Hardware Podcasts

Driver-Assist Actually Stinks | VR and “The Great C” | The Flush of Victory

EE Times Current · 14 Aug 2020 · 44m

What this episode covers

Junko Yoshida explains why AAA testing reveals that active driver-assist systems (ADAS) in US vehicles are unreliable, often disengaging abruptly or failing to recognize obstacles like soft test vehicles, due to a lack of federal safety standards and inconsistent OEM performance. She argues that Driver Monitoring Systems (DMS) must be mandated alongside ADAS to ensure human drivers are alert during handovers, a requirement currently enforced in Europe but not the US. Meanwhile, Luke Van Osch and Steve Miller of Secret Location discuss creating the VR film The Great C, detailing their shift from error-prone 360-degree video rigs to Unreal Engine animation to achieve cinematic immersion and control viewer attention through spatialized sound and camera movement.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
AAA, Secret Location, Gates Foundation, Caltech
Products
The Great C, Oculus Quest
Tools
Unreal Engine
Also
Junko Yoshida, Luke Van Osch, Steve Miller, Steam

Related episodes from other shows

Other shows on the same ground, closest first.

  • 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

  • Embedded.fm · 1h 16m

    198: Unmanned Flying Thingy

    Walter Stockwell, Director of Technical Standards at DJI, discusses the evolving regulatory landscape for drones, including the distinction between autonomous and remotely piloted systems, and the FAA's Part 107 certification requirements. He details the results of the ASSURE UAS Ground Collision Severity Evaluation, which used crash test dummies to determine that drone impacts pose significantly lower injury risks than solid objects of equivalent mass, influencing safety standards. Stockwell also explains the role of Designated Engineering Representatives (DERs) in aviation certification and the technical challenges of sensor fusion, such as Kalman and Madgwick filters, in maintaining stable flight.

    Policy, trade & tariffsMicrocontrollers & dev platforms
    9 chapters

  • The Next Byte Podcast · 20m

    123. Augmented Bad Drivers Turbocharge Autonomous Vehicle Development

    Hosts Daniel and Forbode discuss research from the University of Michigan that uses mixed reality to accelerate autonomous vehicle (AV) testing. By superimposing virtual 'bad driver' vehicles onto real physical cars on the MCity test track, researchers can simulate rare safety-critical events without real-world risk. This approach, leveraging data from smart intersections in Ann Arbor and Detroit, reduces the required testing miles by 99.99%, addressing the 'curse of rarity' in AV training data. The hosts highlight how this method lowers costs and time while improving safety for companies like Waymo, Tesla, and Cruise.

    Connected products & IoTPrototyping & iteration
    9 chapters

  • The Next Byte Podcast · 23m

    134. Can We Trust Self-Driving Cars? 🚗💥

    Hosts Daniel and Forbode discuss a proposal by MIT researchers to bridge the gap between autonomous vehicle technologists and regulators by introducing a hybrid safety model. They analyze how remote human supervisors can assist self-driving cars with complex tasks like highway merging, achieving 99.999% reliability when 30% of vehicles are cooperative. The episode highlights the scalability challenges of this approach, noting that while feasible for early adoption, it requires significant labor resources compared to fully autonomous systems.

    Robotics & autonomyValidation & product-market fit
    7 chapters

  • Embedded.fm · 1h 16m

    421: Paint the Iceberg Yellow

    Chris Hobbs, who works in kernel development at BlackBerry QNX and authored 'Embedded Software Development for Safety-Critical Systems,' explains the distinction between safety-critical and standard embedded systems, emphasizing safety culture and the concept of SOTIF (Safety of the Intended Functionality). He details how modern systems, such as autonomous vehicles and medical devices, face risks from 'accidental systems' where interactions between components create unforeseen hazards, citing examples like a radar system dependent on jammed GPS. Hobbs advocates for goal-based standards like UL 4600 and the use of Safety Cases with Goal Structuring Notation to demonstrate safety rather than relying on prescriptive checklists. He also discusses the challenges of verifying machine learning algorithms, the limitations of languages like C and Rust in safety contexts, and the importance of structured risk analysis using tools like Bayesian fault trees and LaTeX for traceability.

    Embedded firmwareSecurity & privacy
    12 chapters

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