DE102023126795A1 - Method for detecting a relevant alarm event, method for detecting a fire hazard, method for controlling a mobile security robot and mobile security robot - Google Patents

Abstract

Some examples relate to a computer-implemented method for detecting a relevant alarm event. The method comprises determining alarm information of an alarm event based on sensor information generated by one or more sensors of a mobile robot. The method further comprises detecting an unimportant alarm event based on the alarm information and storing information about the unimportant alarm event in a database if the alarm information meets at least a first criterion but does not meet a second criterion. In addition, the method comprises detecting a relevant alarm event based on the alarm information, triggering an output of an alarm to a control center, and storing information about the relevant alarm event in the database if the alarm information meets at least the second criterion.

Description

Technical field

Examples of implementation deal with the use of mobile robots for object protection and object monitoring.

background

Monitoring real estate (e.g., corporate buildings or public buildings such as airports) is a labor-intensive and expensive activity. Therefore, there is a need to support this activity with automation.

Summary

Some examples relate to a computer-implemented method for detecting a relevant alarm event. The method comprises determining alarm information of an alarm event based on sensor information generated by one or more sensors of a mobile robot. The method further comprises detecting an unimportant alarm event based on the alarm information and storing information about the unimportant alarm event in a database if the alarm information meets at least a first criterion but does not meet a second criterion. In addition, the method comprises detecting a relevant alarm event based on the alarm information, triggering an output of an alarm to a control center, and storing information about the relevant alarm event in a database if the alarm information meets at least the second criterion.

By using a mobile robot and automatically classifying alarm events, personnel deployment can be significantly reduced. For example, only relevant events require the control center's capacity. Yet, an overview of all events can still be provided.

Some examples involve a computer-implemented method for detecting a fire hazard. The method includes detecting a heat source based on sensor data from a thermal imaging camera of a mobile robot and receiving a sensor signal from a gas sensor or smoke detector of the mobile robot. The method further includes triggering a fire alarm based on the detected heat source and the sensor signal from the gas sensor or smoke detector.

By using a mobile robot with different sensors, the reliability of fire detection can be increased and the personnel required can be significantly reduced.

Some examples relate to a computer-implemented method for controlling a mobile security robot. The method includes generating two-dimensional map data based on three-dimensional image data of an area and calculating a movement route within the area for the mobile security robot. The method further includes triggering the mobile security robot to follow the movement route.

By using three-dimensional image data, movement routes can be defined and followed by the mobile security robot, even if no two-dimensional maps of the area to be guarded are available. This can significantly reduce personnel deployment.

Some examples involve a computer-implemented method for controlling a mobile security robot. The method includes determining biometric characteristics of a person based on a camera image of a mobile security robot and comparing the determined biometric characteristics with biometric characteristics of a plurality of authorized persons stored in a database. The method further includes triggering an alarm and tracking the person by the mobile security robot if the comparison does not result in a match with an authorized person.

By using a mobile security robot, the deployment of personnel can be significantly reduced and the risk to security personnel when pursuing unauthorized persons can be reduced.

Some examples involve a mobile patrol robot comprising a drone, one or more sensors configured to generate sensor information, and one or more processing circuits configured to detect a hazardous situation based on the sensor information and to launch the drone when a hazardous situation is detected. The drone is configured to provide video footage of an area of the hazardous situation.

By using a mobile security robot, personnel deployment can be significantly reduced. Even if the security robot is attacked, the drone can ensure continued surveillance.

Short character description

• 1 zeigt ein Flussdiagramm eines Verfahrens zum Erkennen eines relevanten Alarmevents;
• 2 zeigt eine schematische Darstellung eines mobilen Wachroboters;
• 3 zeigt eine schematische Darstellung einer Vorrichtung zum Erkennen eines relevanten Alarmevents;
• 4 zeigt ein Flussdiagramm eines Verfahrens zum Erkennen einer Brandgefahr;
• 5 zeigt ein Flussdiagramm eines Verfahrens zum Steuern eines mobilen Wachroboters;
• 6 zeigt ein Flussdiagramm eines Verfahrens zum Steuern eines mobilen Wachroboters; und
• 7 zeigt eine schematische Darstellung eines mobilen Wachroboters.

