Tag
Tesla's FSD Supervised system achieves a new autonomous Cannonball Run record, completing the cross-country drive in record time, marking a significant milestone for autonomous driving technology.
SevDiff is a severity-conditioned diffusion model for generating vehicle conflict trajectories with controlled time-to-collision values, achieving high hit-rate on a real-world dataset for ADAS evaluation.
User @TaoRay analyzes Tesla's stock, believing that although there is a short-term oversold bounce opportunity, intensified competition in autonomous driving and China's improved AI capabilities will erode Tesla's premium, suggesting avoiding investment.
The PAVE panel discussed the practical deployment of autonomous driving in off-highway scenarios (defense, industrial, logistics parks), emphasizing how it improves safety and operational efficiency rather than replacing humans.
Elon Musk responds to a post about the real constraint on scaling Tesla Robotaxi, emphasizing the need for caution to avoid accidents and harm.
Tesla's robotaxi mileage is flat and vehicle count appears shrinking, contrasting with Waymo's much higher mileage, and investors are growing concerned despite Musk's optimistic framing during an earnings call.
Tesla claims that its Full Self-Driving (Supervised) feature helps save lives.
Tesla reports zero notable incidents in over 380,000 miles of Robotaxi operation, highlighting the safety record of its autonomous driving service.
After two years of declining sales and profits, Tesla reported a 26% increase in revenue and 25% increase in vehicle deliveries in Q2 2026, signaling a recovery despite challenges in its robotaxi operations and FSD safety.
Xpeng presents its complete AI stack including the Turing chip, TuringViT perception model, end-to-end AI (XNGP), and embodiments like cars and robots, highlighting their integrated approach to intelligent systems.
An interview-based study across nine companies in six countries examining current autonomous driving system testing practices, challenges, and future trends, proposing an evidence-centered closed-loop testing framework.
Investigators confirmed that the Tesla driver in a fatal Texas crash manually overrode Full Self-Driving by pressing the accelerator pedal 100%, reaching speeds over 70mph in a 30mph zone.
NTSB investigation finds that a Tesla driver who blamed a fatal crash on Autopilot had pressed the accelerator pedal 100%, contradicting claims of a defect like 'Sudden Unintended Acceleration'.
XPeng announced its new budget EV, the L03, at a Munich showcase event, targeting global markets with a starting price of €35,600 and features like fast charging, a 320-mile range, and AI-powered systems.
LIDAR-AD proposes a decoder-free latent-interaction world model for autonomous driving that uses redundancy-reduced latent alignment and residual action updates to improve risk-aware state abstraction and long-horizon dynamics prediction, outperforming baseline world models in simulated and real-world scenarios.
Chat2Scenic is an iterative RAG-based framework that generates executable scenario scripts in Domain Specific Language from regulatory descriptions for autonomous driving testing, achieving 76.42% compilation success rate and outperforming existing methods.
This paper proposes DSiGAT, a dynamic scene graph attention framework that jointly predicts lane-change intentions and future trajectories for all interacting vehicles in a traffic scene, achieving state-of-the-art results on NGSIM and highD datasets.
Tesla showcases FSD Supervised navigating complex real-world scenarios in the Netherlands, including using the opposite lane to avoid construction and yielding to cyclists and oncoming traffic.
Tesla FSD V14.3.5 now allows users to open Camera Preview at any time while driving, including the interior cabin camera, to monitor passengers like children.
The Verge's Decoder podcast interviews Nvidia's head of automotive Xinzhou Wu about the company's role in the auto industry, the transition to software-defined vehicles, autonomous driving challenges, and competing for compute resources within Nvidia.