Efficient Frontier-Sampling-Mixed Autonomous Exploration Using Environmental Complexity
Liang Lu, Ming Xiang, DONGYANG TANG, Zefeng Yan, Hao Wang, Bin Han
AI summary
Problem
UAVs exploring complex unknown environments suffer from inefficient paths, redundant scans, and high computational costs due to unevenly distributed occlusions. Existing hybrid methods struggle to balance real-time performance with global exploration completeness.
Approach
The method introduces an environmental complexity-aware hybrid framework that combines fast limited-field-of-view frontier detection, adaptive viewpoint sampling that switches modes based on scene complexity, and a hierarchical topological graph planner for time-optimal trajectory generation.
Key results
- Fast frontier detection using differential bounding boxes and unique ID management
- Adaptive sampling strategy switching between uniform and sparse modes based on complexity
- Relaxed obstacle-free sphere constraints for accelerated visibility evaluation
- Hierarchical topological graph planner for globally optimal and locally refined trajectories
Why it matters
Enables UAVs to efficiently and robustly map complex, obstacle-dense environments, directly benefiting search and rescue, infrastructure inspection, and autonomous 3D reconstruction.
Abstract
When exploring complex unknown environments, unmanned aerial vehicles (UAVs) often experience reduced efficiency and robustness due to unevenly distributed occlusions. This paper proposes an efficient hybrid autonomous exploration algorithm that adapts to environmental complexity, enabling effective frontier detection and viewpoint sampling to minimize overall exploration time. We introduce a frontier detection method based on a limited field of view (FOV), along with a unique ID-based frontier management mechanism, which ensures detection completeness while significantly reducing computational and memory overhead. Furthermore, an adap- tive sampling strategy incorporating environmental complexity is introduced. By adaptively switching sampling modes and relaxing obstacle-free sphere generation constraints, the method improves both sampling efficiency and visibility evaluation performance. For path planning, a hierarchical planner based on a topological graph is constructed. It jointly optimizes global coverage paths and local frontier information to generate smooth and time-optimal trajectories. Both simulation and real- world experiments validate the advantages of the proposed approach in terms of exploration efficiency, computational overhead, and coverage rate.