# Autonomous Vehicles — Research Brief

**Topic slug:** `autonomous-vehicles`
**Generated:** 2026-11-21T15:36:03Z
**Articles indexed (all-time):** 1439
**Articles in last 30 days:** 49
**Language:** en
**Canonical:** https://wpnews.pro/research/topic/autonomous-vehicles

This brief aggregates curated AI news on the topic "Autonomous Vehicles" for AI research
agents. Each article cites its original source URL. Drop this content directly
into an LLM context window for full topical awareness.

## Top entities mentioned

- **arXiv** — 26 articles
- **NVIDIA** — 13 articles
- **Tesla** — 11 articles
- **Waymo** — 9 articles
- **Nvidia** — 9 articles
- **GPT-6 Astra** — 6 articles
- **CARLA** — 5 articles
- **Hugging Face** — 5 articles
- **Baidu** — 5 articles
- **NVIDIA DRIVE AGX Thor** — 4 articles
- **Apollo World** — 4 articles
- **Apollo Go** — 4 articles
- **OpenAI** — 4 articles
- **National Highway Traffic Safety Administration** — 4 articles
- **Alpamayo 2 Edge** — 3 articles


## Top sources

- arxiv.org — 25 articles
- machinebrief.com — 8 articles
- dev.to — 4 articles
- runtimewire.com — 4 articles
- explainx.ai — 3 articles
- cryptobriefing.com — 3 articles
- blog.us.fixstars.com — 3 articles
- developer.nvidia.com — 2 articles
- pub.towardsai.net — 2 articles
- ibtimes.co.uk — 2 articles