Some examples of devices and/or methods are explained in more detail below with reference to the accompanying figures. They show:

• 1 shows a flowchart of a procedure for detecting a relevant alarm event;
• 2 shows a schematic representation of a mobile security robot;
• 3 shows a schematic representation of a device for detecting a relevant alarm event;
• 4 shows a flowchart of a method for detecting a fire hazard;
• 5 shows a flowchart of a method for controlling a mobile guard robot;
• 6 shows a flowchart of a method for controlling a mobile guard robot; and
• 7 shows a schematic representation of a mobile security robot.

Description

Some examples will now be described in more detail with reference to the accompanying figures. However, other possible examples are not limited to the features of these detailed embodiments. These may include modifications of the features, as well as equivalents and alternatives to the features. Furthermore, the terminology used herein to describe particular examples is not intended to be limiting of other possible examples.

Throughout the description of the figures, identical or similar reference numerals refer to identical or similar elements or features, each of which may be implemented identically or in a modified form while providing the same or a similar function. Furthermore, in the figures, the thickness of lines, layers, and/or regions may be exaggerated for clarity.

When two elements A and B are combined using "or," this should be understood to disclose all possible combinations, i.e., only A, only B, and both A and B, unless explicitly defined otherwise in the individual case. Alternative wording for the same combinations may be "at least one of A and B" or "A and/or B." This applies equivalently to combinations of more than two elements.

When a singular form, such as "a," "an," and "the," is used, and the use of only a single element is neither explicitly nor implicitly defined as mandatory, further examples may also use multiple elements to implement the same functionality. When a functionality is described below as being implemented using multiple elements, further examples may implement the same functionality using a single element or a single processing entity. It is further understood that the terms "comprises," "comprising," "having," and/or "comprising," when used herein, describe the presence of the specified features, integers, steps, operations, processes, elements, components, and/or a group thereof, but do not preclude the presence or addition of one or more other features, integers, steps, operations, processes, elements, components, and/or a group thereof.

1 shows a flowchart of a computer-implemented method for detecting a relevant alarm event. The method 100 includes determining 110 alarm information of an alarm event based on sensor information generated by one or more sensors of a mobile robot. Furthermore, the method 100 includes detecting 120 an unimportant alarm event based on the alarm information and storing information about the unimportant alarm event in a database if the alarm information meets at least a first criterion but does not meet a second criterion. Additionally, the method 100 includes detecting 130 a relevant alarm event based on the alarm information, triggering an alarm to a control center, and storing information about the relevant alarm event in a database if the alarm information meets at least the second criterion.

By using a mobile robot and automatically classifying alarm events, personnel deployment can be significantly reduced. For example, only relevant events require the control center's capacity. Yet, an overview of all events can still be provided.

A relevant or important alarm event can be, for example, unauthorized access by a person or animal, a fire, an open door or window, a heavy water leak or a gas leak.

An unimportant or irrelevant alarm event can, for example, be a person or animal near (but outside) a critical area, a heat source, a tilted window or a small water leak.

An alarm event can be any event that deviates from a normal state. The presence of an alarm event can be determined based on sensor information generated by one or more sensors of a mobile robot. For example, the mobile robot can have one or more cameras (e.g., daylight camera, thermal imaging camera, infrared camera, and/or LIDAR camera) that provide images or videos as sensor information. Based on the images or videos, image recognition can be used to detect, for example, a person, an animal, a heat source, an open door, or an open window. Additionally or alternatively, the mobile robot can have a temperature sensor, a gas sensor, a smoke detector, and/or a microphone that provide a sensor signal or sensor values as sensor information.

The alarm information of an alarm event can be information that characterizes the event. For example, the alarm information can include an alarm parameter, such as a temperature, or the location of a heat source if the alarm event is a heat source or a fire. Alternatively, the alarm information can be information about a detected person or animal and the location of the detected person or animal.

Based on the alarm information received from the alarm event, the alarm event can be categorized into unimportant and relevant alarm events. For example, the alarm event may be of minor severity or of low importance, so that it is sufficient for the alarm event to be stored in a database (e.g., an electronic watch log). For this purpose, it can be determined that the alarm information meets a first criterion (e.g., a heat source exceeds a normal temperature range), but a second criterion is not met (e.g., the heat source does not exceed a dangerous temperature).

