I am a master student working with Dr. Nancy M. Amato on multi-robot motion planning. I joined the lab as an REU (Research Experience for Undergraduate) student in summer 2021 where I worked closely with Irving Solis on developing a hybrid approach that combines the advantages of coupled and decoupled approaches for solving the multi-robot motion planning problem.
My current work focuses on developing trajectory optimization techniques that can be applied in a multi-robot system. As a research assistant in the lab, I also contributed to developing our C++ open-source task and motion planning library, PPL (Parasol Planning Library).
Previously, I worked as a student intern at CyberGIS Center where my work involves visualization of geographic data and data/big data processing.
Research
Multi-Agent Systems
Publications
Adaptive Robot Coordination: A Subproblem-based Approach for Hybrid Multi-Robot Motion Planning, Irving Solis, James Motes, Mike Qin, Marco Morales, Nancy M. Amato, ArXiv Preprint, Dec 2023. DOI: https://arxiv.org/abs/2312.08554 @misc{solis2023adaptive, This work presents Adaptive Robot Coordination (ARC), a novel hybrid framework for multi-robot motion planning (MRMP) that employs local subproblems to resolve inter-robot conflicts. ARC creates subproblems centered around conflicts, and the solutions represent the robot motions required to resolve these conflicts. The use of subproblems enables an inexpensive hybrid exploration of the multi-robot planning space. ARC leverages the hybrid exploration by dynamically adjusting the coupling and decoupling of the multi-robot planning space. This allows ARC to adapt the levels of coordination efficiently by planning in decoupled spaces, where robots can operate independently, and in coupled spaces where coordination is essential. ARC is probabilistically complete, can be used for any robot, and produces efficient cost solutions in reduced planning times. Through extensive evaluation across representative scenarios with different robots requiring various levels of coordination, ARC demonstrates its ability to provide simultaneous scalability and precise coordination. ARC is the only method capable of solving all the scenarios and is competitive with coupled, decoupled, and hybrid baselines.
Keywords: Motion Planning, Multi-Agent Systems, Sampling-Based Motion Planning
Links : [ArXiv] BibTex
title={Adaptive Robot Coordination: A Subproblem-based Approach for Hybrid Multi-Robot Motion Planning},
author={Irving Solis and James Motes and Mike Qin and Marco Morales and Nancy M. Amato},
year={2023},
eprint={2312.08554},
archivePrefix={arXiv},
primaryClass={cs.RO}
}Abstract