2019/10/25 by Amir H. Abdi, Masoud Malakoutian, Abdi, Amir H. +6
Computer Science · Engineering · Neuroscience · #EEG and Brain-Computer Interfaces #FOS: Electrical engineering #Motor Control and Adaptation #Muscle activation and electromyography studies #Prosthetics and Rehabilitation Robotics #Reinforcement Learning in Robotics #Signal Processing (eess.SP) #eess.SP #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1910.13859
Deep Reinforcement Learning Workshop NeurIPS 2019
openalex publication_date 2019/10/25 · arxiv created 2019/12/09 · arxiv updated 2019/12/10 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28
Neural control is an exciting mystery which we instinctively master. Yet, researchers have a hard time explaining the motor control trajectories. Physiologically accurate biomechanical simulations can, to some extent, mimic live subjects and help us form evidence-based hypotheses. In these simulated environments, muscle excitations are typically calculated through inverse dynamic optimizations which do not possess a closed-form solution. Thus, computationally expensive, and occasionally unstable, iterative numerical solvers are the only widely utilized solution. In this work, we introduce ArtiSynth, a 3D modeling platform that supports the combined simulation of multi-body and finite element models, and extended to support reinforcement learning (RL) training. we further use ArtiSynth to investigate whether a deep RL policy can be trained to drive the motor control of a physiologically accurate biomechanical model in a large continuous action space. We run a comprehensive evaluation of its performance and compare the results with the forward dynamics assisted tracking with a quadratic objective function. We assess the two approaches in terms of correctness, stability, energy-efficiency, and temporal consistency.