## Timeline — last 30 days (49 articles)

- **2026-11-20** — Italy Approves Tesla Assisted Driving: Provisional TAD Before EU-Wide Recognition [explainx.ai] (https://explainx.ai/blog/italy-tesla-assisted-driving-provisional-approval-november-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog)
- **2026-11-18** — Build Training-Ready Physical AI Datasets with Two Prompts in NVIDIA Cosmos [developer.nvidia.com] (https://developer.nvidia.com/blog/build-training-ready-physical-ai-datasets-with-two-prompts-in-nvidia-cosmos/)
- **2026-11-18** — AR-WAM: efficient streaming world-action modeling for autonomous driving [arxiv.org] (https://arxiv.org/abs/2611.21851)
- **2026-11-18** — GridDriver: On-Board BEV-Based Language Planning and Reasoning [arxiv.org] (https://arxiv.org/abs/2611.21924)
- **2026-11-18** — Benchmarking Deep Learning Models for Wheelchair Configuration Classification in Accessible Automated Vehicle Applications [arxiv.org] (https://arxiv.org/abs/2611.21945)
- **2026-11-17** — Test Automation to Agentic Validation: Building Governed AI Agents for Physical AI Systems [pub.towardsai.net] (https://pub.towardsai.net/test-automation-to-agentic-validation-building-governed-ai-agents-for-physical-ai-systems-e5c9f4fe6aa9?source=rss----98111c9905da---4)
- **2026-11-16** — Driverless Electric Cars Spotted Pulling Out of Parking Spaces in the Middle of the Night [ibtimes.co.uk] (https://www.ibtimes.co.uk/waymo-driverless-taxis-honking-san-francisco-1832427)
- **2026-11-16** — Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception [arxiv.org] (https://arxiv.org/abs/2611.17438)
- **2026-11-16** — Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles [arxiv.org] (https://arxiv.org/abs/2611.17505)
- **2026-11-15** — Ethiopia Banned Petrol Cars but Climate Was Never the Real Story [energytransitionafrica.com] (https://www.energytransitionafrica.com/insights/article/ethiopia-ev-ban-explainer-africa-energy-transition-2026)
- **2026-11-14** — University of Florida's DWM Slashes AI Safety Verification Errors by 127x [alphasignal.ai] (https://alphasignal.ai/news/university-of-florida-s-dwm-slashes-ai-safety-verification-errors-by-127x)
- **2026-11-13** — The researcher creating AI vision models as powerful as the human eye [news.northeastern.edu] (https://news.northeastern.edu/2026/11/13/machine-vision-algorithm-shadow-research/)
- **2026-11-13** — NVIDIA BirdDreams: Joint BEV and Camera Driving World Model [explainx.ai] (https://explainx.ai/blog/nvidia-birddreams-driving-world-model-bev-perspective-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog)
- **2026-11-12** — Qvyon launches with $8M to improve safety for physical AI deployments [siliconangle.com] (https://siliconangle.com/2026/11/12/qvyon-launches-with-8m-to-improve-safety-for-physical-ai-deployments/)
- **2026-11-11** — Serve Robotics wants to democratize sidewalk delivery robots [theverge.com] (https://www.theverge.com/transportation/1030902/serve-robotics-open-developer-api-sidewalk-delivery)
- **2026-11-11** — URL-Sim: Unified and Regulated LiDAR Simulation for High-Fidelity Reconstruction of Dynamic Driving Scenes [arxiv.org] (https://arxiv.org/abs/2611.12932)
- **2026-11-11** — Finland Approves Tesla Assisted Driving After FSD Name Change [explainx.ai] (https://explainx.ai/blog/finland-tesla-assisted-driving-traficom-approval-november-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog)
- **2026-11-10** — Nvidia Alpamayo 2 Edge brings real-time, self-explaining AI to vehicles [cryptobriefing.com] (https://cryptobriefing.com/nvidia-alpamayo-2-edge-real-time-vehicle-ai/)
- **2026-11-10** — Running AV Reasoning Models Within Onboard Compute and Latency Limits [developer.nvidia.com] (https://developer.nvidia.com/blog/running-av-reasoning-models-within-onboard-compute-and-latency-limits/)
- **2026-11-09** — Nvidia Releases Cosmos 3 Family, Four Open-Weight Nano Checkpoints for Interactive World Simulation [epyhia.com] (https://epyhia.com/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for)
- **2026-11-09** — NVIDIA Physical AI in Korea: Samsung Cuts a Chip Thermal Solve From 18 Hours to 41 Seconds, Kakao Targets Level 4, LG Trains CLOiD [storagereview.com] (https://www.storagereview.com/news/nvidia-physical-ai-korea-samsung-physicsnemo-kakao-level-4-lg-cloid)
- **2026-11-09** — World Models and China’s Humanoid Certification Gap [hellochinatech.com] (https://hellochinatech.com/p/china-humanoid-world-model-certification)
- **2026-11-09** — eSharp: Diffusion-based Sharp Monocular Metric Event-to-Depth Estimation [arxiv.org] (https://arxiv.org/abs/2611.08731)