However, if a relevant alarm event is detected based on the received alarm information, immediate intervention may be necessary. Therefore, in addition to recording the occurrence of the relevant alarm event, an alarm is also triggered to a control center. This can be determined if the alarm information meets the second criterion (e.g., the heat source exceeds a dangerous temperature).

The alarm to the control center can be, for example, an acoustic alarm via a loudspeaker, a visual alarm via a screen or an alarm signal light, an automatic call and/or an automatic electronic message to a control center.

The control center is, for example, a security center manned by security guards, a police station or a gate of a building or area.

The information about unimportant alarm events and the information about the relevant alarm event can be stored in the same database or in different databases.

For example, the alarm information can include an alarm parameter, such as a temperature or a probability that a person has been detected. The first criterion can be met if the alarm parameter lies between a lower limit (e.g., elevated temperature or low probability that a person has been detected) and an upper limit (e.g., critical temperature or high probability that a person has been detected). The second criterion can be met if the alarm parameter lies below the lower limit or above the upper limit (e.g., critical temperature or high probability that a person has been detected).

The lower limit and/or the upper limit may be adjustable (e.g. via a configuration interface or configuration software, for example via user input or loading a configuration file).

For example, the alarm information can contain information about a detected person or animal and the location of the detected person or animal. The first criterion can be met if the location is outside a predefined critical area (e.g., outside property boundaries or at a sufficient distance from a guarded object). The second criterion can be met if the location is within a predefined critical area (e.g., within property boundaries, within a guarded building, or at an insufficient distance from a guarded object).

For example, the method 100 may include the mobile robot independently tracking the detected person or animal if the second criterion is met. This allows the position of the person or animal to be tracked until emergency services arrive.

Additionally or alternatively, the method 100 may include causing a drone to move to the location and take pictures of the Provides information about the detected person or animal (e.g., sends it to a control center or sends it locally or for storage) if the second criterion is met. This allows the situation to be monitored independently of the mobile robot.

Additionally or alternatively, method 100 may involve the control center taking over control of the movement of the mobile robot after detecting a relevant alarm event. This allows for a more precise manual clarification of the situation.

The mobile robot (e.g., a guard robot, robot dog, or security robot) can be a self-driving and/or ground-based robot or a drone. The mobile robot can be an autonomously driving robot. The mobile robot can be powered, for example, by a built-in accumulator or battery that can be charged at a charging station.

The method 100 may be performed entirely or partially on a mobile robot (e.g. 2 ) or be carried out completely or partially on a device separate from the mobile robot (e.g. 3 ) can be executed.

The method 100 can, for example, use software to record all predefined events and document them in an electronic patrol log (EWB). The software can allow scaling (e.g., via adjustable thresholds) for the areas of heat sources, water leaks, person and animal detection, and/or gas leaks (e.g., also smoke detection), right up to ambient air quality measurements. This scaling can be used, for example, to specify the measured value at which an entry is made in the EWB and the reference value at which an alarm is transmitted to the alarm receiving center. The alarm receiving center can, for example, be able to take over control to gain a precise picture of the situation on site. The robot can then take over again and continue its predefined autonomous patrol route. All events entered in the EWB can be viewed at any time (e.g., via online access) (e.g., by authorized users).

Further details and aspects are mentioned in connection with the examples described above or below. 1 The example shown may include one or more optional additional features corresponding to one or more aspects related to the proposed concept or one or more aspects described below (e.g. 2-7 ) examples are mentioned.

2 shows a schematic representation of a mobile security robot. The mobile security robot 200 comprises one or more sensors 210 configured to generate sensor information. Furthermore, the mobile security robot 200 comprises one or more processing circuits 220 configured to determine alarm information of an alarm event based on the sensor information and to detect an unimportant alarm event based on the alarm information and to initiate storage of information about the unimportant alarm event in a database if the alarm information meets at least a first criterion but does not meet a second criterion. In addition, the one or more processing circuits 220 are configured to detect a relevant alarm event based on the alarm information, trigger the output of an alarm to a control center, and store information about the relevant alarm event in a database if the alarm information meets at least the second criterion.

By using a mobile security robot and automatically classifying alarm events, personnel deployment can be significantly reduced. For example, only relevant events require the control center's capacity. Yet, an overview of all events can still be provided.

