Saved in:
Bibliographic Details
Main Authors: Matada, Sharath, Bhan, Luke, Shi, Yuanyuan, Atanasov, Nikolay
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.17547
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915305834414080
author Matada, Sharath
Bhan, Luke
Shi, Yuanyuan
Atanasov, Nikolay
author_facet Matada, Sharath
Bhan, Luke
Shi, Yuanyuan
Atanasov, Nikolay
contents In this work, we introduce a planning neural operator (PNO) for predicting the value function of a motion planning problem. We recast value function approximation as learning a single operator from the cost function space to the value function space, which is defined by an Eikonal partial differential equation (PDE). Therefore, our PNO model, despite being trained with a finite number of samples at coarse resolution, inherits the zero-shot super-resolution property of neural operators. We demonstrate accurate value function approximation at $16\times$ the training resolution on the MovingAI lab's 2D city dataset, compare with state-of-the-art neural value function predictors on 3D scenes from the iGibson building dataset and showcase optimal planning with 4-DOF robotic manipulators. Lastly, we investigate employing the value function output of PNO as a heuristic function to accelerate motion planning. We show theoretically that the PNO heuristic is $ε$-consistent by introducing an inductive bias layer that guarantees our value functions satisfy the triangle inequality. With our heuristic, we achieve a $30\%$ decrease in nodes visited while obtaining near optimal path lengths on the MovingAI lab 2D city dataset, compared to classical planning methods ($A^\ast$, $RRT^\ast$).
format Preprint
id arxiv_https___arxiv_org_abs_2410_17547
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generalizable Motion Planning via Operator Learning
Matada, Sharath
Bhan, Luke
Shi, Yuanyuan
Atanasov, Nikolay
Robotics
In this work, we introduce a planning neural operator (PNO) for predicting the value function of a motion planning problem. We recast value function approximation as learning a single operator from the cost function space to the value function space, which is defined by an Eikonal partial differential equation (PDE). Therefore, our PNO model, despite being trained with a finite number of samples at coarse resolution, inherits the zero-shot super-resolution property of neural operators. We demonstrate accurate value function approximation at $16\times$ the training resolution on the MovingAI lab's 2D city dataset, compare with state-of-the-art neural value function predictors on 3D scenes from the iGibson building dataset and showcase optimal planning with 4-DOF robotic manipulators. Lastly, we investigate employing the value function output of PNO as a heuristic function to accelerate motion planning. We show theoretically that the PNO heuristic is $ε$-consistent by introducing an inductive bias layer that guarantees our value functions satisfy the triangle inequality. With our heuristic, we achieve a $30\%$ decrease in nodes visited while obtaining near optimal path lengths on the MovingAI lab 2D city dataset, compared to classical planning methods ($A^\ast$, $RRT^\ast$).
title Generalizable Motion Planning via Operator Learning
topic Robotics
url https://arxiv.org/abs/2410.17547