Hardware Podcasts

Episode Eleven – Self-Driving Cars: behind the wheel

Robot Talk · 29 Oct 2021 · 34m · Episode 11

What this episode covers

Dr Richard Hawkins of the University of York and Dr Frederic Labrosse of Aberystwyth University discuss the distinct challenges of autonomous vehicle safety, regulation, and perception. Hawkins explains the difficulty of defining safety cases for AI-driven cars in complex urban environments and the UK's new regulations for automated lane keeping systems. Labrosse contrasts on-road challenges, like plastic bag detection, with off-road issues such as terrain variability and LIDAR sensitivity to grass, highlighting applications in farming, archaeology, and surveying.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
University of York, Aberystwyth University, BAE Systems, Tesla, Waymo, Royal Commission on the Ancient and Historical Monuments of Wales
Products
NASA Opportunity, Land Rover
Tools
LIDAR

Related episodes from other shows

Other shows on the same ground, closest first.

  • The Robot Report Podcast · 1h 20m

    Autonomous vehicle technology deep dive at John Deere and Zoox

    Jorge Heraud, VP of Autonomy at John Deere, explains how the company leverages its acquisition of Blue River Technology and Spark AI to deploy Level 4 autonomous tractors, using computer vision and machine learning to enable 'See and Spray' and autonomous tillage while managing rural connectivity challenges. RJ He and Ryan McMichael, technology leaders at Zoox, discuss their purpose-built, steering-wheel-free robotaxi recently deployed on public roads in California, detailing a perception stack that integrates cameras, LIDAR, radar, and thermal imaging to ensure safety through redundancy and diversity. The episode contrasts the agricultural application of autonomy, focused on labor relief and precision, with the urban mobility focus of Zoox, highlighting the technical hurdles of sensor fusion, edge cases, and the critical importance of building a robust safety case for public acceptance.

    Robotics & autonomySensors & measurement in products
    8 chapters

  • The Robot Report Podcast · 44m

    Nuro navigates to fully autonomous driving

    Andrew Clare, CTO of Nuro, explains the company's pivot from solely operating autonomous delivery vehicles to licensing its 'Nuro Driver' technology to automotive OEMs and mobility providers. He details the technical differences between urban and highway driving, emphasizing that highway autonomy requires long-range perception and rapid reaction to off-nominal events, whereas urban driving demands handling complex dynamic behaviors like pedestrians and cyclists. Clare highlights Nuro's safety culture, its federal exemption for occupantless vehicles, and its redundant sensor stack of LiDAR, camera, and radar, while clarifying that the company's North Star remains Level 4 autonomy rather than pursuing unrestricted Level 5.

    Robotics & autonomyMechanical engineering
    6 chapters

  • The Next Byte Podcast · 1h 02m

    192. Karsten Roscher & The Need For Safe AI (Interview)

    Karsten Roscher, Head of the Certifiable AI department at the Fraunhofer Institute for Cognitive Systems (IKS), discusses the critical need for safety in AI development, particularly in autonomous driving. He explains the challenges of out-of-distribution detection, where models fail on unseen data like e-scooters or horse carriages, and introduces Robuscope, a free tool for evaluating model robustness without sharing proprietary data. Roscher also critiques the industry's over-reliance on benchmarks and highlights a new SAE International course designed to bridge the gap between machine learning engineers and safety experts.

    AI & machine learningDebugging & failure analysis
    6 chapters

  • The Next Byte Podcast · 20m

    170. Robot That Drives Better Than The Average American

    Daniel and Forbode discuss research from Professor Sue Xiao’s Robotics Lab at George Mason University, which developed an autonomous robot capable of driving better than humans on variable terrain. The team instrumented an off-the-shelf robot with visual and inertial sensors to collect data on stability, training a machine learning model that reduced instability by 62% while sacrificing only 8.6% of speed. This technology, applicable to first responders and drones, allows robots to adapt their driving style to terrain changes like gravel or ice, improving safety for both autonomous and human-in-the-loop scenarios.

    Robotics & autonomySensors & measurement in products
    6 chapters

  • The Next Byte Podcast · 24m

    76. Off-roading & Ending Stoplights With Autonomous Cars

    Hosts Daniel and Forbode discuss two recent advancements in autonomous driving technology. They first cover MIT research on using neural networks to eliminate stop-and-go traffic at intersections, achieving significant reductions in emissions and travel time. They then discuss Carnegie Mellon University's development of the Tartan Drive dataset, which uses dynamic vehicle data to enable off-road autonomous navigation without relying on annotated maps.

    AI & machine learningConnected products & IoT
    6 chapters

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