- **2026-11-07** — Fooling and blinding self-driving cars in different ways: 30 km/h into 80 km/h with just a flashlight & more. 🚗🛑🔦😵‍💫💥 [it4sec.substack.com] (https://it4sec.substack.com/p/fooling-and-blinding-self-driving)
- **2026-11-06** — VFlash: Enabling System-1 VLMs for Physical AI [research.nvidia.com] (https://research.nvidia.com/labs/lpr/vflash/)
- **2026-11-06** — VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding [aiflash.com] (https://aiflash.com/news/146613/)
- **2026-11-06** — Regulating Autonomous Mobility-on-Demand Operators with Fixed and Adaptive Penalties: A Multi-Agent Reinforcement Learning Approach [arxiv.org] (https://arxiv.org/abs/2611.07122)
- **2026-11-06** — Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving [arxiv.org] (https://arxiv.org/abs/2611.07081)
- **2026-11-05** — New Era of Robot Safety: How VLA Policies Are Rewriting Autonomous Driving Rules! [dev.to] (https://dev.to/amrithesh_dev/new-era-of-robot-safety-how-vla-policies-are-rewriting-autonomous-driving-rules-2ao7)
- **2026-11-05** — NVIDIA details four open-weight Cosmos 3 checkpoints for driving and robot simulation [runtimewire.com] (https://runtimewire.com/article/nvidia-cosmos-3-open-checkpoints-interactive-world-simulation)
- **2026-11-05** — New NVIDIA Cosmos 3 Open Models for Interactive World Simulation [huggingface.co] (https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation)
- **2026-11-05** — Baidu Tests a New Way to Train Robotaxis [technode.com] (https://technode.com/2026/11/05/baidu-tests-a-new-way-to-train-robotaxis/)
- **2026-11-05** — Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds [arxiv.org] (https://arxiv.org/abs/2611.05569)
- **2026-11-04** — Parallel Domain launches PD Forma to turn raw fleet logs into simulation-ready worlds [runtimewire.com] (https://runtimewire.com/article/parallel-domain-pd-forma-launch)
- **2026-11-04** — Baidu launches Apollo World model to train robotaxis in simulated environments [technode.com] (https://technode.com/2026/11/04/baidu-launches-apollo-world-model-to-train-robotaxis-in-simulated-environments/)
- **2026-11-04** — Baidu’s new AI simulator gives robotaxis a crash course in rare road hazards [scmp.com] (https://www.scmp.com/tech/big-tech/article/3373173/baidus-new-ai-simulator-gives-robotaxis-crash-course-rare-road-hazards)
- **2026-11-03** — Baidu unveils Apollo World, an agent-driven world model for physical AI [cryptobriefing.com] (https://cryptobriefing.com/baidu-unveils-apollo-world-model/)
- **2026-11-03** — Toyota shows off SoC that stores model weights and its OS on integrated memory [machinebrief.com] (https://www.machinebrief.com/news/toyota-shows-off-soc-that-stores-model-weights-and-its-os-on-1uce)
- **2026-11-02** — OSWAM: An Effective World Action Model with One-Step Action Generation [aiflash.com] (https://aiflash.com/news/144143/)
- **2026-11-02** — Shinpei Kato brings AI planners into Autoware 2.0 without dropping the rule-based stack [runtimewire.com] (https://runtimewire.com/article/shinpei-kato-autoware-2-0-tier-iv-arm-aws-red-hat)
- **2026-10-31** — GAC starts mass-producing Level 4 robotrucks in China [asia-tech-news.ghost.io] (https://asia-tech-news.ghost.io/gac-starts-mass-producing-level-4-pony-ai-robotrucks/)
- **2026-10-30** — Edge-to-Cloud Swarm Coordination for autonomous urban air mobility routing with ethical auditability baked in [dev.to] (https://dev.to/rikinptl/edge-to-cloud-swarm-coordination-for-autonomous-urban-air-mobility-routing-with-ethical-50an)
- **2026-10-29** — Event Report: Zoox on Measurable Software Assurance at AV & AI USA 2026 [blog.us.fixstars.com] (https://blog.us.fixstars.com/event-report-zoox-on-measurable-software-assurance-at-av-ai-usa-2026/)
- **2026-10-29** — Leonardo brings Shield AI’s Hivemind to Royal Navy Proteus helicopter [aerotime.aero] (https://www.aerotime.aero/articles/leonardo-shield-ai-hivemind-royal-navy-proteus)
- **2026-10-26** — Postmortem 2030 [fffej.substack.com] (https://fffej.substack.com/p/postmortem-2030)
- **2026-10-25** — Tesla 2026.38.5.6: FSD v14.3.12, 20% Faster Reaction [2026] [shattered.io] (https://shattered.io/tesla-2026-38-5-6-fsd-v14-3-12-down-under-release-notes-2026/)
- **2026-10-23** — openpilot 0.11.2 [blog.comma.ai] (https://blog.comma.ai/0112release/)
- **2026-10-23** — Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles [arxiv.org] (https://arxiv.org/abs/2610.30340)
- **2026-10-22** — How Porsche turns rare road events into repeatable AI tests with NVIDIA [rdworldonline.com] (https://www.rdworldonline.com/how-porsche-turns-rare-road-events-into-repeatable-ai-tests-with-nvidia/)


