Episode 82: Software for teleoperation - Chang Liu

Robot Talk · 26 Apr 2024 · 31m · Episode 82

What this episode covers

Chang Liu, CEO and Chief Designer of Extend Robotics, explains how his company uses VR and embodied AI to create intuitive teleoperation interfaces for non-experts. He details the technical challenges of depth perception, motion sickness, and latency, highlighting their custom compression algorithms and digital twin technology. Liu discusses applications ranging from space docking with Airbus to nuclear decommissioning and precision viticulture, noting the company's early revenue and government-funded projects.

Mentioned

Companies
Extend Robotics, Airbus, AtkinsRéalis, Saffron Grand Vineyards
Products
Metaquest, HTC Vive, Apple Vision Pro
Also
Imperial College London, University of Southampton, European Space Agency, Innovate UK, University of Surrey

Other shows on the same ground, closest first.

  • The Robot Report Podcast · 1h 27m

    Veo on manufacturing challenges; tele-operating Spot; Amazon goes to the mall

    Patrick Sobalvarro, CEO of Veo Robotics, explains how their software and sensor technology enables industrial robots to work collaboratively with humans in final assembly, addressing safety certification and the shift toward reshoring. The episode also covers Amazon's strategy of converting vacant mall space into micro-fulfillment centers, iRobot's tariff relief, and a Starship delivery robot incident. Finally, Jeff Linnell, founder of Formant, discusses the teleoperation of Boston Dynamics' Spot robot and the importance of fleet management software.

  • The Robot Report Podcast · 1h 00m

    Dextrous Robotics exits stealth; how robots impact the future of work

    Evan Drumwright, CEO and co-founder of Dextrous Robotics, explains how his Memphis-based startup is exiting stealth mode to automate the unloading of box trucks using a unique 'Chopsticks' system. Drumwright details the engineering challenges of manipulating diverse packages without suction or complex anthropomorphic grippers, relying instead on high-precision custom hardware and human-in-the-loop perception. The episode also covers recent robotics industry news, including Motional's Level 4 autonomous vehicle testing in Nevada and an MIT study on the impact of robots on employment.

  • The Robot Report Podcast · 59m

    George Konidaris on Realtime Robotics future; Intel LiDAR update

    Realtime Robotics founder and CTO George Konidaris explains how his company’s real-time controller enables collision-free motion planning for multiple industrial robots in unstructured environments, allowing them to operate at full speed without cages. He details the system's architecture, which uses 3D perception to avoid dynamic obstacles and integrates with various robot brands, citing automotive welding and mixed-case palletizing as key applications where throughput increases by 20-40%. Konidaris also discusses the roadmap for safety-certified collaborative operation and simulation plugins, emphasizing the shift from rigid, hand-coded programming to automated, high-performance multi-robot coordination.

  • The Robot Report Podcast · 1h 05m

    From Teleoperation to Autonomy: Inside Boston Dynamics' Atlas Training

    Scott Kuindersma, VP of Robotics Research at Boston Dynamics, explains how the company trains the Atlas humanoid robot using Large Behavior Models (LBMs) and teleoperation data. The team collected 20 hours of teleoperation data to enable Atlas to perform complex bi-manual manipulation tasks, such as picking and placing Spot parts, while adapting to real-time disturbances. Kuindersma details the four-stage pipeline of data collection, annotation, model training, and evaluation, highlighting the critical role of simulation data and human demonstrations in generalizing these skills. The episode concludes with plans to test Atlas in Hyundai facilities and further explore AI-centric dynamic behaviors.

  • The Robot Report Podcast · 1h 04m

    Baseball & robotics startups during COVID-19; ROS on Windows 10

    AJ Mayer, CEO of the Boston-based Pickle Robot Company, explains how his startup uses reinforcement learning and deep neural networks to automate loading and unloading trucks with their 'Dill' robot, targeting brownfield logistics facilities rather than fully automated warehouses. He details the 'supervisor ratio' business model, where human operators handle the 2% of edge cases the robot cannot manage, and discusses the challenges of selling to enterprise customers during the pandemic. The episode also features Dave Niewinski from Clearpath Robotics, who discusses the strategic benefits of supporting ROS on Windows 10 for their Unmanned Ground Vehicles (UGVs), highlighting easier IT integration, cloud connectivity via Azure, and lower barriers to entry for corporate clients.

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.