MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans

Yuan Gao (Carnegie Mellon University) · Stone Tao (University of California - San Diego) · Hao Su (UCSD) · Huiyi Wang (McGill University) · Chun Kwang Tan (Northeastern University) · Balint Hodossy (Imperial College London) · Shirui Lyu (King's College London, University of London) · Pierre Schumacher (Max Planck Institute for Intelligent Systems, Max-Planck Institute) · James Heald (University College London, University of London) · Kai Biegun (University College London, University of London) · Samo Hromadka (Gatsby Computational Neuroscience Unit) · Maneesh Sahani (Gatsby Unit, UCL) · Gunwoo Park (KAIST) · Beomsoo Shin (KAIST) · JongHyeon Park · Seungbum Koo (KAIST) · Chenhui Zuo (Tsinghua University, Tsinghua University) · Chengtian Ma (Tsinghua University, Tsinghua University) · Yanan Sui (Tsinghua University) · Nick Hansen (UC San Diego) · Seungmoon Song (Stanford University) · Letizia Gionfrida (King's College London, University of London) · Massimo Sartori (University of Twente) · Guillaume Durandau (McGill University) · Vikash Kumar (CMU / MyoLab) · Vittorio Caggiano (MyoSuite)

bilateral virtual legbionic prostheticshuman-robot coordinationimitation learningjoint controllocomotion taskmanipulation taskmodel-based reinforcement learningmodular prosthetic limbmotor intelligencemuscle synergymyompl modelmyoosl modelopen source legtrans-femoral amputation

Recent advancements in bionic prosthetic technology offer transformative opportunities to restore mobility and functionality for individuals with missing limbs. Users of bionic limbs, or bionic humans, learn to seamlessly integrate prosthetic extensions into their motor repertoire, regaining critical motor abilities. The remarkable movement generalization and environmental adaptability demonstrated by these individuals highlight motor intelligence capabilities unmatched by current artificial intelligence systems. Addressing these limitations, MyoChallenge '24 at NeurIPS 2024 established a benchmark for human-robot coordination with an emphasis on joint control of both biological and mechanical limbs. The competition featured two distinct tracks: a manipulation task utilizing the myoMPL model, integrating a virtual biological arm and the Modular Prosthetic Limb (MPL) for a passover task; and a locomotion task using the novel myoOSL model, combining a bilateral virtual biological leg with a trans-femoral amputation and the Open Source Leg (OSL) to navigate varied terrains. Marking the third iteration of the MyoChallenge, the event attracted over 50 teams with more than 290 submissions all around the globe, with diverse participants ranging from independent researchers to high school students. The competition facilitated the development of several state-of-the-art control algorithms for bionic musculoskeletal systems, leveraging techniques such as imitation learning, muscle synergy, and model-based reinforcement learning that significantly surpassed our proposed baseline performance by a factor of 10. By providing the open-source simulation framework of MyoSuite, standardized tasks, and physiologically realistic models, MyoChallenge serves as a reproducible testbed and benchmark for bridging ML and biomechanics. The competition website is featured here: https://sites.google.com/view/myosuite/myochallenge/myochallenge-2024.