## All articles (most recent 50)

- **2026-11-20** — Italy Approves Tesla Assisted Driving: Provisional TAD Before EU-Wide Recognition [explainx.ai] (https://explainx.ai/blog/italy-tesla-assisted-driving-provisional-approval-november-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog)
- **2026-11-18** — Build Training-Ready Physical AI Datasets with Two Prompts in NVIDIA Cosmos [developer.nvidia.com] (https://developer.nvidia.com/blog/build-training-ready-physical-ai-datasets-with-two-prompts-in-nvidia-cosmos/)
- **2026-11-18** — AR-WAM: efficient streaming world-action modeling for autonomous driving [arxiv.org] (https://arxiv.org/abs/2611.21851)
- **2026-11-18** — GridDriver: On-Board BEV-Based Language Planning and Reasoning [arxiv.org] (https://arxiv.org/abs/2611.21924)
- **2026-11-18** — Benchmarking Deep Learning Models for Wheelchair Configuration Classification in Accessible Automated Vehicle Applications [arxiv.org] (https://arxiv.org/abs/2611.21945)
- **2026-11-17** — Test Automation to Agentic Validation: Building Governed AI Agents for Physical AI Systems [pub.towardsai.net] (https://pub.towardsai.net/test-automation-to-agentic-validation-building-governed-ai-agents-for-physical-ai-systems-e5c9f4fe6aa9?source=rss----98111c9905da---4)
- **2026-11-16** — Driverless Electric Cars Spotted Pulling Out of Parking Spaces in the Middle of the Night [ibtimes.co.uk] (https://www.ibtimes.co.uk/waymo-driverless-taxis-honking-san-francisco-1832427)
- **2026-11-16** — Real-Time Diffusion Relighting as a Neural Sensor: Closing the Low-Light Domain Gap for Robotic Perception [arxiv.org] (https://arxiv.org/abs/2611.17438)
- **2026-11-16** — Adversarial Tracking: Attacks on Image Sensors for Object Tracking in Autonomous Vehicles [arxiv.org] (https://arxiv.org/abs/2611.17505)
- **2026-11-15** — Ethiopia Banned Petrol Cars but Climate Was Never the Real Story [energytransitionafrica.com] (https://www.energytransitionafrica.com/insights/article/ethiopia-ev-ban-explainer-africa-energy-transition-2026)
- **2026-11-14** — University of Florida's DWM Slashes AI Safety Verification Errors by 127x [alphasignal.ai] (https://alphasignal.ai/news/university-of-florida-s-dwm-slashes-ai-safety-verification-errors-by-127x)
- **2026-11-13** — The researcher creating AI vision models as powerful as the human eye [news.northeastern.edu] (https://news.northeastern.edu/2026/11/13/machine-vision-algorithm-shadow-research/)
- **2026-11-13** — NVIDIA BirdDreams: Joint BEV and Camera Driving World Model [explainx.ai] (https://explainx.ai/blog/nvidia-birddreams-driving-world-model-bev-perspective-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog)
- **2026-11-12** — Qvyon launches with $8M to improve safety for physical AI deployments [siliconangle.com] (https://siliconangle.com/2026/11/12/qvyon-launches-with-8m-to-improve-safety-for-physical-ai-deployments/)
- **2026-11-11** — Serve Robotics wants to democratize sidewalk delivery robots [theverge.com] (https://www.theverge.com/transportation/1030902/serve-robotics-open-developer-api-sidewalk-delivery)
- **2026-11-11** — URL-Sim: Unified and Regulated LiDAR Simulation for High-Fidelity Reconstruction of Dynamic Driving Scenes [arxiv.org] (https://arxiv.org/abs/2611.12932)
