging result;
and obtaining a maximum likelihood path based on the determination result and the front path information corresponding to the determination result.
Optionally, the step of determining the driving habit of the driver and obtaining the determination result includes:
obtaining the treading depth and the treading times of an accelerator pedal, the treading depth and the treading times of a brake pedal, the number of whistling times and the duration of whistling each time of a driver in a preset duration;
judging whether the driving habit of a driver meets a more aggressive condition, wherein the more aggressive condition is that the treading depth and the treading frequency of the accelerator pedal are larger than corresponding thresholds and the treading depth and the treading frequency of the brake pedal are larger than corresponding thresholds, and/or the frequency of whistling and the duration of each whistling are larger than corresponding thresholds;
if the driving habit of the driver is satisfied, the judgment result is that the driving habit of the driver is more aggressive;
if the driving habit of the driver is not satisfied, the judgment result is that the driving habit of the driver is stable.
Optionally, the step of obtaining the maximum likelihood path based on the determination result and the forward path information corresponding to the determination result includes:
if the judging result is that the driving habit of the driver is more aggressive, the front path information corresponding to the judging result comprises the road type of the front path, whether a traffic light on the front path is green light when the vehicle runs to an intersection, whether schools exist on the front path in the upper school time period and the lower school time period and whether the front path is blocked;
selecting a target front path from each front path according to each piece of information;
assigning the score corresponding to the selected target front path to be one, and assigning the score corresponding to the unselected front path to be zero;
adding products between the corresponding scores and the corresponding weights of each front path to obtain a plurality of sum values;
the forward path corresponding to the maximum value among the plurality of sum values is set as the maximum likelihood path.
Optionally, the step of selecting the target front path from each front path according to each piece of information includes:
selecting a front path with the highest road type grade from each front path as a target front path according to the road type of the front path;
according to whether the traffic light on the front path is a green light or not when the vehicle runs to the intersection, selecting the front path of which the traffic light is the green light as a target front path from each front path when the vehicle runs to the intersection;
selecting a front path without schools in the time interval of the school from each front path as a target front path according to whether schools exist on the front paths in the time interval of the school;
and selecting a front path without traffic jam from each front path as a target front path according to whether the front path is blocked or not.
Optionally, the step of obtaining the maximum likelihood path based on the determination result and the forward path information corresponding to the determination result includes:
if the judgment result is that the driving habit of the driver is stable, the front path information corresponding to the judgment result is the corresponding rotation angle when the vehicle runs on each front path;
the forward path corresponding to the minimum rotation angle is taken as the maximum likelihood path.
Optionally, after the step of determining whether the front path driver drives the vehicle to travel according to the historical path data of the driver driving the vehicle, the method includes:
if the driver of the front path drives the vehicle to drive through, backtracking the number of times that each front path is driven through when the vehicle passes through the intersection for n times before driving through the intersection, wherein n is a positive integer;
multiplying the number of times each front path is driven by a weight value corresponding to each front path to obtain a plurality of products;
and taking the front path corresponding to the maximum value in the products as the maximum possibility path, wherein the weight value corresponding to the front path which is driven is the largest when the vehicle drives through the intersection last time, and the weight values corresponding to the remaining two front paths are the same.
Optionally, the path prediction method includes:
detecting whether the maximum likelihood path is on a current path;
and if the maximum likelihood path is not on the current path, outputting the maximum likelihood path and other level-one sub-paths corresponding to the intersection.
In a second aspect, the present invention also provides a path prediction apparatus, including:
the determining module is used for determining whether the driver of the front path drives the vehicle to run according to the historical path data of the driver driving the vehicle to pass when the road network prediction tree is expanded to the intersection and navigation information is not available;
the judging module is used for judging the driving habit of the driver if the driver in the front path does not drive the vehicle to pass through, so as to obtain a judging result;
and the path acquisition module is used for acquiring the maximum likelihood path based on the judging result and the front path information corresponding to the judging result.
In a third aspect, the present invention also provides a path prediction apparatus comprising a processor, a memory, and a path prediction program stored on the memory and executable by the processor, wherein the path prediction program, when executed by the processor, implements the steps of the path prediction method as described above.
In a fourth aspect, the present invention also provides a readable storage medium having stored thereon a path prediction program, wherein the path prediction program, when executed by a processor, implements the steps of the path prediction method as described above.
According to the method, when the road network prediction tree is expanded to an intersection and navigation information is not available, whether a driver in a front path drives the vehicle to travel or not is determined according to historical path data of the driver driving the vehicle to travel; if the front path driver does not drive the vehicle to run through, judging the driving habit of the driver to obtain a judging result; and obtaining a maximum likelihood path based on the determination result and the front path information corresponding to the determination result. According to the method and the device for predicting the forward path, for the forward path which does not pass through, the maximum likelihood path is predicted based on the driving habit of the driver and the corresponding forward path information, so that the obtained maximum likelihood path meets the expectations, and the accuracy of path prediction is improved.
Drawings
FIG. 1 is a flowchart of a first embodiment of a path prediction method according to the present invention;
FIG. 2 is a schematic diagram of a first refinement procedure of step S30 in FIG. 1;
FIG. 3 is a schematic diagram of a second refinement procedure of step S30 in FIG. 1;
FIG. 4 is a flowchart of a second embodiment of the path prediction method according to the present invention;
FIG. 5 is a schematic diagram of a maximum likelihood path prediction method according to a first embodiment of the present invention;
FIG. 6 is a schematic diagram of a maximum likelihood path prediction according to a second embodiment of the path prediction method of the present invention;
FIG. 7 is a schematic diagram of functional modules of a first embodiment of a path prediction apparatus according to the present invention;
fig. 8 is a schematic hardware structure of a path prediction device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In a first aspect, an embodiment of the present invention provides a path prediction method.
