AID: 从扩散模型中获取代理意图用于多代理信息路径规划
AID: Agent Intent from Diffusion for Multi-Agent Informative Path Planning
AI总结：
本文提出AID框架，利用扩散模型生成非自回归长时轨迹，通过行为克隆和强化学习优化，提升多代理信息路径规划效率与信息获取能力。
摘要：
在大规模或时间敏感场景（如环境监测、搜索救援）中，需要在有限时间内实现广泛覆盖，推动多代理系统应用。这些场景通常被建模为多代理信息路径规划（MAIPP），多个代理需协调以最大化信息增益，同时受预算约束。MAIPP的核心挑战在于确保有效协调，而环境信念随新测量数据变化。近期基于学习的方法通过使用未来位置分布作为“意图”来支持协调，但这些自回归意图预测器计算成本高且易累积误差。受扩散模型作为表达能力强、长时域策略的启发，我们提出AID，一种完全去中心化的MAIPP框架，利用扩散模型生成非自回归的长时轨迹。AID首先通过现有MAIPP规划器生成的轨迹进行行为克隆，然后通过Diffusion Policy Policy Optimization（DPPO）进行强化学习微调。这种两阶段流程使策略能够继承专家行为，同时通过在线奖励反馈学习改进的协调。实验表明，AID在训练后持续优于其训练的MAIPP规划器，实现4倍更快的执行速度和高达17%的信息增益提升，同时能有效扩展到更多代理。我们的实现可在https://github.com/marmotlab/AID公开获取。
英文摘要：
Information gathering in large-scale or time-critical scenarios (e.g., environmental monitoring, search and rescue) requires broad coverage within limited time budgets, motivating the use of multi-agent systems. These scenarios are commonly formulated as multi-agent informative path planning (MAIPP), where multiple agents must coordinate to maximize information gain while operating under budget constraints. A central challenge in MAIPP is ensuring effective coordination while the belief over the environment evolves with incoming measurements. Recent learning-based approaches address this by using distributions over future positions as "intent" to support coordination. However, these autoregressive intent predictors are computationally expensive and prone to compounding errors. Inspired by the effectiveness of diffusion models as expressive, long-horizon policies, we propose AID, a fully decentralized MAIPP framework that leverages diffusion models to generate long-term trajectories in a non-autoregressive manner. AID first performs behavior cloning on trajectories produced by existing MAIPP planners and then fine-tunes the policy using reinforcement learning via Diffusion Policy Policy Optimization (DPPO). This two-stage pipeline enables the policy to inherit expert behavior while learning improved coordination through online reward feedback. Experiments demonstrate that AID consistently improves upon the MAIPP planners it is trained from, achieving 4x faster execution and up to 17% increased information gain, while scaling effectively to larger numbers of agents. Our implementation is publicly available at https://github.com/marmotlab/AID.
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。