- **2026-11-11** — Finland Approves Tesla Assisted Driving After FSD Name Change [explainx.ai] (https://explainx.ai/blog/finland-tesla-assisted-driving-traficom-approval-november-2026?utm_source=rss&utm_medium=feed&utm_campaign=blog)
- **2026-11-10** — Nvidia Alpamayo 2 Edge brings real-time, self-explaining AI to vehicles [cryptobriefing.com] (https://cryptobriefing.com/nvidia-alpamayo-2-edge-real-time-vehicle-ai/)
- **2026-11-10** — Running AV Reasoning Models Within Onboard Compute and Latency Limits [developer.nvidia.com] (https://developer.nvidia.com/blog/running-av-reasoning-models-within-onboard-compute-and-latency-limits/)
- **2026-11-09** — Nvidia Releases Cosmos 3 Family, Four Open-Weight Nano Checkpoints for Interactive World Simulation [epyhia.com] (https://epyhia.com/nvidia-releases-cosmos-3-family-four-open-weight-nano-checkpoints-for)
- **2026-11-09** — NVIDIA Physical AI in Korea: Samsung Cuts a Chip Thermal Solve From 18 Hours to 41 Seconds, Kakao Targets Level 4, LG Trains CLOiD [storagereview.com] (https://www.storagereview.com/news/nvidia-physical-ai-korea-samsung-physicsnemo-kakao-level-4-lg-cloid)
- **2026-11-09** — World Models and China’s Humanoid Certification Gap [hellochinatech.com] (https://hellochinatech.com/p/china-humanoid-world-model-certification)
- **2026-11-09** — eSharp: Diffusion-based Sharp Monocular Metric Event-to-Depth Estimation [arxiv.org] (https://arxiv.org/abs/2611.08731)
- **2026-11-07** — Fooling and blinding self-driving cars in different ways: 30 km/h into 80 km/h with just a flashlight & more. 🚗🛑🔦😵‍💫💥 [it4sec.substack.com] (https://it4sec.substack.com/p/fooling-and-blinding-self-driving)
- **2026-11-06** — VFlash: Enabling System-1 VLMs for Physical AI [research.nvidia.com] (https://research.nvidia.com/labs/lpr/vflash/)
- **2026-11-06** — VFlash: Fast, Accurate Visual Planning via Flash Primitive Decoding [aiflash.com] (https://aiflash.com/news/146613/)
- **2026-11-06** — Regulating Autonomous Mobility-on-Demand Operators with Fixed and Adaptive Penalties: A Multi-Agent Reinforcement Learning Approach [arxiv.org] (https://arxiv.org/abs/2611.07122)
- **2026-11-06** — Wide View Synthesis from Overlapping Perspective Cameras in Autonomous Driving [arxiv.org] (https://arxiv.org/abs/2611.07081)
- **2026-11-05** — New Era of Robot Safety: How VLA Policies Are Rewriting Autonomous Driving Rules! [dev.to] (https://dev.to/amrithesh_dev/new-era-of-robot-safety-how-vla-policies-are-rewriting-autonomous-driving-rules-2ao7)
- **2026-11-05** — NVIDIA details four open-weight Cosmos 3 checkpoints for driving and robot simulation [runtimewire.com] (https://runtimewire.com/article/nvidia-cosmos-3-open-checkpoints-interactive-world-simulation)
- **2026-11-05** — New NVIDIA Cosmos 3 Open Models for Interactive World Simulation [huggingface.co] (https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation)
- **2026-11-05** — Baidu Tests a New Way to Train Robotaxis [technode.com] (https://technode.com/2026/11/05/baidu-tests-a-new-way-to-train-robotaxis/)
- **2026-11-05** — Role-based Effectiveness of an Epistemic Uncertainty Estimate in Training Models for Semantic Segmentation of 3D LiDAR Point Clouds [arxiv.org] (https://arxiv.org/abs/2611.05569)
- **2026-11-04** — Parallel Domain launches PD Forma to turn raw fleet logs into simulation-ready worlds [runtimewire.com] (https://runtimewire.com/article/parallel-domain-pd-forma-launch)
