COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy

2025-09-18

AI Summary

Manipulation in confined, cluttered environments is challenging due to partial observability and high-dimensional configuration spaces. Method: This paper proposes a multi-stage framework that tightly couples active perception with manipulation planning, comprising three core modules: near-field local mapping, multi-objective viewpoint optimization, and constraint-aware manipulation planning. Crucially, it introduces a joint perception-manipulation optimization strategy that simultaneously balances information gain and manipulability during viewpoint selection. The approach integrates sampling-based planners, multi-objective utility functions, locally constructed collision maps, and constrained optimization techniques. Contribution/Results: We further introduce the first benchmark suite specifically designed for manipulation in confined spaces. Simulation results show a 24.25% improvement in task success rate over methods optimizing information gain alone; real-world experiments validate the framework’s effectiveness and robustness in narrow, constrained scenarios.

Technology Category

• Intelligent Robots: Manipulation
• Constraint Satisfaction and Optimization: Constraint Learning and Acquisition
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Manipulation in confined and cluttered environments remains a significant challenge due to partial observability and complex configuration spaces. Effective manipulation in such environments requires an intelligent exploration strategy to safely understand the scene and search the target. In this paper, we propose COMPASS, a multi-stage exploration and manipulation framework featuring a manipulation-aware sampling-based planner. First, we reduce collision risks with a near-field awareness scan to build a local collision map. Additionally, we employ a multi-objective utility function to find viewpoints that are both informative and conducive to subsequent manipulation. Moreover, we perform a constrained manipulation optimization strategy to generate manipulation poses that respect obstacle constraints. To systematically evaluate method's performance under these difficulties, we propose a benchmark of confined-space exploration and manipulation containing four level challenging scenarios. Compared to exploration methods designed for other robots and only considering information gain, our framework increases manipulation success rate by 24.25% in simulations. Real-world experiments demonstrate our method's capability for active sensing and manipulation in confined environments.

Problem

• Planning manipulation in confined spaces with partial observability
• Developing active sensing strategy for scene understanding
• Generating manipulation poses under obstacle constraints

Innovation

• Manipulation-aware sampling-based planner
• Multi-objective utility function viewpoints
• Constrained manipulation optimization strategy