DOBB：面向状态不确定与异构动力学的动态定向包围盒多智能体避碰方法
DOBB: Dynamic Oriented Bounding Boxes for Multi-Agent Collision Avoidance under State Uncertainty and Heterogeneous Dynamics
AI 导读
arXiv 论文提出动态定向包围盒（DOBB），一种在线几何表示，将状态估计、不确定性与智能体响应特性映射为随方向变化的安全边距。在四个评估环境中，DOBB 的平均总失败率最低，仅 2.6%，且在执行动力学和状态估计不确定性的分布外偏移下，碰撞失败率在每个测试条件下均保持在 2.3% 或以下。这种鲁棒性源于安全边距的几何抽象，降低了对训练分布的耦合。
正文 · 原文
Abstract:Learning-based decentralized collision avoidance must remain reliable under state-estimation uncertainty and heterogeneous agent dynamics. Existing methods typically address these factors through training-domain variation or by exposing uncertainty and capability estimates to the policy at runtime. However, both leave the policy to infer how these quantities should alter the physical separation required for safe interaction, which can couple collision-avoidance behavior to relationships learned from the training distribution. We introduce the Dynamic Oriented Bounding Box (DOBB), an online geometric representation that maps the current state estimate, uncertainty, and agent-specific response characteristics into a dynamic, direction-dependent safety margin. We derive geometric features that jointly characterize the relative configuration and severity of interactions between agents' DOBBs, along with a reward function that preserves the physical interpretation of those interactions. Across four evaluation environments, DOBB achieves the lowest mean total failure rate of 2.6%. This performance persists under out-of-distribution shifts in actuation dynamics and state-estimation uncertainty, with collision-based failure remaining at or below 2.3% in every tested condition. We attribute this robustness to the geometric abstraction of the safety margin, which is less coupled to the specific uncertainty and actuation regimes encountered during training.
| Subjects: | Robotics (cs.RO); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13142 [cs.RO] |
| (or arXiv:2611.13142v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13142 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Pedro Antonio Alarcon Granadeno [view email]
[v1]
Mon, 9 Nov 2026 19:23:34 UTC (293 KB)
来源：arXiv cs.AI · arxiv.org