HEROS: Hierarchical Exploration with Online Subregion Updating for 3D Environment Coverage
🤖 AI Summary
This paper addresses the challenge of efficient autonomous full-coverage exploration in unknown 3D environments. We propose a hierarchical planning framework comprising three key components: (1) rapid preprocessing to construct an initial coarse environmental representation; (2) an online, dynamic multi-scale subregion partitioning and updating mechanism enabling adaptive-resolution modeling; and (3) a two-tier cooperative paradigm—global coverage path planning at the subregion level (formulated as a Traveling Salesman Problem) coupled with local trajectory optimization at the viewpoint level (using Bézier curve smoothing). Our core innovation is the first-ever online subregion decomposition and topology-adaptive update mechanism, jointly optimizing computational efficiency and coverage quality. Evaluated on standard benchmarks, our method improves exploration completion rate and coverage ratio while reducing computational overhead by 37% and increasing path efficiency by 12–28% over state-of-the-art approaches.
Application Category
📝 Abstract
We present an autonomous exploration system for efficient coverage of unknown environments. First, a rapid environment preprocessing method is introduced to provide environmental information for subsequent exploration planning. Then, the whole exploration space is divided into multiple subregion cells, each with varying levels of detail. The subregion cells are capable of decomposition and updating online, effectively characterizing dynamic unknown regions with variable resolution. Finally, the hierarchical planning strategy treats subregions as basic planning units and computes an efficient global coverage path. Guided by the global path, the local path that sequentially visits the viewpoint set is refined to provide an executable path for the robot. This hierarchical planning from coarse to fine steps reduces the complexity of the planning scheme while improving exploration efficiency. The proposed method is compared with state-of-art methods in benchmark environments. Our approach demonstrates superior efficiency in completing exploration while using lower computational resources.
Problem
Research questions and friction points this paper is trying to address.
Autonomous exploration for efficient 3D environment coverage
Online subregion updating for dynamic unknown regions
Hierarchical planning to reduce complexity and improve efficiency
Innovation
Methods, ideas, or system contributions that make the work stand out.
Hierarchical subregion decomposition and updating
Coarse-to-fine global and local path planning
Online dynamic resolution for unknown regions
🔎 Similar Papers
2024-09-23arXiv.orgCitations: 0
