Hardware Podcasts

Dejan Pangercic on ROS based autonomous vehicle software

The Robot Report Podcast · 3 Mar 2023 · 1h 21m

What this episode covers

Dejan Pangercic, co-founder and CTO of APEX.ai, explains how his company has built a hardened, ISO 26262-certified operating system around ROS 2 to address the gap between research prototypes and production-ready autonomous vehicles. He details APEX.ai's software stack, including Apex Ida for data transport and Apex Grace for middleware, which unify diverse automotive protocols into a single, safety-critical interface. The discussion highlights the company's involvement in the India Autonomous Challenge, where they advised teams on real-time determinism and simulation fidelity, and their expansion into agricultural robotics through partnerships with FarmEgg.

Most relevant to

companies scaling up

Topics

Mentioned

Companies
APEX.ai, Figure.AI, Tesla, Boston Dynamics, Waymo, Ford, Argo AI, Latitude AI, FarmEgg
Products
Figure 01, Optimus, Atlas, Full Self-Driving, Apex Ida, Apex Grace
Also
ROS 2

Related episodes from other shows

Other shows on the same ground, closest first.

  • Embedded.fm · 55m

    33: Quitting My Finnish Lessons

    Alison Chaiken, an embedded systems expert at Mentor Graphics, discusses the transition of the automotive industry into a 'rolling data center' with up to 100 microprocessors per vehicle. She explains the shift from proprietary, hand-crafted code to open standards like AUTOSAR and Linux, highlighting the critical role of hypervisors in isolating safety-critical functions from infotainment systems. Chaiken also covers the complexities of automotive networking protocols like CAN and Ethernet AVB, the rigorous ISO 26262 safety certification landscape, and the emerging opportunities in connected cars and autonomous driving technologies.

    Embedded firmwareWireless & RF
    7 chapters

  • EE Times Current · 39m

    Arm’s bold new path | Teenage autonomous drivers | Dealing with the data deluge

    Kevin Krewell of TIRIAS Research reports on Arm Techcon, highlighting Arm's decision to open its instruction set architecture (ISA) to customer-defined custom instructions, a strategic shift driven by CEO Sophie Richardson and SoftBank's influence to compete with RISC-V. Phil Koopman of Carnegie Mellon University discusses the challenges of certifying autonomous vehicles, arguing that current road tests are insufficient for AI systems lacking common sense, and explains how the UL 4600 standard requires manufacturers to prove they have mitigated risks through rigorous engineering evidence rather than just passing a driving test. John Petty of John Petty Research joins to discuss the 'data deluge,' explaining how data visualization and AI tools are essential for making sense of massive datasets from IoT, simulations, and financial transactions.

    Chips, FPGAs & semiconductorsSecurity & privacy
    6 chapters

  • EE Times Current · 13m

    Leveraging Safety Processor Expertise to Develop RISC-V Based Automotive Implementations

    Rich Collins, Senior Product Management Director at Synopsys, discusses the integration of RISC-V processors into automotive safety applications. He explains the industry's shift from domain controllers to zonal architectures, which requires high-performance, safety-certified processing elements. Collins details how Synopsys leverages its Arc5 processor portfolio and extensive functional safety expertise to help SOC vendors meet ISO 26262 ASIL-D requirements through certified IP and work products.

    Microcontrollers & dev platformsChips, FPGAs & semiconductors
    5 chapters

  • EE Times Current · 12m

    "A Turning Point for AVs" - A Special Report

    Brett Brune and Gina Roos from EE Times discuss a special report on the turning point for autonomous vehicles (AVs), focusing on the convergence of AI, perception sensors, and V2X connectivity. They highlight the challenges chipmakers face in implementing ISO 26262 functional safety standards for microprocessors and microcontrollers as vehicles become more software-defined. The conversation also details the role of LiDAR in ADAS, explaining its technology, benefits for safety, and the specific power and efficiency challenges it presents for system design.

    AI & machine learningSensors & measurement in products
    4 chapters

  • Embedded.fm · 1h 01m

    397: Owl

    Elecia White discusses her recent contract work on autonomous off-road trucks, where she implemented reinforcement learning for a safety system and debugged a critical color-space issue in TensorFlow. She also details her preparation for the second cohort of her Making Embedded Systems course, focusing on firmware update security and IoT management. Christopher White shares his experience building a radar data collection system using an NVIDIA Xavier and Python GUIs, and reflects on the importance of practice and exercise.

    Embedded firmwareAI & machine learning
    8 chapters

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