arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.06925cs.ROcs.GT
收藏

高速策略化:多无人机竞速的学习型模型预测博弈

Strategizing at Speed: A Learned Model Predictive Game for Multi-Agent Drone Racing

Department of Cognitive Robotics, Delft University of Technology(认知机器人学系,代尔夫特理工大学)

Andrei-Carlo Papuc, Lasse Peters, Sihao Sun, Laura Ferranti, Javier Alonso-Mora

AI总结:

针对多无人机竞速中策略深度与计算延迟的权衡问题,提出一种学习型模型预测博弈(LMPG)方法,通过摊销模型预测博弈计算来降低延迟,在仿真和硬件实验中优于模型预测博弈和模型预测控制。

摘要:

自主无人机竞速推动了高速运动规划与多智能体策略决策的边界。在此领域,无人机不仅需要极限导航,还需预测并反制竞争对手的动作。本文研究一个基本问题:智能体在采取行动前应进行多深层次的策略思考?为此,我们比较两种规划范式:模型预测博弈(MPG)以较长的计算时间为代价获得交互感知策略,以及轮廓模型预测控制(MPC)快速计算策略但不考虑交互。我们进行了大量实验来研究这一权衡,发现MPG在中速时优于MPC,但在高速时因延迟而失去优势。为解决此问题,我们提出一种学习型模型预测博弈(LMPG)方法,通过摊销模型预测博弈计算来减少延迟。在仿真和硬件实验中,我们在头对头竞速中将我们的方法与MPG和MPC进行基准测试,发现LMPG优于两种基线方法。

英文摘要:

Autonomous drone racing pushes the boundaries of high-speed motion planning and multi-agent strategic decision-making. Success in this domain requires drones not only to navigate at their limits but also to anticipate and counteract competitors' actions. In this paper, we study a fundamental question that arises in this domain: how deeply should an agent strategize before taking an action? To this end, we compare two planning paradigms: the Model Predictive Game (MPG), which finds interaction-aware strategies at the expense of longer computation times, and contouring Model Predictive Control (MPC), which computes strategies rapidly but does not reason about interactions. We perform extensive experiments to study this trade-off, revealing that MPG outperforms MPC at moderate velocities but loses its advantage at higher speeds due to latency. To address this shortcoming, we propose a Learned Model Predictive Game (LMPG) approach that amortizes model predictive gameplay to reduce latency. In both simulation and hardware experiments, we benchmark our approach against MPG and MPC in head-to-head races, finding that LMPG outperforms both baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