Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

OTO Planner: An Efficient Only Travelling Once Exploration Planner for Complex and Unknown Environments

Bo Zhou, Chuanzhao Lu, Yan Pan, Fu Chen

TL;DR

This letter proposes an efficient exploration planner that reduces repeated paths in complex environments, hence it is called "Only Travelling Once Planner", which includes fast frontier updating, viewpoint evaluation and viewpoint refinement.

Abstract

Autonomous exploration in complex and cluttered environments is essential for various applications. However, there are many challenges due to the lack of global heuristic information. Existing exploration methods suffer from the repeated paths and considerable computational resource requirement in large-scale environments. To address the above issues, this letter proposes an efficient exploration planner that reduces repeated paths in complex environments, hence it is called "Only Travelling Once Planner". OTO Planner includes fast frontier updating, viewpoint evaluation and viewpoint refinement. A selective frontier updating mechanism is designed, saving a large amount of computational resources. In addition, a novel viewpoint evaluation system is devised to reduce the repeated paths utilizing the enclosed sub-region detection. Besides, a viewpoint refinement approach is raised to concentrate the redundant viewpoints, leading to smoother paths. We conduct extensive simulation and real-world experiments to validate the proposed method. Compared to the state-of-the-art approach, the proposed method reduces the exploration time and movement distance by 10%-20% and improves the speed of frontier detection by 6-9 times.

OTO Planner: An Efficient Only Travelling Once Exploration Planner for Complex and Unknown Environments

TL;DR

This letter proposes an efficient exploration planner that reduces repeated paths in complex environments, hence it is called "Only Travelling Once Planner", which includes fast frontier updating, viewpoint evaluation and viewpoint refinement.

Abstract

Autonomous exploration in complex and cluttered environments is essential for various applications. However, there are many challenges due to the lack of global heuristic information. Existing exploration methods suffer from the repeated paths and considerable computational resource requirement in large-scale environments. To address the above issues, this letter proposes an efficient exploration planner that reduces repeated paths in complex environments, hence it is called "Only Travelling Once Planner". OTO Planner includes fast frontier updating, viewpoint evaluation and viewpoint refinement. A selective frontier updating mechanism is designed, saving a large amount of computational resources. In addition, a novel viewpoint evaluation system is devised to reduce the repeated paths utilizing the enclosed sub-region detection. Besides, a viewpoint refinement approach is raised to concentrate the redundant viewpoints, leading to smoother paths. We conduct extensive simulation and real-world experiments to validate the proposed method. Compared to the state-of-the-art approach, the proposed method reduces the exploration time and movement distance by 10%-20% and improves the speed of frontier detection by 6-9 times.
Paper Structure (15 sections, 6 equations, 10 figures, 2 tables, 2 algorithms)

This paper contains 15 sections, 6 equations, 10 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Sampling-based Methods
  4. Frontier-based Methods
  5. Methodology
  6. Selective Frontier Updating
  7. Viewpoint Evaluation
  8. Viewpoint Refinement
  9. Experiments and Results
  10. Benchmark and Analysis
  11. Scene 1: Complex Maze Scenario
  12. Scene 2: Cluttered and Large-scale Indoor Scenario
  13. Scene 3: Multi-level garage Scenario
  14. Real-World Experiments
  15. Conclusion

Figures (10)

  • Figure 2: Complex scenes that may cause repeated paths. The upper figures are diagrams and the lower figures are actual scenes in simulation. Gray grids: unknown spaces. Red grids: frontiers. Orange path: exploration path. Greedy strategies are prone to visit frontiers with maximum information gain, like green path (dashed line), which drive the robot back to visit the overlooked small regions. The red box shows the enclosed sub-region. If the robot is located near the enclosed sub-region, it prefers to explore unknown spaces in it, like blue path (solid line), which reduces repeated paths significantly.
  • Figure 3: An overview of proposed exploration approach. Our contributions are shown in frontier detection moudle and viewpoint selection moudle.
  • Figure 4: Selective frontier updating. As robot moves from time $T_i$ to $T_{i+1}$, some unknown grids are newly perceived, like orange grids in the figure. All frontiers at time $T_i$ are checked whether they still meet the features of frontiers. In the meantime, fresh frontiers are detected in the updated (orange) grids.
  • Figure 5: Enclosed sub-region detection. Upper: the whole scene for the robot to explore and a portion of the scene that is centered and extracted around the robot. Lower: the process of detecting enclosed sub-region. Point clouds of different colors represent regions within distinct neighborhoods. The green arrow represents the normal vector of a point cloud neighborhood.
  • Figure 6: Simulation results. (a), (b) and (c) correspond to Scene 1, Scene 2 and Scene 3 respectively. (d) is the result of algorithm runtime comparison of proposed method and TARE in Scene 2.
  • ...and 5 more figures