用动态预测高斯场提升机器人避障能力，零碰撞率且实时运行。
MPPI Planning with Gaussian-Based Human Cost Function for Social Navigation
- 将行人预测扩展到整个规划时长，生成方向对齐的高斯排斥场
- 在三种密度场景下实现0%碰撞率，优于传统方法最高82%的碰撞率
- 适合需要高安全性的复杂人群导航场景，如服务机器人
在拥挤空间中安全导航需考虑人未来的位置，而非仅当前位置。模型预测路径积分（MPPI）是一种高效的采样式规划器，但多数实现将人视为静止点障碍物，低估了动态场景中的风险。本文提出预测高斯交互场（PGIF），一种时空代价函数，将行人预测向前推进至完整规划时长，并将其编码为与行人运动方向一致的各向异性高斯排斥场。每个场的扩散范围随行人的速度增长，形成运动锥形危险区，更严厉惩罚进入行人行进路径的机器人轨迹，而非从后方接近的轨迹。该公式为闭式表达，可在多个回溯中完全并行化，计算开销可忽略不计。在300个随机化人群场景、三种密度水平下评估，PGIF-MPPI在所有密度下均实现0%碰撞率，而原始MPPI最高达82%碰撞率，同时保持实时规划性能。
原文摘要 · Abstract (English)
Safe robot navigation in crowded spaces requires planning that accounts for where people will be, not only where they are now. Model Predictive Path Integral (MPPI) control is an effective sampling-based planner, but many implementations encode humans as static point obstacles at their current positions, underestimating risk in dynamic scenes. We propose Predictive Gaussian Interaction Fields (PGIF), a spatiotemporal cost formulation that propagates pedestrian predictions forward over the full planning horizon and encodes them as anisotropic Gaussian repulsive fields aligned with each pedestrian's direction of motion. The forward spread of each field grows with the pedestrian's speed, creating a motion cone danger zone that penalises robot trajectories entering the pedestrian's path of travel more strongly than those approaching from behind. The formulation is closed-form and fully parallelisable across rollouts, adding no measurable computational overhead. Evaluated over 300 randomised crowd scenarios at three density levels, PGIF-MPPI achieves a 0% collision rate at every density level, compared with up to 82% for vanilla MPPI, while maintaining real-time planning performance.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。