Fast Motion Planning for High-DOF Robot Systems Using Hierarchical System Identification
Lists
Only you see this
Abstract
We present an efficient algorithm for motion planning and controlling a robot system with a high number of degrees-of-freedom (DOF). These systems include high-DOF soft robots and articulated robots interacting with a deformable environment. We present a novel technique to accelerate the evaluations of the forward dynamics function by storing the results of costly computations in a hierarchical adaptive grid. Furthermore, we exploit the underactuated properties of the robot systems and build the grid in a low-dimensional space. Our approach approximates the forward dynamics function with guaranteed error bounds and can be used in optimization-based motion planning and reinforcement-learning-based feed-back control. We highlight the performance on two high-DOF robot systems: a line-actuated elastic robot arm and an underwater swimming robot in water. Compared to prior techniques based on exact dynamics evaluation, we observe one to two orders of magnitude improvement in the performance.
BibTeX
@inproceedings{jia2019fast,
author = {Biao Jia and Zherong Pan and Dinesh Manocha},
title = {{Fast Motion Planning for High-DOF Robot Systems Using Hierarchical System Identification}},
booktitle = {IEEE International Conference on Robotics and Automation},
year = {2019},
doi = {10.1109/icra.2019.8793814},
}| Adaptive Dynamics with Efficient Contact Handling for Articulated Robots | Robotics: Science and Systems · 2006 |
| Model-based Optimal Control for Rigid-Soft Underactuated Systems | arXiv · 2026 |
| Cost-to-Go Function Generating Networks for High Dimensional Motion Planning | arXiv · 2020 |
| Hierarchical Motion Planning in Topological Representations | Robotics: Science and Systems · 2012 |
| Learning Reduced-Order Soft Robot Controller | arXiv · 2023 |
| Soft Robot Optimal Control Via Reduced Order Finite Element Models | arXiv · 2020 |