Projects with Myosuite

MyoChallenge
Publications with Myosuite

MyoChallenge

MyoChallenge is an annual event organized by the MyoSuite team to advance our understanding of the physiological motor control essential for dexterous and agile movements of the human body.

MyoChallenge-2022: Learning Physiological Dexterity

MyoChallenge 2022 : Learning Physiological Dexterity

This competition focuses on learning contact-rich manipulation skills for a physiologically realistic musculo-skeletal hand. The goal of MyoChallenge is to push our understanding of physiological motor-control responsible for nimble and agile movements of the human body. In the current edition of MyoChallenge, we are focusing on developing controllers for contact rich dexterous manipulation behaviors. This challenge builds upon the MyoSuite ecosystem – a fast (>4000x faster) and contact-rich framework for musculoskeletal motor control.

MyoChallenge-2023: Towards Human-Level Dexterity and Agility

MyoChallenge 2023 : Towards Human-Level Dexterity and Agility

Humans effortlessly grasp objects of diverse shapes and properties and execute agile locomotion without overwhelming their cognitive capacities. This ability was acquired through millions of years of evolution, which honed the symbiotic relationship between the central and peripheral nervous systems and the musculoskeletal structure. Consequently, it is not surprising that uncovering the intricacies of these complex, evolved systems underlying human movement remains a formidable challenge. Advancements in neuromechanical simulations and data driven methods offer promising avenues to overcome these obstacles.

MyoChallenge 2024: Physiological Dexterity and Agility in Enhanced Humans

MyoChallenge 2024: Physiological Dexterity and Agility in Enhanced Humans

The movement generalization and environment adaptability skills displayed by humans using bionic extensions are a testament to motor intelligence, a capability yet unmatched by current artificial intelligence.

Limb loss profoundly affects an individual’s quality of life and independence. Bionic prosthetic limbs provide a chance to restore mobility and functionality, enabling users to compensate for their lost limbs and regain motor abilities. The adaptability and movement skills of bionic limb users highlight a level of motor intelligence that current artificial intelligence agents have yet to achieve.

The MyoChallenge 2024 will push the boundaries on how symbiotic human-robotic interaction needs to be coordinated to produce agile and dexterous behaviors.

Publications with Myosuite

Please feel free to create a PR for your own project with Myosuite

MyoDex: A Generalizable Prior for Dexterous Manipulation

Caggiano, V., Dasari, S., Kumar, V. (2023). International Conference on Machine Learning (ICML). Paper, project page

DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

Schumacher, P., Haeufle, D.F.B., Büchler, D., Schmitt, S., Martius, G. (2023). International Conference on Learning Representations (ICLR). Paper, code

Lattice: Latent Exploration for Reinforcement Learning

Chiappa, A.S., Marin Vargas, A., Huang, A.Z., Mathis, A. (2023). Advances in Neural Information Processing Systems (NeurIPS). Paper, code

SAR: Generalization of Physiological Agility and Dexterity via Synergistic Action Representation

Berg, C., Caggiano, V., Kumar, V. (2023). Robotics: Science and Systems (RSS). Paper, project page

MuscleMimic: Towards Embodied AI with MuscleMimic: Unlocking full-body musculoskeletal motor learning at scale

Li, C., Wang, C., Ziliotto, B., Simos, M., Kovecses, J., Durandau, G., Mathis, A. (2026). arXiv:2603.25544. Paper, code. Used for the full-body tutorials 5.1-5.5; the motion data and retargeting sources are listed on References.

MyoInteract: A Framework for Fast Prototyping of Biomechanical HCI Tasks using Reinforcement Learning

Bhattarai, A., Selder, H., Fischer, F., Fleig, A., Kristensson, P.O. (2026). ACM Designing Interactive Systems Conference (DIS). Paper, DOI. Builds on MyoSuite: designers set up interaction tasks, user models and training from a GUI and train muscle-actuated simulated users within minutes.