In an embodiment, referring to fig. 1, fig. 1 is a flowchart illustrating a first embodiment of a path prediction method according to the present invention. As shown in fig. 1, the path prediction method includes:
step S10, when the road network prediction tree is expanded to an intersection and navigation information is not available, determining whether a driver of a front path drives the vehicle to travel according to historical path data of the driver driving the vehicle;
in this embodiment, when the road network prediction tree extends to the intersection and there is no navigation information, the position of the front path is obtained, and whether the driver of any path drives the vehicle to travel in front is determined according to the historical path data of the driver driving the vehicle. It is easily conceivable that when the road network prediction tree expands to an intersection, there are at least two forward paths.
When the road network prediction tree expands to the intersection and navigation information exists, the maximum likelihood path is completely determined according to the navigation path.
When the road network prediction tree is not expanded to the intersection, the EHP (electronic horizon provider) broadcasts relevant information of the current path of the vehicle to the EHR (ElectricHorizon Reconstructor, electronic horizon reconstructor). The EHP depends on a vehicle positioning module to broadcast path information of a certain distance in front of the vehicle to the vehicle according to the actual position of the vehicle, wherein the information comprises but is not limited to speed limit, ramp, curvature, signal lamp, school and other position and attribute information, and as the vehicle continuously runs along the path, a road network prediction tree is expanded according to the real-time positioning of the vehicle, and the EHP continuously updates and broadcasts the path information of the certain distance in front to the EHR. The road network prediction tree comprises: MPP (Most ProbablePath, maximum likelihood path) and non-MPP paths, i.e., sub-paths. Wherein the MPP is a predicted maximum likelihood travel path of the vehicle, one path may include at least one road segment, each MPP road segment is connected to form an MPP (maximum likelihood path), and the non-MPP may be a road segment extended from the MPP road segment of the MPP; the non-MPP is a predicted path of non-maximum likelihood travel of the vehicle; a non-MPP may include at least one non-MPP segment.
Step S20, if the front path driver does not drive the vehicle, judging the driving habit of the driver, and obtaining a judging result;
in this embodiment, if the front-path driver does not drive the vehicle, it is necessary to determine whether the driving habit of the driver is more aggressive or smoother, and to obtain a determination result, that is, to determine whether the driving habit of the driver is more aggressive or to determine that the driving habit of the driver is smoother.
Step S30, obtaining the maximum likelihood path based on the judging result and the front path information corresponding to the judging result.
In this embodiment, the driving habit of the driver is determined based on the determination result, if the determination result is that the driving habit of the driver is more aggressive, the front path information corresponding to the driving habit of the driver is acquired, and the maximum likelihood path is obtained based on the front path information corresponding to the driving habit is more aggressive. If the driving habit of the driver is stable as a result of the judgment, the corresponding front path information when the driving habit of the driver is stable is obtained, and the maximum likelihood path can be obtained based on the corresponding front path information when the driving habit is stable.
In the embodiment, when the road network prediction tree is expanded to an intersection and navigation information is not available, whether a driver in a front path drives the vehicle to travel or not is determined according to historical path data of the driver driving the vehicle to travel; if the front path driver does not drive the vehicle to run through, judging the driving habit of the driver to obtain a judging result; and obtaining a maximum likelihood path based on the determination result and the front path information corresponding to the determination result. According to the embodiment, for the front paths which do not run, the maximum likelihood path is predicted based on the driving habit of the driver and the corresponding front path information, so that the obtained maximum likelihood path meets the expectations, and the accuracy of path prediction is improved.
Further, in an embodiment, the step of determining the driving habit of the driver to obtain the determination result includes:
obtaining the treading depth and the treading times of an accelerator pedal, the treading depth and the treading times of a brake pedal, the number of whistling times and the duration of whistling each time of a driver in a preset duration;
judging whether the driving habit of a driver meets a more aggressive condition, wherein the more aggressive condition is that the treading depth and the treading frequency of the accelerator pedal are larger than corresponding thresholds and the treading depth and the treading frequency of the brake pedal are larger than corresponding thresholds, and/or the frequency of whistling and the duration of each whistling are larger than corresponding thresholds;
if the driving habit of the driver is satisfied, the judgment result is that the driving habit of the driver is more aggressive;
if the driving habit of the driver is not satisfied, the judgment result is that the driving habit of the driver is stable.
In this embodiment, the tread depth and tread frequency of the accelerator pedal, the tread depth and tread frequency of the brake pedal, the number of whistles and the duration of each whistle of the driver are obtained within a preset duration.
If the treading depth and the treading times of the accelerator pedal are larger than the corresponding threshold values and the treading depth and the treading times of the brake pedal are larger than the corresponding threshold values, and/or the number of whistling times in the preset duration and the duration of each whistling time are larger than the corresponding threshold values, the driving habit of the driver is more aggressive as a judging result.
If the treading depth and the treading times of the accelerator pedal are smaller than or equal to the corresponding threshold values, and the treading depth and the treading times of the brake pedal are smaller than or equal to the corresponding threshold values, and/or the number of whistling times in the preset duration and the duration of each whistling time are smaller than or equal to the corresponding threshold values, the driving habit of the driver is stable as a judging result. It is easily conceivable that the threshold value corresponding to the depression depth of the accelerator pedal may be the same or different from the threshold value corresponding to the depression depth of the brake pedal, and the threshold value corresponding to the number of times of depression of the accelerator pedal may be the same or different from the threshold value corresponding to the number of times of depression of the brake pedal.
