Round One Entries Due: October 13, 2019
Seungmoon Song and Łukasz Kidziński, postdoctoral fellows at Stanford University, are organizing a scientific challenge to develop a controller that enables a 3D human model to walk. Based on the OpenSim platform, this challenge is one of the official competitions at Neural Information Processing Systems (NeurIPS) 2019.
The challenge this year includes a separate track for the most novel biomechanics solution. Prizes include an Xsens 3D motion capture suit and software license. Winners will also be invited to submit their solution to the Journal of NeuroEngineering and Rehabilitation and publish with no fee, if accepted.
Details on how to participate, including information on free resources to get started, are available at the NeurIPS 2019: Learn to Move Challenge website. You can learn more about reinforcement learning and the challenge in our past webinar, Robust Control Strategies for Musculoskeletal Models Using Deep Reinforcement Learning.