The mobile security robot 200 may have wheels, legs, or a track to enable it to move on the ground. The mobile security robot 200 may be a self-propelled and/or ground-based security robot. The mobile security robot 200 may be an autonomously driving security robot. The mobile security robot 200 may be powered, for example, by a built-in accumulator or battery that can be charged at a charging station.

Further details and aspects are mentioned in connection with the examples described above or below. 2 The example shown may comprise one or more optional additional features corresponding to one or more aspects related to the proposed concept or one or more of the above (e.g. 1 ) or below (e.g. 3-7 ) examples are mentioned.

3 shows a schematic representation of a device for detecting a relevant alarm event. The device 300 comprises one or more processing circuits 310 and one or more memory devices 320. The one or more processing circuits 310 are designed to evaluate sensor information received from one or more sensors of a mobile robot to determine alarm information of an alarm event. Furthermore, the one or more processing circuits 310 are configured to detect an unimportant alarm event based on the alarm information and store information about the unimportant alarm event in a database if the alarm information meets at least a first criterion but does not meet a second criterion. In addition, the one or more processing circuits 310 are configured to detect a relevant alarm event based on the alarm information, trigger an output of an alarm to a control center, and store information about the relevant alarm event in the database if the alarm information meets at least the second criterion.

By using a mobile robot and automatically classifying alarm events, personnel deployment can be significantly reduced. For example, only relevant events require the control center's capacity. Yet, an overview of all events can still be provided.

The one or more processing circuits 310 may, for example, be one or more processors (e.g., CPU or GPU) or may be implemented as an ASIC or FPGA or another hardware component.

The device 300 can, for example, be part of a mobile robot. Alternatively, the device 300 can be implemented in a data center or in a company's IT infrastructure.

Further details and aspects are mentioned in connection with the examples described above or below. 3 The example shown may comprise one or more optional additional features corresponding to one or more aspects related to the proposed concept or one or more of the above (e.g. 1-2 ) or below (e.g. 4-7 ) examples are mentioned.

4 shows a flowchart of a computer-implemented method for detecting a fire hazard. The method 400 includes detecting 410 a heat source based on sensor data from a thermal imaging camera of a mobile robot and receiving 420 a sensor signal from a gas sensor or smoke detector of the mobile robot. Furthermore, the method 400 includes triggering 430 a fire alarm based on the detected heat source and the sensor signal from the gas sensor or smoke detector.

By using a mobile robot with different sensors, the reliability of fire detection can be increased and the personnel required can be significantly reduced.

The thermal imaging camera can generate sensor data in the form of images of an area in which the mobile robot is located. Through image analysis (e.g., by the robot or by a processing unit that receives the images from the robot), heat sources can be detected.

Furthermore, the mobile robot may have a gas sensor and/or a smoke detector that generates a sensor signal. The sensor signal may contain information about the amount of gas and/or smoke in the air.

For example, a fire or fire hazard can be detected when an area in a thermal imaging camera image indicates that a threshold temperature has been exceeded and the sensor signal indicates information about the amount of gas and/or smoke in the air above a predetermined threshold.

A fire alarm can be triggered, for example, by sending an alarm signal to an alarm system (e.g. to trigger an acoustic or optical signal), by sending an alarm signal to a control center or a fire department.

Method 400 may further include providing a video stream from a camera (e.g., an HD camera) of the mobile robot to a control center when a fire alarm is triggered. The video stream may include footage from the location of the heat source. This may allow a control center to be automatically informed of the current situation.

For example, redundant testing can be performed using combined technology (e.g., gas sensor, thermal imaging camera, and HD camera). To avoid false alarms, the software could use multiple reference values from different sensors for redundancy. For example, the thermal imaging camera could report a heat or heat source above the preset reference value. At the same time, the gas sensor can check whether smoke particles are already being detected in the air, and the HD camera can send images from the corresponding device or location.

Further details and aspects are mentioned in connection with the examples described above or below. 4 example shown may include one or more optional additional features that may be associated with one or more aspects related to the proposed concept or one or more of the above (e.g. 1-3 ) or below (e.g. 5-7 ) examples are mentioned.

5 shows a flowchart of a computer-implemented method for controlling a mobile security robot. The method 500 includes generating 510 two-dimensional map data based on three-dimensional image data of an area and calculating 520 a movement route within the area for the mobile security robot. Furthermore, the method 500 includes triggering 530 a travel of the movement route by the mobile security robot.

