Autonomous Search of Real-Life Environments Combining Dynamical System-Based Path Planning and Unsupervised Learning
In recent years, advances have been made in chaotic coverage path planning (CCPP) for autonomous search and traversal of spaces with limited environmental cues. However, the field remains unfit for practical application due to limited experimental work addressing three critical challenges: 1) an obs...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11027064/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | In recent years, advances have been made in chaotic coverage path planning (CCPP) for autonomous search and traversal of spaces with limited environmental cues. However, the field remains unfit for practical application due to limited experimental work addressing three critical challenges: 1) an obstacle avoidance technique that reduces halts or disruptions in continuous chaotic trajectories, 2) a means to spread chaotic trajectories across the environment (especially crucial for large and/or complex-shaped environments) that need to be covered, and 3) a real-time coverage calculation technique that is accurate and independent of cell size. This study develops a novel framework implemented in ROS to address these challenges. We compare our Chaotic Coverage Path Planning (CCPP) approach against Boustrophedon Coverage Path Planning (BCPP) in both simulated and real-world environments. Across all three simulated environments of increasing complexity, BCPP consistently achieved shorter coverage times than our CCPP algorithm. However, an interesting pattern emerged when analyzing the relative performance degradation. When comparing coverage times across environments, CCPP showed less performance degradation than BCPP. Specifically, when normalizing coverage times against the simplest environment, BCPP’s performance degraded by factors of 3.31 and 3.59 for the medium and most complex environments, respectively, while CCPP showed lower degradation factors of 2.57 and 2.35. This suggests that CCPP may be more adaptive to increasing environmental size and complexity, despite having longer absolute coverage times. The source code is available at: <uri>https://gitlab.com/dsim-lab/paper-codes/Autonomous_search_of_real-life_environments</uri> |
|---|---|
| ISSN: | 2169-3536 |