Andreas Wendel

Tesla just expanded their Robotaxi geofence in ATX. It's now 243 square miles, 3.7x larger than Waymo's. However, the Robotaxi fleet is only 25% of Waymo's size. And there remains human supervisors in the car during rides. I think this is a regulatory thing. Does Tesla's lack of mapping and simpler sensor suite mean that it can move faster and expand more than Waymo? Elon certainly thinks so.... "Tesla autonomous driving might spread faster than any technology ever. The hardware foundations have been laid for such a long time that a software update enables self-driving for millions of pre-existing cars in a short period of time."

230

83 Comments

Day 26 of 100 – LiDAR vs. RGB: Choosing the Right Tool I’ll admit — I’m a little behind on these posts. Life and business got in the way, and I didn’t want to sacrifice quality just to tick a box. Because quality matters. Speaking of quality — today’s post is about a recent project we completed with a forward-thinking engineering firm. They’re eager to integrate drone technology into their workflows, and one of the key conversations was around LiDAR vs. Photogrammetry (RGB). We started by capturing the site with photogrammetry. It gave us beautiful, accurate models — but the client needed something more: utility wires. That’s where LiDAR shines. Even the smallest details can be picked up when light penetrates through gaps where cameras fall short. Here’s a quick breakdown 👇 📸 Photogrammetry (RGB) Pros: High-resolution imagery, realistic textures. Cost-effective and widely accessible. Great for orthomosaics, 3D visuals, volumetrics, and contour maps. Cons: Struggles with thin objects like wires or dense vegetation. Accuracy can be limited without GCPs or RTK/PPK workflows. 🌐 LiDAR Pros: Exceptional at capturing fine details (wires, vegetation, small features). Penetrates through trees/brush to create accurate ground models. Highly accurate for surveys, TINs, and complex engineering workflows. Cons: More expensive to fly and process. Doesn’t produce the “pretty” visuals clients sometimes want on their reports. The takeaway? Neither is “better.” It’s about choosing the right tool for the problem. In this case, LiDAR and RGB together gave the client exactly what they needed — a detailed, accurate dataset for decision-making. 👉 My question for you: Do you think most industries understand the difference between LiDAR and photogrammetry yet, or is this still something we need to educate on? #100DaysOfLinkedIn #Drones #LiDAR #Photogrammetry #Engineering #Innovation

238

13 Comments

Tesla's recent pilot launch of its robotaxi service in Austin, Texas, marks a pivotal moment in the self-driving industry. This move could redefine the trajectory of autonomous vehicle (AV) deployment, challenging existing paradigms and setting new standards. Waymo is a technological cathedral (multi-sensor redundancy, $200K+ per unit, fine-tuned for dense urban complexity). But it’s a system that can’t scale to millions of consumers. Tesla, by contrast, is betting on brute-force AI, data, and commodity hardware to crack the hardest problem in tech with an Apple-like vertical stack. If Tesla succeeds at L4 or even robust L3 autonomy with just vision, we’ll look back at the last decade of LiDAR as the Maginot Line of autonomy; beautifully engineered, utterly bypassed❗️ #ComputerVision #SpatialIntelligence

544

199 Comments

The internet is arguing about LiDAR vs Vision after Waymo's fleet went offline during the SF power outage while Tesla's vision-only robotaxis kept running. Here's my take: You need both. But vision alone can do wonders. LiDAR is precise. It's great in controlled environments, but it doesn't scale without infrastructure, maps, and significant investment at every location. Vision adapts. It learns from the real world and works anywhere — no special conditions required. We see the exact same debate in logistics: Vision vs RFID. RFID needs a tag on every item, a reader at every checkpoint, and a controlled environment to function. It works, but it's expensive and doesn't scale easily. Vision just needs a camera. That doesn't mean sensors, LiDAR, or RFID don't have value; they absolutely do. But if I had to pick one to bet on, Vision. Every single time. It solves most of the problems at a fraction of the cost and complexity. And it doesn't require perfect conditions to work; it adapts to imperfect ones. That's how AI scales in the real world. #Vision #AI #Lidar #RFID #OCR #Barcode #Tesla

84

6 Comments

I spent the last year and a half building autonomous systems for orchards at Bonsai Robotics. The biggest surprise? Connectivity is the infrastructure problem nobody talks about. Everyone focuses on the robotics—the perception systems, the path planning, the manipulation. But when you're operating in a 500-acre almond orchard in Australia or the Central Valley, you're dealing with spotty cellular coverage, dust that degrades signal quality, and distances that make WiFi impractical. The robots can see. They can navigate. They can make decisions. But if they can't reliably communicate with fleet management systems or push telemetry data for analysis, you're running blind. This isn't just an ag problem. I've seen similar challenges in all off-road and remote applications, including marine robotics with Wave Gliders operating thousands of miles offshore, army tanks on the frontlines, and rail vehicles and trucks in rural ODDs. The solution isn't just "add more cellular towers." It requires edge computing architectures that let vehicles operate autonomously when connectivity drops, smart data prioritization that pushes critical telemetry first, and mesh networking between vehicles to create resilient communication networks. Connectivity infrastructure is as important as the autonomy stack itself. You can't deploy at scale without solving both. What connectivity challenges have you seen in deploying hardware in remote environments?

153

47 Comments

Waymo’s latest milestone — fully driverless freeway service — marks a major step forward not only for autonomous mobility, but for the broader AI ecosystem. Freeways may appear simple, yet the perception, sensing, and safety requirements behind this achievement push the limits of today’s photonics and AI-driven decision systems. At ficonTEC, we are proud to support this evolution behind the scenes. Our precision photonics assembly and test systems help enable the production of the advanced optical sensors — including next-generation LiDAR — that autonomous vehicles rely on for high-fidelity perception. These sensors feed the AI models that allow AVs to understand the environment, anticipate behavior, and make real-time decisions with safety and confidence. As autonomy extends from surface streets to high-speed freeways, both the AI algorithms and the photonics hardware powering them must perform at unprecedented levels. It is exciting to see this technology now deployed across Phoenix, Los Angeles, and the Bay Area. Autonomous driving is becoming a real transportation infrastructure — and AI is the engine behind it. Photonics is the vision system. And ficonTEC is proud to enable both. #AI, #Autonomusdriving, #waymo, #siliconphotonics, #ficonTEC,

43