2015/03/01 by Grady Williams, Williams, Grady, Eric Rombokas +4 · 11 citations
Computer Science · Engineering · #Acoustics #Advanced Control Systems Optimization #Artificial intelligence #Computer science #Control (management) #Dynamics (music) #Path (computing) #Path integral formulation #Physics #Programming language #Robotic Path Planning Algorithms #Robotics and Sensor-Based Localization #cs.RO
paper · pdf · doi:10.48550/arxiv.1503.00330
published in arXiv (Cornell University) (Cornell University) · 6 pages, NIPS 2014 - Autonomously Learning Robots Workshop
arxiv created 2015/03/01 · openalex publication_date 2015/03/01 · arxiv updated 2015/03/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
We present an algorithm which combines recent advances in model based path integral control with machine learning approaches to learning forward dynamics models. We take advantage of the parallel computing power of a GPU to quickly take a massive number of samples from a learned probabilistic dynamics model, which we use to approximate the path integral form of the optimal control. The resulting algorithm runs in a receding-horizon fashion in realtime, and is subject to no restrictive assumptions about costs, constraints, or dynamics. A simple change to the path integral control formulation allows the algorithm to take model uncertainty into account during planning, and we demonstrate its performance on a quadrotor navigation task. In addition to this novel adaptation of path integral control, this is the first time that a receding-horizon implementation of iterative path integral control has been run on a real system.