Long-horizon motion planning with branch-and-bound and neural dynamics

Shen, Keyi

Permalink

https://hdl.handle.net/2142/129224 Copy

Description

Title

Long-horizon motion planning with branch-and-bound and neural dynamics

Author(s)

Shen, Keyi

Issue Date

2025-05-09

Director of Research (if dissertation) or Advisor (if thesis)

• Zhang, Huan
• Li, Yunzhu

Department of Study

Electrical & Computer Eng

Discipline

Electrical & Computer Engr

Degree Granting Institution

University of Illinois Urbana-Champaign

Degree Name

M.S.

Degree Level

Thesis

Keyword(s)

• Robotic Manipulation
• Model-based Planning
• Neural Dynamics Models
• Branch-and-bound Method

Language

eng

Abstract

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 α,β-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.

Graduation Semester

2025-05

Type of Resource

Text

Handle URL

https://hdl.handle.net/2142/129224

Copyright and License Information

Copyright 2025 Keyi Shen

Owning Collections