BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shen, Keyi, Yu, Jiangwei, Barreiros, Jose, Zhang, Huan, Li, Yunzhu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909538217623552
author Shen, Keyi
Yu, Jiangwei
Barreiros, Jose
Zhang, Huan
Li, Yunzhu
author_facet Shen, Keyi
Yu, Jiangwei
Barreiros, Jose
Zhang, Huan
Li, Yunzhu
contents Neural-network-based dynamics models learned from observational data have shown strong predictive capabilities for scene dynamics in robotic manipulation tasks. However, their inherent non-linearity presents significant challenges for effective planning. Current planning methods, often dependent on extensive sampling or local gradient descent, struggle with long-horizon motion planning tasks involving complex contact events. In this paper, we present a GPU-accelerated branch-and-bound (BaB) framework for motion planning in manipulation tasks that require trajectory optimization over neural dynamics models. Our approach employs a specialized branching heuristics to divide the search space into subdomains, and applies a modified bound propagation method, inspired by the state-of-the-art neural network verifier alpha-beta-CROWN, to efficiently estimate objective bounds within these subdomains. The branching process guides planning effectively, while the bounding process strategically reduces the search space. Our framework achieves superior planning performance, generating high-quality state-action trajectories and surpassing existing methods in challenging, contact-rich manipulation tasks such as non-prehensile planar pushing with obstacles, object sorting, and rope routing in both simulated and real-world settings. Furthermore, our framework supports various neural network architectures, ranging from simple multilayer perceptrons to advanced graph neural dynamics models, and scales efficiently with different model sizes.
format Preprint
id arxiv_https___arxiv_org_abs_2412_09584
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics
Shen, Keyi
Yu, Jiangwei
Barreiros, Jose
Zhang, Huan
Li, Yunzhu
Robotics
Neural-network-based dynamics models learned from observational data have shown strong predictive capabilities for scene dynamics in robotic manipulation tasks. However, their inherent non-linearity presents significant challenges for effective planning. Current planning methods, often dependent on extensive sampling or local gradient descent, struggle with long-horizon motion planning tasks involving complex contact events. In this paper, we present a GPU-accelerated branch-and-bound (BaB) framework for motion planning in manipulation tasks that require trajectory optimization over neural dynamics models. Our approach employs a specialized branching heuristics to divide the search space into subdomains, and applies a modified bound propagation method, inspired by the state-of-the-art neural network verifier alpha-beta-CROWN, to efficiently estimate objective bounds within these subdomains. The branching process guides planning effectively, while the bounding process strategically reduces the search space. Our framework achieves superior planning performance, generating high-quality state-action trajectories and surpassing existing methods in challenging, contact-rich manipulation tasks such as non-prehensile planar pushing with obstacles, object sorting, and rope routing in both simulated and real-world settings. Furthermore, our framework supports various neural network architectures, ranging from simple multilayer perceptrons to advanced graph neural dynamics models, and scales efficiently with different model sizes.
title BaB-ND: Long-Horizon Motion Planning with Branch-and-Bound and Neural Dynamics
topic Robotics
url https://arxiv.org/abs/2412.09584