By using three-dimensional image data, movement routes can be defined and followed by the mobile security robot, even if no two-dimensional maps of the area to be guarded are available. This can significantly reduce personnel deployment.

Three-dimensional image data can be used to generate data for a three-dimensional representation of the area, and these data can be reduced to two-dimensional map data.

The movement route of the mobile security robot can be determined, for example, using route optimization algorithms. For this purpose, the start and end points, optional intermediate points, and other optional parameters can be specified so that the movement route can be calculated automatically. For example, an optional parameter can be that the area contains a building and the movement route runs along at least one or all of the building's exterior walls. The area can contain multiple buildings or other objects, or it can be a building or part of a building.

The mobile guard robot's travel along the movement route can be triggered, for example, by sending the travel route to the mobile guard robot (e.g., if the guard robot has not calculated the travel route itself) and an activation signal. Alternatively, the guard robot can calculate the travel route itself and travel along the movement route in response to a received activation signal or based on a schedule. Method 500 can include repeatedly triggering the mobile guard robot's travel along the movement route. This allows an area or object to be repeatedly traveled and guarded. The time intervals between successive repetitions of the travel can vary. This can increase safety because the appearance of the guard robot is less predictable for an observer.

Method 500 may further include calculating a second movement route within the area for the mobile guard robot. For example, the first movement route differs from the second movement route. Additionally, triggering the mobile guard robot to follow the second movement route may be included. This may increase safety because the guard robot's movement is less predictable for an observer.

For example, a mobile security robot or a drone can take a series of three-dimensional images (e.g., using a LIDAR sensor, a radar sensor, or a time-of-flight sensor). The three-dimensional images can be combined to create three-dimensional image data for an area.

For example, a 3D lidar sensor (e.g., on a mobile robot or a drone) can capture an image of the current location and feed it into software, which is then converted into a 2D representation. This allows waypoints to be set for the mobile robot's autonomous operation. For example, it is then no longer necessary to have current plans of the terrain or buildings on hand. The robot can autonomously travel its patrol area at predefined time intervals and then return to its charging station. The software can evaluate whether the loop can be completed based on the battery level or whether it should return to the charging station immediately.

For example, in addition to Wi-Fi, there may be the option of having the mobile robot send waypoints using QR code, NFC and/or GPS.

Further details and aspects are mentioned in connection with the examples described above or below. 5 The example shown may comprise one or more optional additional features corresponding to one or more aspects related to the proposed concept or one or more of the above (e.g. 1-4 ) or below (e.g. 6-7 ) examples are mentioned.

Some examples relate to a device for controlling a mobile guard robot, as described by 5 The device comprises one or more processing circuits and one or more memory devices. The one or more processing circuits may be configured to generate two-dimensional map data based on three-dimensional image data of an area, calculate a movement route on the area for the mobile guard robot, and trigger a travel of the movement route by the mobile guard robot.

The device can, for example, be part of a mobile security robot. Alternatively, the device can be implemented in a data center or in a company's IT infrastructure.

Further details and aspects are mentioned in connection with the examples described above or below.

6 shows a flowchart of a computer-implemented method for controlling a mobile security robot. The method 600 includes determining 610 biometric characteristics of a person based on a recording from a camera of a mobile security robot and comparing 620 the determined biometric characteristics with biometric characteristics of a plurality of authorized persons stored in a database. Furthermore, the method 600 includes triggering 630 an alarm and tracking the person by the mobile security robot if the comparison does not result in a match with an authorized person.

By using a mobile security robot, the deployment of personnel can be significantly reduced and the risk to security personnel when pursuing unauthorized persons can be reduced.

Camera footage can show one or more people, partially or completely. For example, facial recognition algorithms can determine a person's biometric characteristics based on such footage.

When comparing with the biometric characteristics of authorized individuals, it may be sufficient that there is sufficient similarity between the characteristics. For example, a probability can be calculated that an authorized individual was recognized in the comparison. If the calculated probability exceeds a specified or adjustable threshold, the individual can be recognized as an authorized individual, thus a match is detected. The comparison can be terminated as soon as a match is detected.

If no match is found with a person in the database, an alarm can be triggered. This can, for example, send security guards or alert the police.

Until security personnel or the police arrive or until the situation is clarified, the security robot can track the unauthorized person to prevent escape.

