Learning with Muscles: Benefits for Data-Efficiency and Robustness in Anthropomorphic Tasks
This addresses core robotics challenges by potentially enabling more efficient and stable learning for human-like movements, though it appears incremental as it builds on existing muscle-actuated systems.
The study investigated the role of nonlinear muscle dynamics in improving learning for anthropomorphic tasks, finding that muscle actuators enhance data-efficiency, reduce hyperparameter sensitivity, and increase robustness compared to traditional methods.
Humans are able to outperform robots in terms of robustness, versatility, and learning of new tasks in a wide variety of movements. We hypothesize that highly nonlinear muscle dynamics play a large role in providing inherent stability, which is favorable to learning. While recent advances have been made in applying modern learning techniques to muscle-actuated systems both in simulation as well as in robotics, so far, no detailed analysis has been performed to show the benefits of muscles when learning from scratch. Our study closes this gap and showcases the potential of muscle actuators for core robotics challenges in terms of data-efficiency, hyperparameter sensitivity, and robustness.