Artificial Intelligence for Prosthetics - challenge solutions
This work addresses the problem of developing AI controllers for prosthetic devices, but it is incremental as it compiles and analyzes existing solutions from a competition.
The paper describes the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, where participants built controllers using deep reinforcement learning to match a time-varying velocity vector, resulting in thirteen solutions with various modifications to known algorithms.
In the NeurIPS 2018 Artificial Intelligence for Prosthetics challenge, participants were tasked with building a controller for a musculoskeletal model with a goal of matching a given time-varying velocity vector. Top participants were invited to describe their algorithms. In this work, we describe the challenge and present thirteen solutions that used deep reinforcement learning approaches. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each team implemented different modifications of the known algorithms by, for example, dividing the task into subtasks, learning low-level control, or by incorporating expert knowledge and using imitation learning.