SAMP: Spatial Anchor-based Motion Policy for Collision-Aware Robotic Manipulators

2025-09-14

AI Summary

Existing neural motion planning approaches struggle to jointly model robotic arm geometry and environmental structure, leading to incomplete collision detection and degraded obstacle avoidance performance in complex scenes. To address this, we propose a spatial-anchor-based neural motion policy: for the first time, we introduce a signed distance field (SDF) anchor mechanism on a shared 3D mesh to unify geometric encoding of both robot body and environment. An SDF network precisely represents the manipulator’s morphology, while spatial anchors fuse environmental information; combined with efficient feature alignment and neural policy learning, the framework generates safe, smooth trajectories. Extensive simulation and real-world experiments demonstrate that our method achieves an 11% improvement in task success rate and a 7% reduction in collision rate, significantly outperforming state-of-the-art approaches.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Natural Language Processing: Safety and Robustness

Application Category

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

Abstract

Neural-based motion planning methods have achieved remarkable progress for robotic manipulators, yet a fundamental challenge lies in simultaneously accounting for both the robot's physical shape and the surrounding environment when generating safe and feasible motions. Moreover, existing approaches often rely on simplified robot models or focus primarily on obstacle representation, which can lead to incomplete collision detection and degraded performance in cluttered scenes. To address these limitations, we propose spatial anchor-based motion policy (SAMP), a unified framework that simultaneously encodes the environment and the manipulator using signed distance field (SDF) anchored on a shared spatial grid. SAMP incorporates a dedicated robot SDF network that captures the manipulator's precise geometry, enabling collision-aware reasoning beyond coarse link approximations. These representations are fused on spatial anchors and used to train a neural motion policy that generates smooth, collision-free trajectories in the proposed efficient feature alignment strategy. Experiments conducted in both simulated and real-world environments consistently show that SAMP outperforms existing methods, delivering an 11% increase in success rate and a 7% reduction in collision rate. These results highlight the benefits of jointly modelling robot and environment geometry, demonstrating its practical value in challenging real-world environments.

Problem

• Simultaneously accounts for robot shape and environment for safe motions
• Addresses incomplete collision detection in cluttered robotic scenes
• Overcomes reliance on simplified robot models and obstacle representations

Innovation

• Spatial anchor-based motion policy framework
• Signed distance field encoding robot geometry
• Neural motion policy generating collision-free trajectories