Further, referring to fig. 2, fig. 2 is a schematic diagram of a first refinement procedure of step S30 in fig. 1. As shown in fig. 2, the step of obtaining the maximum likelihood path based on the determination result and the forward path information corresponding to the determination result includes:
step S301, if the judgment result is that the driving habit of the driver is more aggressive, the front path information corresponding to the judgment result comprises the road type of the front path, whether the traffic lights on the front path are green lights when the vehicle runs to the intersection, whether schools exist on the front path in the time period of going up and down and whether the front path is blocked;
step S302, selecting a target front path from each front path according to each piece of information;
step S303, the score corresponding to the selected target front path is assigned as one, and the score corresponding to the unselected front path is assigned as zero;
step S304, adding products of the corresponding scores and the corresponding weights of each front path to obtain a plurality of sum values;
in step S305, a front path corresponding to the maximum value among the plurality of sum values is set as a maximum likelihood path.
In this embodiment, if the driving habit of the driver is more aggressive as a result of the determination, the front path information corresponding to the more aggressive driving habit of the driver is obtained, including the road type of the front path, whether the traffic light on the front path is green light when the vehicle is driving to the intersection, whether there is a school on the front path in the time slot of going up and down, and whether the front path is blocked.
Taking the example that the front path includes a front left path a, a front middle path B and a front right path C, a target front path is selected from the front left path a, the front middle path B and the front right path C according to each piece of information.
If a front Zuo Celu path a is selected according to the road type of the front path, the front left path a is the target front path, the score corresponding to the selected front Zuo Celu path a is assigned as one, and the score corresponding to the front middle path and the front right path C is assigned as zero.
If a forward Zuo Celu path A is selected according to whether a traffic light on a forward path is a green light when the vehicle runs to an intersection, the forward left path A is a target forward path, the score corresponding to the selected forward Zuo Celu path A is assigned as one, and the score corresponding to the forward middle path B and the forward right path C is assigned as zero.
If a front right path C is selected according to whether schools exist on the front paths of the upper and lower learning time periods, the front right path C is the target front path, the score corresponding to the selected front right path C is assigned as one, and the score corresponding to the front left path A and the front middle path B is assigned as zero.
If the front path is blocked, the front middle path B and the front right path C are selected, the front middle path B and the front right path C are the target front paths, the scores corresponding to the selected front middle path B and the front right path C are assigned as one, and the score corresponding to the front left path A is assigned as zero.
And adding the products of the corresponding scores and the corresponding weights of each front path to obtain a plurality of sum values. Specifically, taking an example that the weight corresponding to the road type of the front path is 0.2, whether the traffic light on the front path is green light when the vehicle runs to the intersection is 0.1, whether the weight corresponding to school is 0.1 on the front path in the upper and lower school time periods, and whether the weight corresponding to traffic jam of the front path is 0.1, adding the products of the score corresponding to the front Zuo Celu path a and the corresponding weight to obtain a sum value L corresponding to the front Zuo Celu path a, namely l=0.2×1+0.1×1+0.1×0.1×0+0.1×0.3. The respective products between the corresponding scores and the corresponding weights of the front intermediate path B are added, the sum value M corresponding to the front intermediate path B is obtained, i.e. m=0.2×0+0.1×0+0.1×0+0.1×1 =0.1. And adding the products of the scores corresponding to the front right paths C and the corresponding weights to obtain a sum value R corresponding to the front right paths C, namely R=0.2×0+0.1×0+0.1×1+0.1×1=0.2.
The maximum value function max () is obtained to select the maximum value from the sum L, the sum M, and the sum R, and the forward path corresponding to the maximum value from the sum L, the sum M, and the sum R is used as the maximum likelihood path. Since the maximum value of the sum L, the sum M, and the sum R is the sum L and the front path corresponding to the sum L is the front left path a, the front left path a is the maximum likelihood path.
Further, when the maximum value of the plurality of sum values is not the same, the most probable path is preferentially output based on the corresponding score value and the corresponding weight condition of each front path. Specifically, if the sum value L is the same as the sum value M, the weight corresponding to the road type of the front route is the largest, and the front Zuo Celu route a corresponding to the sum value L is selected according to the road type of the front route, so that the front left route a is taken as the most probable route at this time. Further, if the score corresponding to each of the forward paths is the same as the corresponding weight, the forward path corresponding to the smallest angle of rotation when the vehicle travels on the forward path is taken as the most probable path. It should be noted that the parameters in this embodiment are only used for reference, and are not limited herein.
Further, in an embodiment, the step of selecting the target forward path from each forward path according to each piece of information includes:
selecting a front path with the highest road type grade from each front path as a target front path according to the road type of the front path;
according to whether the traffic light on the front path is a green light or not when the vehicle runs to the intersection, selecting the front path of which the traffic light is the green light as a target front path from each front path when the vehicle runs to the intersection;
selecting a front path without schools in the time interval of the school from each front path as a target front path according to whether schools exist on the front paths in the time interval of the school;
and selecting a front path without traffic jam from each front path as a target front path according to whether the front path is blocked or not.
In this embodiment, taking the case that the front route includes the front left side route a, the front middle route B, and the front right side route C as an example, if the road types of the front Zuo Celu route a and the front middle route B out of the front Zuo Celu route a, the front middle route B, and the front right side route C are highest in rank, the front Zuo Celu route a and the front middle route B are selected as the target front route according to the road types of the front routes.
And if the traffic lights on the front path A, the front middle path B and the front left path A in the front right path C are green lights when the vehicle is predicted to travel to the intersection, selecting the front Zuo Celu path A as a target front path.
