# DOBB动态包围盒算法实现多智能体2.6%低碰撞率

> 原文链接：https://robotics.hellobike.com/papers/2026-11-11-2611-13142-72f0a4e9
> 频道：papers | 更新日期：2026-11-11 | 标签：auto, arxiv
> 核心摘要：针对状态不确定与异构动力学挑战，DOBB算法将安全裕度映射为方向依赖的几何边界。在四类环境中平均总失败率仅2.6%，OOD工况下碰撞失败率≤2.3%，显著提升多机避障鲁棒性。

# DOBB动态包围盒算法实现多智能体2.6%低碰撞率

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[DOBB: Dynamic Oriented Bounding Boxes for Multi-Agent Collision Avoidance under State Uncertainty and Heterogeneous Dynamics](https://arxiv.org/abs/2611.13142)（arXiv 2611.13142）

## 核心内容

针对学习型去中心化避障在状态估计不确定及异构动力学下的可靠性难题，研究提出动态定向包围盒（DOBB）方法。该方案摒弃了传统依赖训练域变化或运行时暴露不确定性估计的做法，转而构建在线几何表征。实验显示，DOBB在四个评估环境中取得最低平均总失败率2.6%，且在执行动力学与状态估计不确定性发生分布外偏移时，碰撞失败率始终控制在2.3%及以下。

DOBB核心机制是将当前状态估计、不确定性及智能体响应特性映射为动态、方向相关的安全裕度，并推导联合表征相对构型与交互严重度的几何特征，配合保持物理可解释性的奖励函数。这种安全裕度的几何抽象有效解耦了避障行为与特定训练分布的关联，使策略无需重新学习即可适应未见的致动器动态与感知噪声水平，解决了现有方法因耦合训练数据导致的泛化瓶颈。

## 关键看点

- **核心指标**：四环境评测平均总失败率2.6%，OOD条件下碰撞失败率≤2.3%，优于传统方法
- **技术机制**：构建DOBB在线几何表征，将状态不确定性与异构动力学映射为方向依赖安全裕度
- **泛化原理**：通过几何特征抽象解耦避障策略与训练分布，避免对特定噪声与致动模式的过拟合
- **算法设计**：推导交互严重度几何特征并设计物理可解释奖励函数，保障安全边界的语义一致性

## 工程与产业观察

DOBB通过将不确定性转化为几何安全边界，解决了多机协同中感知噪声与动力学差异导致的避障失效痛点。其2.6%的低失败率与强OOD鲁棒性表明，基于几何抽象的安全约束比纯端到端学习更适合高可靠具身导航任务，为异构机器人集群在非标环境下的部署提供了可验证的理论支撑。

## 英文摘要 (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.

作者：Pedro Antonio Alarcon Granadeno, Jane Cleland-Huang
:::

## 原始参考来源 (Sources)

- [arXiv 2611.13142：DOBB: Dynamic Oriented Bounding Boxes for Multi-Agent Collision Avoidance under State Uncertainty and Heterogeneous Dynamics](https://arxiv.org/abs/2611.13142)