arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.16462cs.RO
收藏

动态环境中基于粒子的感知的反应式运动生成

Reactive Motion Generation With Particle-Based Perception in Dynamic Environments

State Key Laboratory of Digital Medical Engineering(数字医疗工程国家重点实验室);Jiangsu Key Lab of Robot Sensing and Control(江苏省机器人感知与控制重点实验室);School of Instrument Science and Engineering(仪器科学与工程学院);Southeast University(东南大学)

Xiyuan Zhao, Huijun Li, Lifeng Zhu, Zhikai Wei, Xianyi Zhu, Aiguo Song

AI总结:

本文提出了一种基于模型的动态环境反应式运动生成方法,通过张量化的粒子权重更新和障碍物意识的MPPI规划,提升安全性和反应性。

摘要:

在动态和无结构的场景中,反应式运动生成通常受到本质上静态的感知和系统动态的限制。可靠地建模动态障碍物并在感知和控制不确定性下优化无碰撞轨迹具有挑战性。本文从基于模型的角度揭示了反应式规划与机械臂动态映射之间的紧密联系。为了实现高效的基于粒子的感知并具有表达性动态特性,我们提出了一种张量化的粒子权重更新方案,该方案明确维护障碍物的速度和协方差。在此动态表示基础上,我们提出了一种具有障碍物意识的基于MPPI的规划公式,该公式联合传播机器人-障碍物动态,使在不确定性下能够预测和评估未来的系统运动。模型预测方法被证明能显著提高在动态环境中的安全性和反应性。通过在模拟和噪声现实环境中应用我们的完整框架,我们证明了对机器人-障碍物动态的显式建模在避免多个静态和动态障碍物方面始终优于最先进的基于MPPI的感知-规划基线。

英文摘要:

Reactive motion generation in dynamic and unstructured scenarios is typically subject to essentially static perception and system dynamics. Reliably modeling dynamic obstacles and optimizing collision-free trajectories under perceptive and control uncertainty are challenging. This article focuses on revealing tight connection between reactive planning and dynamic mapping for manipulators from a model-based perspective. To enable efficient particle-based perception with expressively dynamic property, we present a tensorized particle weight update scheme that explicitly maintains obstacle velocities and covariance meanwhile. Building upon this dynamic representation, we propose an obstacle-aware MPPI-based planning formulation that jointly propagates robot-obstacle dynamics, allowing future system motion to be predicted and evaluated under uncertainty. The model predictive method is shown to significantly improve safety and reactivity with dynamic surroundings. By applying our complete framework in simulated and noisy real-world environments, we demonstrate that explicit modeling of robot-obstacle dynamics consistently enhances performance over state-of-the-art MPPI-based perception-planning baselines avoiding multiple static and dynamic obstacles.

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。

↑