Learning Sensor Feedback Models from Demonstrations via Phase-Modulated Neural Networks

TL;DR

This paper introduces a data-driven neural network framework that learns reactive feedback models from demonstrations, enabling robots to adapt their movements based on sensory deviations, demonstrated on a tactile scraping task.

Contribution

It develops a phase-modulated neural network approach for learning feedback models from demonstrations, applicable to movement primitives and reactive control tasks.

Findings

Effective tactile feedback model learned for scraping task

Framework successfully applied to an anthropomorphic robot

Demonstrated adaptability to sensory deviations

Abstract

In order to robustly execute a task under environmental uncertainty, a robot needs to be able to reactively adapt to changes arising in its environment. The environment changes are usually reflected in deviation from expected sensory traces. These deviations in sensory traces can be used to drive the motion adaptation, and for this purpose, a feedback model is required. The feedback model maps the deviations in sensory traces to the motion plan adaptation. In this paper, we develop a general data-driven framework for learning a feedback model from demonstrations. We utilize a variant of a radial basis function network structure --with movement phases as kernel centers-- which can generally be applied to represent any feedback models for movement primitives. To demonstrate the effectiveness of our framework, we test it on the task of scraping on a tilt board. In this task, we are learning a reactive policy in the form of orientation adaptation, based on deviations of tactile sensor traces. As a proof of concept of our method, we provide evaluations on an anthropomorphic robot. A video demonstrating our approach and its results can be seen in https://youtu.be/7Dx5imy1Kcw