And if no school exists on the front right path C in the front left path A, the front middle path B and the front right path C in the front and lower school time periods according to the existence of schools on the front paths in the upper and lower school time periods, selecting the front right path C as a target front path. If the time period is not up and down, the front left path a, the front middle path B, and the front right path C are all target front paths.
If the forward intermediate path B and the forward right path C among the forward Zuo Celu path a, the forward intermediate path B, and the forward right path C are not blocked, the forward intermediate path B and the forward right path C are selected as the target forward paths, depending on whether the forward paths are blocked.
Further, in an embodiment, referring to fig. 3, fig. 3 is a schematic diagram of a second refinement procedure of step S30 in fig. 1. As shown in fig. 3, the step of obtaining the maximum likelihood path based on the determination result and the forward path information corresponding to the determination result includes:
step S306, if the judgment result is that the driving habit of the driver is stable, the front path information corresponding to the judgment result is the corresponding rotation angle when the vehicle runs on each front path;
in step S307, the front path corresponding to the minimum rotation angle is used as the maximum likelihood path.
In this embodiment, if the determination result is that the driving habit of the driver is relatively stable, the front path information corresponding to the relatively stable driving habit of the driver is obtained, including the corresponding rotation angle when the vehicle travels on each front path. Taking the example that the front path includes a front left-side path a, a front middle path B and a front right-side path C, a first corner corresponding to the vehicle when traveling from the current path to the front left-side path a, a second corner corresponding to the vehicle when traveling from the current path to the front middle path B and a third corner corresponding to the vehicle when traveling from the current path to the front right-side path C are obtained.
If the second corner is the smallest among the first corner, the second corner and the second corner, the front middle path B corresponding to the second corner is used as the maximum likelihood path. It is easily conceivable that at the intersection, the corresponding second rotation angle in the ideal state when the vehicle travels from the current path to the front intermediate path B is 0 degrees.
Further, in an embodiment, referring to fig. 4, fig. 4 is a flowchart illustrating a second embodiment of the path prediction method according to the present invention. As shown in fig. 4, after the step of determining whether the front path driver drives the vehicle to travel based on the history of the distance data that the driver has driven the vehicle, it includes:
step S40, if the driver of the front path drives the vehicle to travel, backtracking the number of times that each front path is driven when the vehicle passes through the intersection n times before, wherein n is a positive integer;
step S50, multiplying the number of times each front path is driven by a weight value corresponding to each front path to obtain a plurality of products;
and step S60, taking a front path corresponding to the maximum value in the products as a maximum possibility path, wherein the weight value corresponding to the front path which is driven is the largest when the vehicle drives through the intersection last time, and the weight values corresponding to the remaining two front paths are the same.
In this embodiment, taking an example in which the front route includes a front left-side route a, a front middle route B, and a front right-side route C, if the front route driver drives the vehicle to travel through the road, and the front route through which the vehicle has traveled last time is a front Zuo Celu route a, the weight value corresponding to the front Zuo Celu route a is the largest, and the weight values corresponding to the front middle route B and the front right-side route C are the same.
Taking the example that the weight value corresponding to the forward Zuo Celu path a is 0.7, the weight value corresponding to the forward middle path B and the forward right path C is 0.3, and n=5, the number of times the forward Zuo Celu path a, the forward middle path B and the forward right path C have been travelled when the vehicle has travelled 5 times before the vehicle is traced back through the intersection.
If the front Zuo Celu path a is travelled 2 times, the front middle path B is travelled 2 times, and the front right path C is travelled 1 time, the number of times the front Zuo Celu path a is travelled is multiplied by the weight value corresponding to the front Zuo Celu path a to obtain a first product X corresponding to the front Zuo Celu path a, where the first product x=0.7x2=1.4. And multiplying the number of times the front intermediate path B is driven by the weight value corresponding to the front intermediate path B to obtain a second product Y corresponding to the front intermediate path B, wherein the second product y=0.3×2=0.6. And multiplying the number of times the front right path C is driven by the weight value corresponding to the front right path C to obtain a third multiplication product Z corresponding to the front right path C, wherein the third multiplication product Z=0.3×1=0.3.
And selecting the maximum value from the first product X, the second product Y and the third product Z by solving the maximum value function max (), and taking a front path corresponding to the maximum value in the first product X, the second product Y and the third product Z as a maximum possibility path. The maximum value of the first product X, the second product Y, and the third product Z is the first product X, and the front path corresponding to the first product X is the front left path a, so the front left path a is taken as the maximum likelihood path. It is easy to think that, when the driving habits of the driver are determined, it is determined that the same driver is driving the vehicle and that the driver is not driving the vehicle on the front route. Specifically, according to historical route data of the driver a driving the vehicle, if the driver a does not drive the vehicle, determining driving habits of the driver a according to the stepping depth and the stepping times of the accelerator pedal, the stepping depth and the stepping times of the brake pedal, the number of whistles and the duration of each whistle of the driver a in a preset duration. The identity of the driver is judged through the camera or the human body electromyographic signals.
Further, in an embodiment, the path prediction method includes:
detecting whether the maximum likelihood path is on a current path;
and if the maximum likelihood path is not on the current path, outputting the maximum likelihood path and other level-one sub-paths corresponding to the intersection.
In this embodiment, it is detected whether the most probable path predicted by the road network prediction tree is on the current path. And if the maximum likelihood path is not on the current path, outputting only the maximum likelihood path and other level-one sub-paths corresponding to the intersection. If the maximum likelihood path is on the current path, the maximum likelihood path and other multi-level sub-paths are output.
