Mobile robots, Sim2real, simulation, learning
Artificial Intelligence and Robotics | Computer Engineering | Robotics
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.
17th INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (IAS-17)
Lyons, Damian; Finocchiaro, James; Novitsky, Misha; and Korpela, Chris, "A Monte Carlo Framework for Incremental Improvement of Simulation Fidelity" (2022). Faculty Publications. 77.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 International License.