Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving
| Autor: | Brian Goldfain, iEvangelos A. Theodorou, James M. Rehg, Paul Drews, Grady Williams |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Stochastic control
Scheme (programming language) 0209 industrial biotechnology Mathematical optimization Stochastic process Computer science Monte Carlo method Sampling (statistics) 02 engineering and technology Optimal control Computer Science Applications Task (project management) Model predictive control 020901 industrial engineering & automation Control and Systems Engineering 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Electrical and Electronic Engineering computer computer.programming_language |
| Zdroj: | IEEE Transactions on Robotics. 34:1603-1622 |
| ISSN: | 1941-0468 1552-3098 |
| DOI: | 10.1109/tro.2018.2865891 |
| Popis: | We present an information-theoretic approach to stochastic optimal control problems that can be used to derive general sampling-based optimization schemes. This new mathematical method is used to develop a sampling-based model predictive control algorithm. We apply this information-theoretic model predictive control scheme to the task of aggressive autonomous driving around a dirt test track, and compare its performance with a model predictive control version of the cross-entropy method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|