Specifically, referring to fig. 5, fig. 5 is a schematic diagram of maximum likelihood path prediction according to a first embodiment of the path prediction method of the present invention. As shown in fig. 5, taking the current path as an example of the path 1, when the road network prediction tree extends to the intersection, if the maximum likelihood path is a path corresponding to the dotted line on the path 1, the maximum likelihood path is on the current path, and the maximum likelihood path and other multi-level sub-paths are output, that is, the maximum likelihood path (path 1) and other multi-level sub-paths (path 2, path 3, path 4, path 5 and path 6) are output.
When the road network prediction tree extends to the intersection, referring to fig. 6, fig. 6 is a schematic diagram of the maximum likelihood path prediction according to the second embodiment of the path prediction method of the present invention. As shown in fig. 6, if the maximum likelihood path is a path corresponding to a broken line on the path 4, the maximum likelihood path is not on the current path, and only the maximum likelihood path (the path 4) and other first-level sub-paths corresponding to the intersection, that is, the left-side path 2 in front of the current path and the middle-side path 1 in front of the current path are output.
Further, when the distance between the vehicle and the intersection is smaller than the preset distance and the turn-on time of the turn lamp is greater than or equal to the corresponding threshold value, if the front path corresponding to the turn lamp is different from the maximum likelihood path, the front path corresponding to the turn lamp is output as a sub-path, and the predicted distance of the front path corresponding to the turn lamp is increased.
Or when the distance between the vehicle and the intersection is smaller than the preset distance and the forward-looking camera is used for identifying the road edge of the current path or the directional arrow on the road surface, if the forward path corresponding to the directional arrow is different from the maximum possibility path, outputting the forward path corresponding to the directional arrow as a sub-path, and increasing the predicted distance of the forward path corresponding to the steering lamp.
Further, the EHR (electric horizon reconstruction party) receives a path output by the EHP (electric horizon provider), and then stores the received path, and timely deletes information after the vehicle. And after the received paths are post-processed, the paths are provided for other functions to use.
In a second aspect, an embodiment of the present invention further provides a path prediction apparatus.
In an embodiment, referring to fig. 7, fig. 7 is a schematic functional block diagram of a first embodiment of a path prediction apparatus according to the present invention. As shown in fig. 7, the path prediction apparatus includes:
the determining module 10 is configured to determine whether the driver of the front path drives the vehicle to travel according to the historical path data of the driver driving the vehicle when the road network prediction tree extends to the intersection and no navigation information exists;
a determining module 20, configured to determine a driving habit of the driver if the driver does not drive the vehicle through the front path, and obtain a determination result;
the path acquisition module 30 is configured to obtain a maximum likelihood path based on the determination result and the forward path information corresponding to the determination result.
Further, in an embodiment, the determining module 20 is configured to:
obtaining the treading depth and the treading times of an accelerator pedal, the treading depth and the treading times of a brake pedal, the number of whistling times and the duration of whistling each time of a driver in a preset duration;
judging whether the driving habit of a driver meets a more aggressive condition, wherein the more aggressive condition is that the treading depth and the treading frequency of the accelerator pedal are larger than corresponding thresholds and the treading depth and the treading frequency of the brake pedal are larger than corresponding thresholds, and/or the frequency of whistling and the duration of each whistling are larger than corresponding thresholds;
if the driving habit of the driver is satisfied, the judgment result is that the driving habit of the driver is more aggressive;
if the driving habit of the driver is not satisfied, the judgment result is that the driving habit of the driver is stable.
Further, in an embodiment, the path obtaining module 30 is configured to:
if the judging result is that the driving habit of the driver is more aggressive, the front path information corresponding to the judging result comprises the road type of the front path, whether a traffic light on the front path is green light when the vehicle runs to an intersection, whether schools exist on the front path in the upper school time period and the lower school time period and whether the front path is blocked;
selecting a target front path from each front path according to each piece of information;
assigning the score corresponding to the selected target front path to be one, and assigning the score corresponding to the unselected front path to be zero;
adding products between the corresponding scores and the corresponding weights of each front path to obtain a plurality of sum values;
the forward path corresponding to the maximum value among the plurality of sum values is set as the maximum likelihood path.
Further, in an embodiment, the path obtaining module 30 is further configured to:
selecting a front path with the highest road type grade from each front path as a target front path according to the road type of the front path;
according to whether the traffic light on the front path is a green light or not when the vehicle runs to the intersection, selecting the front path of which the traffic light is the green light as a target front path from each front path when the vehicle runs to the intersection;
selecting a front path without schools in the time interval of the school from each front path as a target front path according to whether schools exist on the front paths in the time interval of the school;
and selecting a front path without traffic jam from each front path as a target front path according to whether the front path is blocked or not.
Further, in an embodiment, the path obtaining module 30 is further configured to:
if the judgment result is that the driving habit of the driver is stable, the front path information corresponding to the judgment result is the corresponding rotation angle when the vehicle runs on each front path;
the forward path corresponding to the minimum rotation angle is taken as the maximum likelihood path.
Further, in an embodiment, the path obtaining module 30 is further configured to:
if the driver of the front path drives the vehicle to drive through, backtracking the number of times that each front path is driven through when the vehicle passes through the intersection for n times before driving through the intersection, wherein n is a positive integer;
multiplying the number of times each front path is driven by a weight value corresponding to each front path to obtain a plurality of products;
and taking the front path corresponding to the maximum value in the products as the maximum possibility path, wherein the weight value corresponding to the front path which is driven is the largest when the vehicle drives through the intersection last time, and the weight values corresponding to the remaining two front paths are the same.
Further, in an embodiment, the path prediction apparatus further includes an output module, configured to:
detecting whether the maximum likelihood path is on a current path;
and if the maximum likelihood path is not on the current path, outputting the maximum likelihood path and other level-one sub-paths corresponding to the intersection.