Additionally, the security robot can, for example, prompt the person via an acoustic signal to identify themselves more clearly (e.g., removing a hat or mask), and the biometric characteristics can be re-determined based on new images. A new comparison can then be made with people in the database.

For example, in combination with visitor management software (e.g., digital gate), prior registration for autonomous access can allow a photo or biometric data of the visitor or service provider to be stored in the database. This can be compared with the corresponding authorization during the robot's patrols. If authorization only applies to certain areas or certain routes and these do not match the visitor's current location, a notification can be sent to the host or security service.

For example, visitors can pre-register using the digital gate software and upload data (e.g., ID card and/or signature for occupational health and safety instructions) into the system. The data can be stored on a secure server. The robot can access this server and, using a biometric scan, determine whether the person has access authorization or is on the premises without authorization. If this is the case, the robot can immediately send a message to the alarm receiving center, and an intervention can be triggered. The robot can then use its camera system to monitor the person until an appropriate response is received.

Further details and aspects are mentioned in connection with the examples described above or below. 6 The example shown may comprise one or more optional additional features corresponding to one or more aspects related to the proposed concept or one or more of the above (e.g. 1-5 ) or below (e.g. 6-7 ) examples are mentioned.

7 shows a schematic representation of a mobile security robot. The mobile security robot The drone 700 includes a drone 710, one or more sensors 210 configured to generate sensor information, and one or more processing circuits 220 configured to detect a hazardous situation based on the sensor information and to launch the drone 710 when a hazardous situation is detected. The drone 710 is configured to provide video recordings of an area of the hazardous situation.

By using a mobile security robot, personnel deployment can be significantly reduced. Even if the security robot is attacked, the drone can ensure continued surveillance.

In the event of an alarm, for example, a drone can autonomously launch from the back of the robot to the alarm location and transmit images from above to the control center. In the event of an attack on the robot on the ground, images of the operation can still be transmitted.

Further details and aspects are mentioned in connection with the examples described above or below. 6 The example shown may comprise one or more optional additional features corresponding to one or more aspects related to the proposed concept or one or more of the above (e.g. 1-6 ) or examples described below.

Some examples relate to a mobile security robot comprising a marking device, one or more sensors configured to generate sensor information, and one or more processing circuits configured to detect an unauthorized person based on the sensor information and to activate the marking device when an unauthorized person is detected. The marking device is configured to spray a marking substance (e.g., artificial DNA) onto the unauthorized person.

The one or more processing circuits may be configured to determine a location of the unauthorized person based on the sensor information and to trigger an alignment of the marking device (e.g., by controlling the movement of the mobile guard robot and/or the marking device) such that the unauthorized person is within range and spray direction of the marking device.

The unauthorized person could be, for example, a burglar or saboteur or another person who does not have access permission to a particular area.

Further details and aspects are mentioned in connection with the examples described above or below.

Some examples relate to mobile robots (e.g., guard robots, robot dogs, or security robots) with the functions of monitoring (e.g., reporting human and animal presence), fire, gas, water damage, open doors and/or windows, and forwarding these to humans, control centers, technicians, and/or further processing software (e.g., electronic guard logs or digital gates). Furthermore, a mobile robot could retrieve information from an electronic guard log (e.g., a database with information about alarm events) or a digital gate or digital visitor management system (e.g., a database with information about authorized persons) and further process it (e.g., comparing access authorizations and/or residence permits) and/or comparing target/actual values of specified human and technical parameters/specifications.

Additionally or alternatively, the mobile robot can also access or be linked to installed alarm systems (e.g., alarm system or fire alarm system) and/or be used for water damage detection, for checking open doors and windows, and/or for corresponding documentation in an electronic watch log. For example, redundant monitoring can be enabled. For example, existing alarm systems can be connected to the robot's system and the alarm location can be automatically controlled with live transmission to an alarm receiving center and/or video control center. All occurrences and/or events can be documented in an electronic watch log (e.g., database with information on alarm events), and an alarm can be triggered in the control center when defined events occur (e.g., 1-3 ).

For example, by combining and/or replacing digital surveillance technology with, among other things, software for digital visitor management, comparing person recognition and checking the authorization to stay in certain areas or generally on the premises and integrating it into security and reporting systems, faster alarm tracking and/or more automated recording in an EWB can be achieved.

