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

by   Giovanni Sutanto, et al.

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 in sensory traces from nominal. These deviations in sensory traces can be used to drive the plan 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, replacing hand-design processes. 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


Supervised Learning and Reinforcement Learning of Feedback Models for Reactive Behaviors: Tactile Feedback Testbed

Robots need to be able to adapt to unexpected changes in the environment...

Learning to Represent Haptic Feedback for Partially-Observable Tasks

The sense of touch, being the earliest sensory system to develop in a hu...

Adaptation and Robust Learning of Probabilistic Movement Primitives

Probabilistic representations of movement primitives open important new ...

Interactive Trajectory Adaptation through Force-guided Bayesian Optimization

Flexible manufacturing processes demand robots to easily adapt to change...

Zero-shot sim-to-real transfer of tactile control policies for aggressive swing-up manipulation

This paper aims to show that robots equipped with a vision-based tactile...

Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation

Versatile movement representations allow robots to learn new tasks and r...

Model Mediated Teleoperation with a Hand-Arm Exoskeleton in Long Time Delays Using Reinforcement Learning

Telerobotic systems must adapt to new environmental conditions and deal ...

Please sign up or login with your details

Forgot password? Click here to reset