- **2026-11-04** — Baidu launches Apollo World model to train robotaxis in simulated environments [technode.com] (https://technode.com/2026/11/04/baidu-launches-apollo-world-model-to-train-robotaxis-in-simulated-environments/)
- **2026-11-04** — Baidu’s new AI simulator gives robotaxis a crash course in rare road hazards [scmp.com] (https://www.scmp.com/tech/big-tech/article/3373173/baidus-new-ai-simulator-gives-robotaxis-crash-course-rare-road-hazards)
- **2026-11-03** — Baidu unveils Apollo World, an agent-driven world model for physical AI [cryptobriefing.com] (https://cryptobriefing.com/baidu-unveils-apollo-world-model/)
- **2026-11-03** — Toyota shows off SoC that stores model weights and its OS on integrated memory [machinebrief.com] (https://www.machinebrief.com/news/toyota-shows-off-soc-that-stores-model-weights-and-its-os-on-1uce)
- **2026-11-02** — OSWAM: An Effective World Action Model with One-Step Action Generation [aiflash.com] (https://aiflash.com/news/144143/)
- **2026-11-02** — Shinpei Kato brings AI planners into Autoware 2.0 without dropping the rule-based stack [runtimewire.com] (https://runtimewire.com/article/shinpei-kato-autoware-2-0-tier-iv-arm-aws-red-hat)
- **2026-10-31** — GAC starts mass-producing Level 4 robotrucks in China [asia-tech-news.ghost.io] (https://asia-tech-news.ghost.io/gac-starts-mass-producing-level-4-pony-ai-robotrucks/)
- **2026-10-30** — Edge-to-Cloud Swarm Coordination for autonomous urban air mobility routing with ethical auditability baked in [dev.to] (https://dev.to/rikinptl/edge-to-cloud-swarm-coordination-for-autonomous-urban-air-mobility-routing-with-ethical-50an)
- **2026-10-29** — Event Report: Zoox on Measurable Software Assurance at AV & AI USA 2026 [blog.us.fixstars.com] (https://blog.us.fixstars.com/event-report-zoox-on-measurable-software-assurance-at-av-ai-usa-2026/)
- **2026-10-29** — Leonardo brings Shield AI’s Hivemind to Royal Navy Proteus helicopter [aerotime.aero] (https://www.aerotime.aero/articles/leonardo-shield-ai-hivemind-royal-navy-proteus)
- **2026-10-26** — Postmortem 2030 [fffej.substack.com] (https://fffej.substack.com/p/postmortem-2030)
- **2026-10-25** — Tesla 2026.38.5.6: FSD v14.3.12, 20% Faster Reaction [2026] [shattered.io] (https://shattered.io/tesla-2026-38-5-6-fsd-v14-3-12-down-under-release-notes-2026/)
- **2026-10-23** — openpilot 0.11.2 [blog.comma.ai] (https://blog.comma.ai/0112release/)
- **2026-10-23** — Foundation4D: Towards a unified perception and reconstruction model for autonomous vehicles [arxiv.org] (https://arxiv.org/abs/2610.30340)
- **2026-10-22** — How Porsche turns rare road events into repeatable AI tests with NVIDIA [rdworldonline.com] (https://www.rdworldonline.com/how-porsche-turns-rare-road-events-into-repeatable-ai-tests-with-nvidia/)
- **2026-10-22** — Tesla FSD v14.3.13 Update Claims 20% Faster Reaction [2026] [shattered.io] (https://shattered.io/tesla-fsd-v14-3-13-update-2026-38-5-10-2026/)


---

**Related endpoints:**
- RSS feed: https://wpnews.pro/topics/autonomous-vehicles/feed.xml
- HTML view: https://wpnews.pro/topics/autonomous-vehicles
- JSON API: https://api.wpnews.pro/api/v1/topics/autonomous-vehicles
- Full corpus: https://wpnews.pro/llms-full.txt

**Citation:**
```
wpnews.pro Research Brief: Autonomous Vehicles (2026-11-21T15:36:03Z)
Available at: https://wpnews.pro/research/topic/autonomous-vehicles
```
