ParaMaP: Parallel Mapping and Collision-free Motion Planning for Reactive Robot Manipulation

2025-12-27

AI Summary

Addressing the challenge of real-time, collision-free motion planning for robotic manipulators in unknown environments, this paper proposes a parallel-coupled mapping-and-planning framework enabling perception-driven, millisecond-scale online replanning. Our key contributions are: (1) the first online mask distance field (MDF) update mechanism for robots, effectively suppressing self-collision false positives; (2) an SE(3)-consistent pose tracking metric that integrates Euclidean distance transform (EDT)-based implicit geometric modeling with batch-parallel sampling model predictive control (SMPC); and (3) a fully GPU-accelerated stack supporting dense distance field construction and high-frequency trajectory optimization. Evaluated in simulation and on a real 7-DoF manipulator, the method significantly improves robustness in dynamic obstacle avoidance and achieves superior convergence accuracy to target poses.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Computer Vision: Motion & Tracking

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Real-time and collision-free motion planning remains challenging for robotic manipulation in unknown environments due to continuous perception updates and the need for frequent online replanning. To address these challenges, we propose a parallel mapping and motion planning framework that tightly integrates Euclidean Distance Transform (EDT)-based environment representation with a sampling-based model predictive control (SMPC) planner. On the mapping side, a dense distance-field-based representation is constructed using a GPU-based EDT and augmented with a robot-masked update mechanism to prevent false self-collision detections during online perception. On the planning side, motion generation is formulated as a stochastic optimization problem with a unified objective function and efficiently solved by evaluating large batches of candidate rollouts in parallel within a SMPC framework, in which a geometrically consistent pose tracking metric defined on SE(3) is incorporated to ensure fast and accurate convergence to the target pose. The entire mapping and planning pipeline is implemented on the GPU to support high-frequency replanning. The effectiveness of the proposed framework is validated through extensive simulations and real-world experiments on a 7-DoF robotic manipulator. More details are available at: https://zxw610.github.io/ParaMaP.

Problem

• Enables real-time collision-free motion planning in unknown environments
• Integrates distance-field mapping with parallel sampling-based predictive control
• Prevents false self-collision detection during continuous perception updates

Innovation

• GPU-based parallel mapping and planning for real-time replanning
• EDT-based environment representation with robot-masked updates to avoid false collisions
• SMPC with SE(3) pose tracking for efficient stochastic optimization in motion generation