基于点云输入的神经运动策略，实现在动态环境中的实时避障与规划。
Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments
- 采用基于Transformer的神经政策，直接处理点云输入生成反应式动作。
- 在模拟与真实场景中成功率显著超越传统方法和已有神经方法。
- 适合需要快速响应复杂动态环境的机械臂任务，如工业装配与服务机器人。
在部分可观测的动态环境中生成无碰撞运动路径，是机器人机械臂的核心挑战。经典运动规划器虽能计算全局最优轨迹，但需完整环境信息且运行缓慢；神经运动策略虽可闭环处理原始感知输入，却常在复杂或动态场景中泛化能力不足。本文提出深度反应策略（Deep Reactive Policy, DRP），一种面向多样动态环境的视觉-运动神经策略，直接处理点云感知输入。其核心为IMPACT，一个基于变压器的神经运动策略，在1000万条生成专家轨迹上预训练，覆盖多种仿真场景。通过迭代师生微调提升静态障碍物避让能力，并引入局部反应式目标提议模块DCP-RMP，增强推理时对动态障碍物的避让能力。在包含杂乱场景、移动障碍物及目标遮挡的挑战性任务中评估，DRP展现出优异泛化性能，成功率达到现有经典与神经方法的领先水平。视频与代码见https://deep-reactive-policy.com
原文摘要 · Abstract (English)
Generating collision-free motion in dynamic, partially observable environments is a fundamental challenge for robotic manipulators. Classical motion planners can compute globally optimal trajectories but require full environment knowledge and are typically too slow for dynamic scenes. Neural motion policies offer a promising alternative by operating in closed-loop directly on raw sensory inputs but often struggle to generalize in complex or dynamic settings. We propose Deep Reactive Policy (DRP), a visuo-motor neural motion policy designed for reactive motion generation in diverse dynamic environments, operating directly on point cloud sensory input. At its core is IMPACT, a transformer-based neural motion policy pretrained on 10 million generated expert trajectories across diverse simulation scenarios. We further improve IMPACT's static obstacle avoidance through iterative student-teacher finetuning. We additionally enhance the policy's dynamic obstacle avoidance at inference time using DCP-RMP, a locally reactive goal-proposal module. We evaluate DRP on challenging tasks featuring cluttered scenes, dynamic moving obstacles, and goal obstructions. DRP achieves strong generalization, outperforming prior classical and neural methods in success rate across both simulated and real-world settings. Video results and code available at https://deep-reactive-policy.com
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。