Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed
This addresses the tedious hand-designing of feedback models for robot adaptation, offering a data-driven alternative, though it appears incremental as it combines existing methods like segmentation, learning from demonstrations, and reinforcement learning.
The paper tackles the problem of robots adapting to unexpected environmental changes by introducing a framework for learning feedback models for reactive motion planning, resulting in successful evaluation on a real anthropomorphic robot for a tactile feedback task.
Robots need to be able to adapt to unexpected changes in the environment such that they can autonomously succeed in their tasks. However, hand-designing feedback models for adaptation is tedious, if at all possible, making data-driven methods a promising alternative. In this paper we introduce a full framework for learning feedback models for reactive motion planning. Our pipeline starts by segmenting demonstrations of a complete task into motion primitives via a semi-automated segmentation algorithm. Then, given additional demonstrations of successful adaptation behaviors, we learn initial feedback models through learning from demonstrations. In the final phase, a sample-efficient reinforcement learning algorithm fine-tunes these feedback models for novel task settings through few real system interactions. We evaluate our approach on a real anthropomorphic robot in learning a tactile feedback task.