The function implementation of each module in the path prediction device corresponds to each step in the path prediction method embodiment, and the function and implementation process thereof are not described in detail herein.
In a third aspect, an embodiment of the present invention provides a path prediction apparatus, which may be an apparatus having a data processing function, such as a Personal Computer (PC), a notebook computer, a server, or the like.
Referring to fig. 8, fig. 8 is a schematic hardware structure of a path prediction apparatus according to an embodiment of the present invention. In an embodiment of the present invention, the path prediction apparatus may include a processor 1001 (e.g., a central processor CentralProcessingUnit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein the communication bus 1002 is used to enable connected communications between these components; the user interface 1003 may include a Display screen (Display), an input unit such as a Keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface, a WIreless interface (e.g., WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed Random Access Memory (RAM) or a stable memory (non-volatile memory), such as a disk memory, and the memory 1005 may alternatively be a storage device independent of the processor 1001. Those skilled in the art will appreciate that the hardware configuration shown in fig. 8 is not limiting of the invention and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
With continued reference to fig. 8, an operating system, a network communication module, a user interface module, and a path prediction program may be included in the memory 1005, which is one type of computer storage medium in fig. 8. The processor 1001 may call a path prediction program stored in the memory 1005, and execute the path prediction method provided by the embodiment of the present invention.
In a fourth aspect, embodiments of the present invention also provide a readable storage medium.
The readable storage medium of the present invention stores a path prediction program, wherein the path prediction program, when executed by a processor, implements the steps of the path prediction method as described above.
The method implemented when the path prediction program is executed may refer to various embodiments of the path prediction method of the present invention, which are not described herein.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) as described above, comprising several instructions for causing a terminal device to perform the method according to the embodiments of the present invention.
The foregoing description is only of the preferred embodiments of the present invention, and is not intended to limit the scope of the invention, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. A path prediction method, characterized in that the path prediction method comprises:
when the road network prediction tree is expanded to the intersection and navigation information is not available, determining whether a driver of a front path drives the vehicle to travel according to historical path data of the driver driving the vehicle;
if the front path driver does not drive the vehicle to run through, judging the driving habit of the driver to obtain a judging result;
and obtaining a maximum likelihood path based on the determination result and the front path information corresponding to the determination result.
2. The route prediction method according to claim 1, wherein the step of determining the driving habit of the driver to obtain the determination result includes:
obtaining the treading depth and the treading times of an accelerator pedal, the treading depth and the treading times of a brake pedal, the number of whistling times and the duration of whistling each time of a driver in a preset duration;
judging whether the driving habit of a driver meets a more aggressive condition, wherein the more aggressive condition is that the treading depth and the treading frequency of the accelerator pedal are larger than corresponding thresholds and the treading depth and the treading frequency of the brake pedal are larger than corresponding thresholds, and/or the frequency of whistling and the duration of each whistling are larger than corresponding thresholds;
if the driving habit of the driver is satisfied, the judgment result is that the driving habit of the driver is more aggressive;
if the driving habit of the driver is not satisfied, the judgment result is that the driving habit of the driver is stable.
3. The path prediction method according to claim 1, wherein the step of obtaining the maximum likelihood path based on the determination result and the forward path information corresponding to the determination result includes:
if the judging result is that the driving habit of the driver is more aggressive, the front path information corresponding to the judging result comprises the road type of the front path, whether a traffic light on the front path is green light when the vehicle runs to an intersection, whether schools exist on the front path in the upper school time period and the lower school time period and whether the front path is blocked;
selecting a target front path from each front path according to each piece of information;
assigning the score corresponding to the selected target front path to be one, and assigning the score corresponding to the unselected front path to be zero;
adding products between the corresponding scores and the corresponding weights of each front path to obtain a plurality of sum values;
the forward path corresponding to the maximum value among the plurality of sum values is set as the maximum likelihood path.
4. A path prediction method according to claim 3, wherein the step of selecting the target forward path from each forward path based on each piece of information, respectively, comprises:
selecting a front path with the highest road type grade from each front path as a target front path according to the road type of the front path;
according to whether the traffic light on the front path is a green light or not when the vehicle runs to the intersection, selecting the front path of which the traffic light is the green light as a target front path from each front path when the vehicle runs to the intersection;
selecting a front path without schools in the time interval of the school from each front path as a target front path according to whether schools exist on the front paths in the time interval of the school;
and selecting a front path without traffic jam from each front path as a target front path according to whether the front path is blocked or not.
5. The path prediction method according to claim 1, wherein the step of obtaining the maximum likelihood path based on the determination result and the forward path information corresponding to the determination result includes:
if the judgment result is that the driving habit of the driver is stable, the front path information corresponding to the judgment result is the corresponding rotation angle when the vehicle runs on each front path;
the forward path corresponding to the minimum rotation angle is taken as the maximum likelihood path.
6. The path prediction method according to claim 1, characterized by comprising, after the step of determining whether the front path driver is driving the vehicle to travel based on the history of the path data that the driver is driving the vehicle to travel, the steps of:
if the driver of the front path drives the vehicle to drive through, backtracking the number of times that each front path is driven through when the vehicle passes through the intersection for n times before driving through the intersection, wherein n is a positive integer;
multiplying the number of times each front path is driven by a weight value corresponding to each front path to obtain a plurality of products;
and taking the front path corresponding to the maximum value in the products as the maximum possibility path, wherein the weight value corresponding to the front path which is driven is the largest when the vehicle drives through the intersection last time, and the weight values corresponding to the remaining two front paths are the same.
7. The path prediction method according to any one of claims 1 to 6, characterized in that the path prediction method comprises:
detecting whether the maximum likelihood path is on a current path;
and if the maximum likelihood path is not on the current path, outputting the maximum likelihood path and other level-one sub-paths corresponding to the intersection.
