Simple Kinematic Feedback Enhances Autonomous Learning in Bio-Inspired Tendon-Driven Systems
This work addresses the challenge of enhancing learning efficiency and robustness in bio-inspired tendon-driven systems, which is incremental as it builds on existing autonomous learning methods by incorporating feedback.
The study tackled the problem of accelerating and robustifying autonomous learning in tendon-driven robots by adding simple kinematic feedback to the General-to-Particular algorithm, resulting in improved performance even with sensory delays up to 100 ms and substantial contact collisions, and enabling effective operation after only 60 seconds of initial motor babbling.
Error feedback is known to improve performance by correcting control signals in response to perturbations. Here we show how adding simple error feedback can also accelerate and robustify autonomous learning in a tendon-driven robot. We implemented two versions of the General-to-Particular (G2P) autonomous learning algorithm to produce multiple movement tasks using a tendon-driven leg with two joints and three tendons: one with and one without kinematic feedback. As expected, feedback improved performance in simulation and hardware. However, we see these improvements even in the presence of sensory delays of up to 100 ms and when experiencing substantial contact collisions. Importantly, feedback accelerates learning and enhances G2P's continual refinement of the initial inverse map by providing the system with more relevant data to train on. This allows the system to perform well even after only 60 seconds of initial motor babbling.