Towards a Robust Soft Baby Robot With Rich Interaction Ability for Advanced Machine Learning Algorithms
This addresses the problem of fragile robotic designs for researchers using trial-and-error learning algorithms, representing an incremental step toward tailored robots for general intelligence.
The paper tackles the need for robust robotic platforms for advanced machine learning by presenting a novel hybrid soft-hard robotic limb with rich sensory feedback, demonstrating in proof-of-concept experiments that it succeeds in a target-finding task under sensor failures with minimal human oversight.
Advanced machine learning algorithms require platforms that are extremely robust and equipped with rich sensory feedback to handle extensive trial-and-error learning without relying on strong inductive biases. Traditional robotic designs, while well-suited for their specific use cases, are often fragile when used with these algorithms. To address this gap -- and inspired by the vision of enabling curiosity-driven baby robots -- we present a novel robotic limb designed from scratch. Our design has a hybrid soft-hard structure, high redundancy with rich non-contact sensors (exclusively cameras), and easily replaceable failure points. Proof-of-concept experiments using two contemporary reinforcement learning algorithms on a physical prototype demonstrate that our design is able to succeed in a simple target-finding task even under simulated sensor failures, all with minimal human oversight during extended learning periods. We believe this design represents a concrete step toward more tailored robotic designs for achieving general-purpose, generally intelligent robots.