Workshop Dates: October 22-26, 2018We are pleased to announce a Virtual workshop will take place over the course of one week in October. The goal of the workshop is to accelerate the research projects of OpenSim community members. Participants will work on their projects, with support and advice from the Stanford OpenSim team and each other. The event will span one week, including several video conference meetings, along with a daily forum and chat support. It is expected that participants have already begun to use OpenSim for their project. Small teams (2-3) of applicants, working on the same project, are particularly encouraged.
Read more and apply.
Participate in a Machine Learning Challenge with OpenSim
Entries Due: September 15, 2018
Łukasz Kidziński, a Postdoctoral Fellow at Stanford University, has organized a challenge to use reinforcement learning approaches to develop a controller that enables a human model with a prosthetic leg to walk and run. Based on the OpenSim platform, this challenge is one of eight selected to be part of the Neural Information Processing Systems (NIPS) 2018 Competition Track.
Participants are provided with a physiologically based human musculoskeletal model, the OpenSim simulation environment, and datasets of normal gait kinematics. The goal is to match the requested velocity vector, which changes in real time. Round 1 of the challenge ends on September 15.
Details on how to participate, including information on free resources to get started, are available at the
NIPS 2018: AI for Prosthetics Challenge website. You can learn more about reinforcement learning and the challenge in our recent webinar,
Robust Control Strategies for Musculoskeletal Models Using Deep Reinforcement Learning.