Repairing Neural Networks for Safety in Robotic Systems using Predictive Models

This paper introduces a new method for safety-aware robot learning, focusing on repairing policies using predictive models. Our method combines behavioral cloning with neural network repair in a two-step supervised learning framework. It first learns a policy from expert demonstrations and then appl...

Full description

Saved in:
Bibliographic Details
Main Authors: Majd, Keyvan, Clark, Geoffrey, Fainekos, Georgios, Amor, Heni Ben
Format: Conference Proceeding
Language:English
Subjects:
Intelligent robots
Maintenance engineering
Mobile robots
Navigation
Neural networks
Predictive models
Propioception
Robot learning
Safety
Supervised learning
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper introduces a new method for safety-aware robot learning, focusing on repairing policies using predictive models. Our method combines behavioral cloning with neural network repair in a two-step supervised learning framework. It first learns a policy from expert demonstrations and then applies repair subject to predictive models to enforce safety constraints. The predictive models can encompass various aspects relevant to robot learning applications, such as proprioceptive states and collision likelihood. Our experimental results demonstrate that the learned policy successfully adheres to a predefined set of safety constraints on two applications: mobile robot navigation, and real-world lower-leg prostheses. Additionally, we have shown that our method effectively reduces repeated interaction with the robot, leading to substantial time savings during the learning process.
ISSN:2153-0866
DOI:10.1109/IROS58592.2024.10802650