الملخص
GAMBIT is an opening chess move in which a player sacrifices a piece, typically a pawn, to gain a positional advantage later in the game. Analogously, in multi-robot coordination, individual robots may need to forgo locally reward-maximising behaviours to improve overall team performance. Such self-sacrificial behaviours are difficult to capture with manually designed heuristics, particularly in dense, interaction-rich environments. Focusing on double-integrator continuous dynamics, this work studies how to learn such coordinated heuristics over motion primitives for multi-robot trajectory execution. Our framework, GAMBIT, first learns coordinated motion-primitive selection through imitation learning and subsequently fine-tunes the policy through reinforcement learning. We further introduce a safeguarded rollout mechanism with backup trajectories that guarantees collision-free execution at all times. Experiments demonstrate that GAMBIT substantially outperforms a range of baselines, including centralised motion planners and decentralised reactive planners, while exhibiting strong scalability. In particular, it coordinates over a thousand robots with planning latency below a few hundred milliseconds in continuous domains.
الكلمات المفتاحية
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Jain, R., Moldagalieva, A., Magnino, L., Amir, M., Okumura, K., Shankar, A., Hönig, W., & Prorok, A. (2026). GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories. https://omanscience.com/ar/articles/gambit-learning-to-plan-continuous-multi-robot-trajectories
MLA 9
Jain, Rishabh, et al. "GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories." https://omanscience.com/ar/articles/gambit-learning-to-plan-continuous-multi-robot-trajectories.
شيكاغو (المؤلف–التاريخ)
Jain, Rishabh, Akmaral Moldagalieva, Lorenzo Magnino, Michael Amir, Keisuke Okumura, Ajay Shankar, Wolfgang Hönig, and Amanda Prorok. 2026. "GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories." https://omanscience.com/ar/articles/gambit-learning-to-plan-continuous-multi-robot-trajectories.
هارفارد
Jain, R., Moldagalieva, A., Magnino, L., Amir, M., Okumura, K., Shankar, A., Hönig, W. and Prorok, A. (2026) 'GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories', Available at: https://omanscience.com/ar/articles/gambit-learning-to-plan-continuous-multi-robot-trajectories.
فانكوفر
Jain R, Moldagalieva A, Magnino L, Amir M, Okumura K, Shankar A, et al. GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories. https://omanscience.com/ar/articles/gambit-learning-to-plan-continuous-multi-robot-trajectories
IEEE
R. Jain, A. Moldagalieva, L. Magnino, M. Amir, K. Okumura, A. Shankar, W. Hönig, and A. Prorok, "GAMBIT: Learning to Plan Continuous Multi-Robot Trajectories," https://omanscience.com/ar/articles/gambit-learning-to-plan-continuous-multi-robot-trajectories.