改进运动规划算法，让机器人在障碍物前不犹豫、不碰撞。
Clustering-Embedded Model Predictive Path Integral Control: Avoiding Averaging-Induced Failure and Enabling Efficient Cluster Selection for Dynamic Obstacles
- 用聚类方法分离可行与不可行轨迹，避免传统算法因平均导致的错误决策。
- 在动态场景中主动避开移动障碍，实测路径缩短12%，到达时间减少48%。
- 适合需要高可靠性的机械臂避障任务，尤其适合复杂动态环境。
随着并行计算硬件普及，基于采样的运动规划方法如模型预测路径积分（MPPI）在非光滑任务空间中的复杂非线性系统中日益强大。然而，标准MPPI的采样与前向仿真流程在杂乱环境中易出现平均化失效问题：重要性加权更新会混合不兼容的轨迹，导致障碍物正前方时出现迟疑甚至碰撞。本文提出聚类嵌入式MPPI（CE-MPPI），通过引入高保真剪枝与聚类阶段，从根本上解决标准MPPI在非凸环境中的固有缺陷。该方法结合基于密度的空间聚类算法（DBSCAN）与一种从碰撞参考点提取的新几何方向特征，将可行轨迹模式从不可行轨迹噪声中分离。同时采用智能选择逻辑：静态场景下优化最小代价，动态场景中主动反向于障碍物流。2D JAX加速仿真实验显示，CE-MPPI有效缓解了障碍物前迟疑问题，并避免与移动障碍物持续耦合。真实世界测试中，搭载CUDA并行轨迹生成的6-DoF UR5e机械臂在Isaac Gym平台实现时间到目标减少48%，末端执行器路径缩短12%。
原文摘要 · Abstract (English)
With the widespread availability of parallel computing hardware, sampling-based motion planning methods such as Model Predictive Path Integral (MPPI) control have become increasingly powerful for complex nonlinear systems in non-smooth task spaces. However, the sampling and forward-simulation pipeline in MPPI suffers from averaging-induced failure in cluttered environments, where the importance-weighted update averages incompatible rollouts and leads to hesitation or even collision when an obstacle lies directly ahead. This paper proposes Clustering-Embedded MPPI (CE-MPPI), a framework that architecturally resolves the averaging-induced failures inherent in standard MPPI within non-convex environments. Rather than simply mitigating interference, CE-MPPI redefines the control law by integrating a high-fidelity pruning and clustering stage. By leveraging density-based spatial clustering of applications with noise (DBSCAN) alongside a novel geometric direction feature that is extracted from collision-derived reference points, the system isolates feasible trajectory modes from the noise of infeasible rollouts. This is paired with an intelligent selection logic that optimizes for minimum cost in static scenes while actively steering opposite to obstacle flux in dynamic environments. Experiments in 2-D JAX-accelerated simulations show that CE-MPPI alleviates obstacle-front hesitation and avoids persistent coupling with moving obstacles in dynamic scenes. In particular, real-world tests on a 6-DoF UR5e manipulator with CUDA-parallel rollouts in Isaac Gym achieve a 48\% reduction in time-to-goal and a 12\% shorter end-effector path.
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。