Webinar: “Robust Control Strategies for Musculoskeletal Models Using Deep Reinforcement Learning”

Tuesday, August 7, 2018 at 10:00am Pacific Daylight Time

Reinforcement learning is an unsupervised machine learning approach that seeks to take actions to maximize some user-defined performance metric, or reward, thus creating a complex controller for any movement without specific domain knowledge. In this webinar, Łukasz Kidziński from Stanford University will introduce reinforcement learning and its application to developing control strategies. Learn more and register

NCSRR/OpenSim Pilot Project Program

Application Deadline: 5pm Pacific Daylight Time on August 1, 2018

The National Center for Simulation in Rehabilitation Research (NCSRR) and OpenSim project at Stanford University seek proposals for our pilot project program. The program awards seed grants to innovative and meritorious projects that will accelerate the use of simulation in rehabilitation research. Pilot project awardees may request funding up to $40,000 for their research. Learn more and apply

Below-Knee Amputee Model that Accounts for Residuum-Socket Interaction

When modeling the gait of individuals with lower limb loss who use a prosthesis, the motion and loads of the residual limb inside the socket are typically not captured and thus, cannot be included in the model. Andrew LaPre and colleagues at the University of Massachusetts @ Amherst have developed a below-knee amputee model that includes a residuum-socket joint with zero to 6 degrees of freedom (DOFs). They used a global optimization technique and anatomical constraints to find the parameters for the interface, including the DOFs, that best satisfied both experimental data and data from the literature. Read more about their model and process for making it patient-specific in their publication “Approach for Gait Analysis in Persons with Limb Loss Including Residuum and Prosthesis Socket Dynamics.”  You can download the model from https://simtk.org/projects/bkamputee_model/.

---

Joy P. Ku, PhD

Project Manager, SimTK

Director of Communications & Training, NCSRR

Director of Communications & Engagement, Mobilize Center

Stanford University

(w)  650.736.8434, (f) 650.723.7461

Email:  joyku@stanford.edu