The camera systems in combination with the thermal imaging camera of a mobile robot can, for example, detect open windows, doors and/or of the roof hatches. Additionally or alternatively, water pipe damage or other liquid leaks can be reported via the thermal imaging camera of a mobile robot and/or fire detection can be enabled in combination with the gas sensors (e.g. 4 ).

Furthermore, a mobile robot can also be used in combination with one or more of the other functions for occupational health and safety testing (e.g. checking the validity of the sticker on fire extinguishers).

The above-mentioned findings (data) may be transmitted to third parties, for example to carry out and/or monitor repairs, inspections and/or maintenance.

A robot can optionally also be designed as a mobile launch pad for isolated technical devices (e.g. drones, stationary data collectors or other independently operating (e.g. AI-based), mobile or immobile devices).

A mobile robot can, for example, be used to monitor properties and/or link various technical monitoring devices.

The use of the technology described above can be used to save on stationary (e.g. surveillance) technology (e.g. unnecessary video surveillance or measuring technology, e.g. for machine monitoring).

The concepts described can, for example, result in cost savings compared to the isolated use of different systems, purely staffed and/or the use of stationary (monitoring) technology, rapid intervention in the event of alarms, rapid reaction in the event of water damage and fire, detection of devices that are still switched on and pose a fire hazard, rapid transmission of open windows or skylights to prevent burglary or water damage caused by heavy rainfall, transmission of gas leaks, redundant testing using combined technology (e.g. gas sensor, thermal imaging camera, HD camera), seamless recording of incidents, automatic notification in the event of system malfunctions or sabotage, near real-time streaming via VR glasses for the control center, audio pattern recognition to compare possible hazards (e.g. voices, bangs or broken glass), ID card recognition or NFC chip comparison for employee recognition, operation of an elevator, activation of light switches and/or connection to the building automation system and/or property marking (e.g. spraying artificial DNA on a person or object in the event of sabotage).

Some examples relate to a computer program with program code for performing a described method when the computer program is executed on one or more computers or processors. A computer-implemented method is, for example, a method whose steps are carried out on one or more computers, one or more processors, or one or more other programmable hardware components. The one or more computers, one or more processors, or one or more other programmable hardware components can be located at one location or distributed.

Some examples relate to a machine-readable storage medium containing program code that, when executed, causes a machine to perform one of the described methods.

The aspects and features described in connection with a particular one of the previous examples may also be combined with one or more of the further examples to replace an identical or similar feature of that further example or to additionally introduce the feature into the further example.

Examples may further include or relate to a (computer) program having program code for performing one or more of the above methods when the program is executed on a computer, a processor, or other programmable hardware component. Steps, operations, or processes of various of the methods described above may therefore also be performed by programmed computers, processors, or other programmable hardware components. Examples may also cover program storage devices, e.g., digital data storage media, that are machine-, processor-, or computer-readable and encode or contain machine-executable, processor-executable, or computer-executable programs and instructions. The program storage devices may include, for example, digital memories, magnetic storage media such as magnetic disks and magnetic tapes, hard disk drives, or optically readable digital data storage media.

Other examples may also include computers, processors, control units, field-programmable logic arrays ((F)PLAs = (Field) Programmable Logic Arrays), field-programmable gate arrays ((F)PGA = (Field) Programmable Gate Arrays), graphics processors (GPU = Graphics Processor Unit), application-specific integrated circuits (ASIC = application-specific integrated circuit), integrated circuits (IC = Integrated Circuit) or single-chip systems (SoC = System-on-a-Chip) programmed to carry out the steps of the methods described above.

It is further understood that the disclosure of multiple steps, processes, operations, or functions disclosed in the specification or claims should not be construed as necessarily being in the described order, unless explicitly stated in the individual case or absolutely necessary for technical reasons. Therefore, the foregoing description does not limit the performance of multiple steps or functions to any particular order. Furthermore, in further examples, a single step, function, process, or operation may include and/or be broken down into multiple sub-steps, functions, processes, or operations.

If some aspects in the preceding sections were described in connection with a device or system, these aspects are also to be understood as a description of the corresponding method. For example, a block, a device, or a functional aspect of the device or system can correspond to a feature, such as a method step, of the corresponding method. Accordingly, aspects described in connection with a method are also to be understood as a description of a corresponding block, a corresponding element, a property, or a functional feature of a corresponding device or system.

