Information Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving
About
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 (IT-MPC) scheme to the task of aggressive autonomous driving around a dirt test track, and compare its performance to a model predictive control version of the cross-entropy method.
Grady Williams, Paul Drews, Brian Goldfain, James M. Rehg, Evangelos A. Theodorou• 2017
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| BlackBox Optimization | Rastrigin | Optimized Cost3.65e+3 | 18 | |
| BlackBox Optimization | Levy | Optimized Cost744.3 | 18 | |
| BlackBox Optimization | Ackley | Optimized Cost14.2 | 18 | |
| Trajectory Optimization | Humanoid Standup | Computational Time (s)17.7 | 8 | |
| Trajectory Optimization | Walker2D | Computational Time (s)34.7 | 8 | |
| Trajectory Optimization | Push T | Time (s)1.03e+3 | 8 | |
| Path planning | Simulated Path Planning Environment 1 | Steps137 | 6 | |
| Path planning | Simulated Path Planning Environment 3 | Steps150 | 6 | |
| Path planning | Simulated Path Planning Environment 4 | Steps198 | 6 | |
| Trajectory Optimization | Halfcheetah | Optimized Cost0.924 | 6 |
Showing 10 of 31 rows