# Manifold-constrained Hamilton-Jacobi Reachability Learning for Decentralized Multi-Agent Motion Planning

Source: [Manifold-constrained Hamilton-Jacobi Reachability Learning for Decentralized Multi-Agent Motion Planning](<https://www.sota2.com/research/paper/690c2b832828b7cc6937c596>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-07-03T05:00:04.966Z

Authors: Qingyi Chen, Ruiqi Ni, Junyoung Kim, Ahmed H. Qureshi

Published: 2025-11-05T16:11:12.000Z

## Abstract

Safe multi-agent motion planning (MAMP) under task-induced constraints is a critical challenge in robotics. Many real-world scenarios require robots to navigate dynamic environments while adhering to manifold constraints imposed by tasks. For example, service robots must carry cups upright while avoiding collisions with humans or other robots. Despite recent advances in decentralized MAMP for high-dimensional systems, incorporating manifold constraints remains difficult. To address this, we propose a manifold-constrained Hamilton-Jacobi reachability (HJR) learning framework for decentralized MAMP. Our method solves HJR problems under manifold constraints to capture task-aware safety conditions, which are then integrated into a decentralized trajectory optimization planner. This enables robots to generate motion plans that are both safe and task-feasible without requiring assumptions about other agents' policies. Our approach generalizes across diverse manifold-constrained tasks and scales effectively to high-dimensional multi-agent manipulation problems. Experiments show that our method outperforms existing constrained motion planners and operates at speeds suitable for real-world applications. Video demonstrations are available at https://youtu.be/RYcEHMnPTH8 .

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Cup-holding goal-reaching on Cup-holding UR5 Manipulators 2 agents](<https://www.sota2.com/research/sota/cup-holding-goal-reaching-on-cup-holding-ur5-manipulators-2-agents.md>): Cup-holding goal-reaching; Cup-holding UR5 Manipulators 2 agents; Success Rate (SR): 82.

- [Multi-agent motion planning on Doorway-crossing experiment](<https://www.sota2.com/research/sota/multi-agent-motion-planning-on-doorway-crossing-experiment.md>): Multi-agent motion planning; Doorway-crossing experiment; Success Rate: 71.

- [Object-carrying on Object-carrying task](<https://www.sota2.com/research/sota/object-carrying-on-object-carrying-task.md>): Object-carrying; Object-carrying task; Success Rate (SR): 85.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2511.03591>)

[PDF](<https://arxiv.org/pdf/2511.03591.pdf>)