#autonomous driving
Autonomous Driving: 12 AI articles covering autonomous driving news, analysis, and research
Articles
Beyond Textual Chain-of-Thought: A Survey on Action-Grounded⭐9
A survey of 171 papers analyzing action-grounded reasoning beyond textual chain-of-thought in autonomous driving, with a taxonomy of 13 methods for real-world A...
Waymo Robotaxis Head to Munich as Company Expands in Europe⭐9
Waymo enters Germany with plans to launch robotaxi service in Munich by 2027, expanding its autonomous driving operations into Europe.
RISE: Adaptive Imagination for World Action Models⭐8
RISE introduces adaptive imagination for world action models in autonomous driving, using selective rollout to cut computation and boost planning safety.
Tesla Robotaxis Operate Fully Unsupervised in Austin Ahead of⭐8
Tesla robotaxis complete 170 fully unsupervised rides in Austin ahead of Cybercab launch, signaling major FSD milestone.
Tesla's Cybercab Launch: A High-Stakes Bet on Autonomous Readiness⭐8
Tesla launches its Cybercab robotaxi, betting its camera-based autonomy software is ready for real-world roads amid fierce competition and regulatory hurdles.
MapTCL: Temporal Consistency Learning via Bidirectional⭐9
MapTCL improves HD map temporal consistency via bidirectional alignment, boosting mAP gains on nuScenes and Argoverse2 without extra overhead.
NVIDIA Releases Alpamayo 2 Super: A 34B Open⭐7
NVIDIA's Alpamayo 2 Super 34B open-source VLA model enhances autonomous driving safety, handling rare scenarios with end-to-end trajectory planning on
Tesla Driver Faces Manslaughter Charges After Fatal Crash Kills⭐6
Tesla driver faces manslaughter charges after fatal crash kills woman in her home; case tests liability for self-driving tech.
TechCrunch Mobility: All Eyes on Tesla FSD as Scrutiny Intensifies⭐9
TechCrunch Mobility examines growing scrutiny of Tesla's Full Self-Driving after a fatal Texas crash, NHTSA/NTSB probes, and a lawsuit settlement.
Neuro-Symbolic Drive: Rule-Grounded Faithful Reasoning for⭐8
Neuro-Symbolic Drive uses rule-grounded reasoning traces from classical planners to train a driving VLA, reducing ADE@3s from 0.47 to 0.26 and miss rate from 8....