8. A path prediction apparatus, comprising:
the determining module is used for determining whether the driver of the front path drives the vehicle to run according to the historical path data of the driver driving the vehicle to pass when the road network prediction tree is expanded to the intersection and navigation information is not available;
the judging module is used for judging the driving habit of the driver if the driver in the front path does not drive the vehicle to pass through, so as to obtain a judging result;
and the path acquisition module is used for acquiring the maximum likelihood path based on the judging result and the front path information corresponding to the judging result.
9. A path prediction device comprising a processor, a memory, and a path prediction program stored on the memory and executable by the processor, wherein the path prediction program, when executed by the processor, implements the steps of the path prediction method of any of claims 1 to 7.
10. A readable storage medium, wherein a path prediction program is stored on the readable storage medium, wherein the path prediction program, when executed by a processor, implements the steps of the path prediction method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310690071.8A CN116952263B (en) | 2023-06-09 | 2023-06-09 | Path prediction method, device, equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310690071.8A CN116952263B (en) | 2023-06-09 | 2023-06-09 | Path prediction method, device, equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116952263A true CN116952263A (en) | 2023-10-27 |
| CN116952263B CN116952263B (en) | 2025-07-04 |
Family
ID=88446913
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310690071.8A Active CN116952263B (en) | 2023-06-09 | 2023-06-09 | Path prediction method, device, equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116952263B (en) |
Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6711498B1 (en) * | 1999-09-08 | 2004-03-23 | Robert Bosch Gmbh | Method for operating a navigation system for a vehicle |
| JP2007327872A (en) * | 2006-06-08 | 2007-12-20 | Denso Corp | Driver personality determination device and vehicle navigation device |
| US8700251B1 (en) * | 2012-04-13 | 2014-04-15 | Google Inc. | System and method for automatically detecting key behaviors by vehicles |
| CN107270923A (en) * | 2017-06-16 | 2017-10-20 | 广东欧珀移动通信有限公司 | Method, terminal and storage medium for route push |
| CN108827334A (en) * | 2018-08-09 | 2018-11-16 | 北京智行者科技有限公司 | A kind of automatic Pilot method |
| CN110525447A (en) * | 2019-10-09 | 2019-12-03 | 吉林大学 | A kind of the man-machine of anti-commercial vehicle driver road anger drives system altogether |
| US20200051428A1 (en) * | 2017-12-13 | 2020-02-13 | Tencent Technology (Shenzhen) Company Limited | Road condition generation method, apparatus and device, and storage medium |
| CN111197991A (en) * | 2020-01-15 | 2020-05-26 | 西安电子科技大学 | A method for predicting the best driving path of vehicles based on deep neural network |
| CN111486857A (en) * | 2019-01-28 | 2020-08-04 | 阿里巴巴集团控股有限公司 | Road network prediction tree construction method and device, electronic equipment and storage medium |
| CN111483465A (en) * | 2019-01-28 | 2020-08-04 | 阿里巴巴集团控股有限公司 | MPP expanding method and device, electronic equipment and storage medium |
| CN111566578A (en) * | 2018-02-27 | 2020-08-21 | 三星电子株式会社 | Autonomous driving device and method therefor |
| CN112109720A (en) * | 2020-09-09 | 2020-12-22 | 长安大学 | A system and method for monitoring and predicting the emotion of a bus driver |
| CN112512885A (en) * | 2020-10-12 | 2021-03-16 | 华为技术有限公司 | Driving assisting method and device and automobile |
| KR20210083048A (en) * | 2019-12-26 | 2021-07-06 | 엘지전자 주식회사 | Path providing device and path providing method thereof |
| CN113085861A (en) * | 2021-03-26 | 2021-07-09 | 银隆新能源股份有限公司 | Control method and device for automatic driving vehicle and automatic driving vehicle |
| CN113829989A (en) * | 2021-09-24 | 2021-12-24 | 岚图汽车科技有限公司 | Driving information prompting method and device, storage medium and electronic equipment |
| CN114299607A (en) * | 2021-12-13 | 2022-04-08 | 南京理工大学 | A method for analyzing the risk of collision between people and vehicles based on autonomous vehicles |
| CN114929541A (en) * | 2020-03-19 | 2022-08-19 | 宝马股份公司 | Method for operating a motor vehicle and motor vehicle |
| CN115290106A (en) * | 2022-07-14 | 2022-11-04 | 北京百度网讯科技有限公司 | A method, device, device and storage medium for determining an intersection path |
| US20230117426A1 (en) * | 2021-10-14 | 2023-04-20 | Mitac Digital Technology Corporation | Method and system for adaptively providing auxiliary driving information |
| US20230267549A1 (en) * | 2022-02-21 | 2023-08-24 | Carvi Inc. | Method of predicting the future accident risk rate of the drivers using artificial intelligence and its device |
| CN118211479A (en) * | 2024-03-26 | 2024-06-18 | 广东星唯信息技术有限公司 | Accurate evaluation method for simulated driving |
-
2023
- 2023-06-09 CN CN202310690071.8A patent/CN116952263B/en active Active
Patent Citations (22)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6711498B1 (en) * | 1999-09-08 | 2004-03-23 | Robert Bosch Gmbh | Method for operating a navigation system for a vehicle |
| JP2007327872A (en) * | 2006-06-08 | 2007-12-20 | Denso Corp | Driver personality determination device and vehicle navigation device |
| US8700251B1 (en) * | 2012-04-13 | 2014-04-15 | Google Inc. | System and method for automatically detecting key behaviors by vehicles |