The following claims are hereby incorporated into the Detailed Description, with each claim being capable of standing on its own as a separate example. It should also be noted that although a dependent claim in the claims refers to a particular combination with one or more other claims, other examples may include a combination of the dependent claim with the subject matter of any other dependent or independent claim. Such combinations are hereby explicitly contemplated unless it is specifically stated that a particular combination is not intended. Furthermore, features of a claim for any other independent claim are also intended to be included, even if that claim is not directly defined as being dependent on that other independent claim.

Claims (18)

A computer-implemented method (100) for detecting a relevant alarm event, the method comprising: Determining (110) alarm information of an alarm event based on sensor information generated by one or more sensors of a mobile robot; Detecting (120) a non-relevant alarm event based on the alarm information and storing information about the non-relevant alarm event in a database if the alarm information meets at least a first criterion but does not meet a second criterion; Detecting (130) a relevant alarm event based on the alarm information, triggering an alarm output to a control center, and storing information about the relevant alarm event in a database if the alarm information meets at least the second criterion. Procedure according to Claim 1 , wherein the alarm information comprises an alarm parameter, wherein the first criterion is met when the alarm parameter is between a lower limit and an upper limit, wherein the second criterion is met when the alarm parameter is below the lower limit or above the upper limit. Procedure according to Claim 2 , whereby at least the lower limit or the upper limit can be adjusted. Method according to one of the preceding claims, wherein the alarm information comprises information about a detected person or animal and a location of the detected person or animal, wherein the first criterion is met if the location lies outside a predefined critical area, wherein the second criterion is met if the location lies within a predefined critical area. Procedure according to Claim 4 , further comprising causing a drone to move to the location and provide images of the detected person or animal if the second criterion is met. Procedure according to Claim 4 or 5 , further comprising autonomous tracking of the detected person or animal by the mobile robot if the second criterion is met. Method according to one of the preceding claims, further comprising taking over control of the movement of the mobile robot by the control center after detecting a relevant alarm event. A computer-implemented method (400) for detecting a fire hazard, the method comprising: Detecting (410) a heat source based on sensor data from a thermal imaging camera of a mobile robot; Receiving (420) a sensor signal from a gas sensor or smoke detector of the mobile robot; Triggering (430) a fire alarm based on the detected heat source and the sensor signal from the gas sensor or smoke detector. The procedure according to Claim 8 , further comprising providing a video stream from a camera of the mobile robot to a control center when a fire alarm is triggered, the video stream comprising footage of the location of the heat source. A computer-implemented method (500) for controlling a mobile security robot, the method comprising: generating (510) two-dimensional map data based on three-dimensional image data of an area; calculating (520) a movement route within the area for the mobile security robot; and triggering (530) the mobile security robot to follow the movement route. Procedure according to Claim 10 , wherein the area comprises a building, wherein the movement route runs along at least one outer wall of the building. Method according to one of the Claims 10 - 11 , further comprising: calculating a second movement route on the area for the mobile guard robot; and triggering a travel of the second movement route by the mobile guard robot, wherein the first movement route is different from the second movement route. Method according to one of the Claims 10 - 12 , further comprising repeatedly triggering the mobile guard robot to follow the movement route. Procedure according to Claim 13 , whereby the time intervals between successive repetitions of the run vary. Method according to one of the Claims 10 - 14 , further comprising generating the three-dimensional recording data of the area by the mobile guard robot or a drone. A computer-implemented method (600) for controlling a mobile security robot, the method comprising: determining (610) biometric characteristics of a person based on a camera image of a mobile security robot; comparing (620) the determined biometric characteristics with biometric characteristics of a plurality of authorized persons stored in a database; and triggering (630) an alarm and tracking the person by the mobile security robot if the comparison does not result in a match with an authorized person. A mobile patrol robot (700) comprising: a drone (710); one or more sensors (210) configured to generate sensor information; one or more processing circuits (220) configured to: detect a hazardous situation based on the sensor information; and launch the drone when a hazardous situation is detected, wherein the drone is configured to provide video footage of an area of the hazardous situation. Computer program with a program code for carrying out the method according to one of the Claims 1 - 16 when the computer program is executed on one or more computers or processors.

Images