SafeAPT: Safe Simulation-to-Real Robot Learning Using Diverse Policies Learned in Simulation

Loading...
Thumbnail Image

Access rights

openAccess
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Date

2022-07-01

Major/Subject

Mcode

Degree programme

Language

en

Pages

8

Series

IEEE Robotics and Automation Letters, Volume 7, issue 3, pp. 6838-6845

Abstract

The framework of sim-to-real learning, i.e., training policies in simulation and transferring them to real-world systems, is one of the most promising approaches towards data-efficient learning in robotics. However, due to the inevitable reality gap between the simulation and the real world, a policy learned in the simulation may not always generate a safe behaviour on the real robot. As a result, during policy adaptation in the real world, the robot may damage itself or cause harm to its surroundings. In this work, we introduce SafeAPT, a multi-goal robot learning algorithm that leverages a diverse repertoire of policies evolved in simulation and transfers the most promising safe policy to the real robot through episodic interaction. To achieve this, SafeAPT iteratively learns probabilistic reward and safety models from real-world observations using simulated experiences as priors. Then, it performs Bayesian optimization to select the best policy from the repertoire with the reward model, while maintaining the specified safety constraint using the safety model. SafeAPT allows a robot to adapt to a wide range of goals safely with the same repertoire of policies evolved in the simulation. We compare SafeAPT with several baselines, both in simulated and real robotic experiments, and show that SafeAPT finds high-performing policies within a few minutes of real-world operation while minimizing safety violations during the interactions.

Description

Publisher Copyright: © 2016 IEEE.

Keywords

Evolutionary robotics, learning from experience, machine learning for robot control

Other note

Citation

Kaushik, R, Arndt, K & Kyrki, V 2022, ' SafeAPT: Safe Simulation-to-Real Robot Learning Using Diverse Policies Learned in Simulation ', IEEE Robotics and Automation Letters, vol. 7, no. 3, pp. 6838-6845 . https://doi.org/10.1109/LRA.2022.3177294