Loading [a11y]/accessibility-menu.js
Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces | IEEE Journals & Magazine | IEEE Xplore

Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces


Abstract:

When the dynamics of a system are difficult to model and/or time-consuming to evaluate, such as in deformable object manipulation tasks, motion planning algorithms strugg...Show More

Abstract:

When the dynamics of a system are difficult to model and/or time-consuming to evaluate, such as in deformable object manipulation tasks, motion planning algorithms struggle to find feasible plans efficiently. Such problems are often reduced to state spaces where the dynamics are straightforward to model and evaluate. However, such reductions usually discard information about the system for the benefit of computational efficiency, leading to cases where the true and reduced dynamics disagree on the result of an action. This letter presents a formulation for planning in reduced state spaces that uses a classifier to bias the planner away from state-action pairs that are not reliably feasible under the true dynamics. We present a method to generate and label data to train such a classifier, as well as an application of our framework to rope manipulation, where we use a Virtual Elastic Band (VEB) approximation to the true dynamics. Our experiments with rope manipulation demonstrate that the classifier significantly improves the success rate of our RRT-based planner in several difficult scenarios which are designed to cause the VEB to produce incorrect predictions in key parts of the environment.
Published in: IEEE Robotics and Automation Letters ( Volume: 5, Issue: 2, April 2020)
Page(s): 3540 - 3547
Date of Publication: 10 February 2020

ISSN Information:

Funding Agency:


References

References is not available for this document.