Hardware Podcasts

189. Stanford & Toyota Drift Cars With AI

The Next Byte Podcast · 27 Aug 2024 · 21m

What this episode covers

Hosts Daniel and Forbode discuss a collaboration between Stanford University and the Toyota Research Institute, where Professor Christian Gerits' team used AI to achieve autonomous tandem drifting in Toyota Supras. They explain that training neural networks on these extreme boundary cases—specifically the 'feel' of friction and inertia rather than rigid physics models—aims to make Level 3-5 autonomous vehicles safer in unpredictable, low-friction scenarios like icy roads. The hosts highlight the technical details, such as 50Hz route replanning and sensor instrumentation, while noting the technology's potential portability to standard consumer vehicles.

Most relevant to

large enterprises

Topics

Mentioned

Companies
Stanford University, Toyota Research Institute, Tesla, Waymo, Mouser Electronics
Products
Toyota Supra
Also
Christian Gerits

Related episodes from other shows

Other shows on the same ground, closest first.

  • Moore's Lobby · 53m

    Ep. 22 | Cruise's Sr. VP of Engineering, Mo ElShenawy, on Developing Autonomous Vehicles

    Mo ElShenawy, Senior VP of Engineering at Cruise (a GM subsidiary), discusses the engineering challenges of developing fully autonomous vehicles (L4/L5). He explains why Cruise targets San Francisco's complex environment to accelerate learning and details the hardware stack, including LiDAR, radar, and cameras, fused for perception and prediction. ElShenawy emphasizes that because state-of-the-art literature cannot yet solve L4/L5 driving, Cruise is inventing new algorithms and building a massive simulation and data infrastructure to ensure safety and scale.

    AI & machine learningRobotics & autonomy
    6 chapters

  • Robot Talk · 30m

    Episode 91: Robot navigation on land and in water - John Leonard

    John Leonard, a Professor at MIT and Technical Advisor at Toyota Research Institute, explains the challenges of autonomous navigation for underwater vehicles and self-driving cars. He details how pose graph optimization and SLAM allow robots to build maps and localize themselves, while discussing the specific difficulties of underwater sonar and perceptual aliasing. Leonard also describes his concept of 'robot dreaming' for lifelong learning and Toyota's human-centric AI approach, which includes autonomous drifting to improve safety systems for human drivers.

    Robotics & autonomySensors & measurement in products
    6 chapters

  • Robot Talk · 18m

    Episode 81: Vision for self-driving cars - Vassia Simaiaki

    Vassia Simaiaki, Head of AI Vision and Graphics at Wayve, explains the company's end-to-end AI approach to autonomous driving, which relies on camera data rather than expensive hardware like LiDAR or HD maps. She details how Wayve uses novel view synthesis and a neural simulator called NeuroSim to generate synthetic data, allowing their models to generalize to unseen scenarios like the 'plastic bag problem' or complex London traffic. The discussion highlights Wayve's partnership with Asda to expand grocery delivery coverage and their focus on proving safety through simulation to build public trust.

    Robotics & autonomyAI & machine learning
    6 chapters

  • EE Times Current · 19m

    Recalling Apollo 11 | What, Exactly, Is a Car? | AI Benchmarks

    Analyst Karl Freund discusses the latest ML Perf benchmarks with EE Times editor Rick Merritt, revealing that NVIDIA and Google dominate the AI training market through significant software innovations, while startups struggle to compete in this high-cost segment. The episode then explores automotive innovation, featuring Israeli startup Ree's modular EV platform that integrates motors, steering, and suspension entirely within the wheels, challenging traditional OEM architectures. Finally, EE Times editor George Leopold reflects on the 50th anniversary of Apollo 11, highlighting the enduring legacy of the mission and the critical engineering challenge of abrasive moon dust for future lunar exploration.

    AI & machine learningMechanical engineering
    5 chapters

  • EE Times Current · 29m

    AVs and the Blame Game | Indian IC Industry Ascendent | The Artistry of AI

    Colin Barnden of Semicast Research discusses Tesla's Smart Summon feature, arguing it is a gimmick that beta-tests software on public roads and creates legal ambiguity regarding OEM liability for autonomous driving failures. Sanjay Gupta, VP of Engineering at NXP Semiconductors, explains how India has evolved from back-office support to leading global semiconductor design projects, including ADAS products, driven by government policy and deep engineering talent. Researchers at Deep Mind used reinforcement learning to train an AI to draw human faces, demonstrating that machines can identify facial features without labeled data, though the output is not considered true art due to a lack of intent.

    Security & privacyAI & machine learning
    5 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by The Next Byte Podcast. The episode itself belongs to its publisher.