Degree of Contribution

Lead

Document Type

Article

Keywords

Mobile robots, Sim2real, simulation, learning

Disciplines

Computer Engineering | Robotics

Abstract

Robot software developed in simulation often does not be- have as expected when deployed because the simulation does not sufficiently represent reality - this is sometimes called the `reality gap' problem. We propose a novel algorithm to address the reality gap by injecting real-world experience into the simulation. It is assumed that the robot program (control policy) is developed using simulation, but subsequently deployed on a real system, and that the program includes a performance objective monitor procedure with scalar output. The proposed approach collects simulation and real world observations and builds conditional probability functions. These are used to generate paired roll-outs to identify points of divergence in simulation and real behavior. From these, state-space kernels are generated that, when integrated with the original simulation, coerce the simulation into behaving more like observed reality. Performance results are presented for a long-term deployment of an autonomous delivery vehicle example.

Publication Title

INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS

Volume

17

Article Number

1082

Publication Date

Summer 2022

Language

English

Version

Published

Creative Commons License

Creative Commons Attribution 4.0 International License
This work is licensed under a Creative Commons Attribution 4.0 International License.

Available for download on Friday, July 01, 2022

Included in

Robotics Commons

Share

COinS