Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics
Robotics
2020-05-07 v3 Machine Learning
Systems and Control
Systems and Control
Optimization and Control
Abstract
This paper focuses on learning a model of system dynamics online while satisfying safety constraints.Our motivation is to avoid offline system identification or hand-specified dynamics models and allowa system to safely and autonomously estimate and adapt its own model during online operation.Given streaming observations of the system state, we use Bayesian learning to obtain a distributionover the system dynamics. In turn, the distribution is used to optimize the system behavior andensure safety with high probability, by specifying a chance constraint over a control barrier function.
Cite
@article{arxiv.1912.10116,
title = {Probabilistic Safety Constraints for Learned High Relative Degree System Dynamics},
author = {Mohammad Javad Khojasteh and Vikas Dhiman and Massimo Franceschetti and Nikolay Atanasov},
journal= {arXiv preprint arXiv:1912.10116},
year = {2020}
}
Comments
To appear in L4DC 2020. First two authors contributed equally