| CN107270923A (en) * | 2017-06-16 | 2017-10-20 | 广东欧珀移动通信有限公司 | Method, terminal and storage medium for route push |
| US20200051428A1 (en) * | 2017-12-13 | 2020-02-13 | Tencent Technology (Shenzhen) Company Limited | Road condition generation method, apparatus and device, and storage medium |
| CN111566578A (en) * | 2018-02-27 | 2020-08-21 | 三星电子株式会社 | Autonomous driving device and method therefor |
| CN108827334A (en) * | 2018-08-09 | 2018-11-16 | 北京智行者科技有限公司 | A kind of automatic Pilot method |
| CN111483465A (en) * | 2019-01-28 | 2020-08-04 | 阿里巴巴集团控股有限公司 | MPP expanding method and device, electronic equipment and storage medium |
| CN111486857A (en) * | 2019-01-28 | 2020-08-04 | 阿里巴巴集团控股有限公司 | Road network prediction tree construction method and device, electronic equipment and storage medium |
| CN110525447A (en) * | 2019-10-09 | 2019-12-03 | 吉林大学 | A kind of the man-machine of anti-commercial vehicle driver road anger drives system altogether |
| KR20210083048A (en) * | 2019-12-26 | 2021-07-06 | 엘지전자 주식회사 | Path providing device and path providing method thereof |
| CN111197991A (en) * | 2020-01-15 | 2020-05-26 | 西安电子科技大学 | A method for predicting the best driving path of vehicles based on deep neural network |
| CN114929541A (en) * | 2020-03-19 | 2022-08-19 | 宝马股份公司 | Method for operating a motor vehicle and motor vehicle |
| CN112109720A (en) * | 2020-09-09 | 2020-12-22 | 长安大学 | A system and method for monitoring and predicting the emotion of a bus driver |
| CN112512885A (en) * | 2020-10-12 | 2021-03-16 | 华为技术有限公司 | Driving assisting method and device and automobile |
| CN113085861A (en) * | 2021-03-26 | 2021-07-09 | 银隆新能源股份有限公司 | Control method and device for automatic driving vehicle and automatic driving vehicle |
| CN113829989A (en) * | 2021-09-24 | 2021-12-24 | 岚图汽车科技有限公司 | Driving information prompting method and device, storage medium and electronic equipment |
| US20230117426A1 (en) * | 2021-10-14 | 2023-04-20 | Mitac Digital Technology Corporation | Method and system for adaptively providing auxiliary driving information |
| CN114299607A (en) * | 2021-12-13 | 2022-04-08 | 南京理工大学 | A method for analyzing the risk of collision between people and vehicles based on autonomous vehicles |
| US20230267549A1 (en) * | 2022-02-21 | 2023-08-24 | Carvi Inc. | Method of predicting the future accident risk rate of the drivers using artificial intelligence and its device |
| CN115290106A (en) * | 2022-07-14 | 2022-11-04 | 北京百度网讯科技有限公司 | A method, device, device and storage medium for determining an intersection path |
| CN118211479A (en) * | 2024-03-26 | 2024-06-18 | 广东星唯信息技术有限公司 | Accurate evaluation method for simulated driving |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116952263B (en) | 2025-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11067988B1 (en) | Interactive autonomous vehicle agent | |
| JP6074553B1 (en) | Information processing system, information processing method, and program | |
| US11275379B2 (en) | Vehicle control apparatus and method for controlling automated driving vehicle | |
| CN114061581B (en) | Ranking agents near an autonomous vehicle by mutual importance | |
| CN111583715B (en) | A vehicle trajectory prediction method, vehicle collision warning method, device and storage medium | |
| KR20230026961A (en) | Method and apparatus for predicting motion track of obstacle and autonomous vehicle | |
| CN113366497A (en) | Agent prioritization for autonomous vehicles | |
| RU2669501C2 (en) | Information presentation device and information presentation method | |
| JP4743275B2 (en) | Own vehicle route determination method and own vehicle route determination device | |
| KR20200094641A (en) | Method and device for performing multiple agent sensor fusion in cooperative driving based on reinforcement learning | |
| CN107901909B (en) | Control method and device for automatic lane replacement and controller | |
| US20210200230A1 (en) | Conditional behavior prediction for autonomous vehicles | |
| JP2019510677A (en) | Control data creation method for driver's rule-based assistance | |
| JP5587170B2 (en) | Driving support device and program | |
| US11131997B2 (en) | Route generation apparatus | |
| CN109213153B (en) | Automatic vehicle driving method and electronic equipment | |
| US20220379918A1 (en) | Vehicle behavior generation device, vehicle behavior generation method, and vehicle behavior generation program product | |
| CN114162144A (en) | Automatic driving decision method and device and electronic equipment | |
| CN110678914A (en) | Vehicle control device and method for control of an autonomous vehicle | |
| JP2017044474A (en) | On-vehicle device, lane change determination program, and lane change determination method | |
| WO2006102615A2 (en) | Crash prediction network with graded warning for vehicle | |
| US11657268B1 (en) | Training neural networks to assign scores | |
| CN116952263B (en) | Path prediction method, device, equipment and readable storage medium | |
| CN116513233A (en) | Method, computer system, readable medium for target selection near a vehicle | |
| CN110956299A (en) | Arrival time estimation method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 430109 Hubei Province, Wuhan City, Yunfeng Avenue 8, Wuhan Economic and Technological Development Zone Patentee after: Lantu Automotive Technology Co.,Ltd. Country or region after: China Address before: 430000 No. n3010, 3rd floor, R & D building, building n, Artificial Intelligence Science Park, Wuhan Economic and Technological Development Zone, Hubei Province Patentee before: Lantu Automobile Technology Co.,Ltd. Country or region before: China |