.png){kind=icon}
返回
Chaotic sequence-driven path planning for autonomous robot terrain coverage
.png){kind=icon}
PRE
AI
DOI：10.1016/j.compeleceng.2024.110032.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Path planning for terrain coverage in autonomous robotics faces challenges due to traditional methods' limitations and the high computational demands of heuristic and machine learning approaches. This study investigates the use of simple 1D chaotic maps in coverage path planning (CPP) to enhance efficiency, unpredictability, and security. Two approaches were evaluated: Theoretical Testing and Graphing (TTG) and Robot Simulation Testing (RST). TTG involved testing in gridded mazes with dynamic target updates based on the furthest distance from the current position, using chaotic sequences. RST utilized real-world coordinates and robot dimensions in MATLAB simulations. Both A* and Probabilistic Roadmap (PRM) algorithms were implemented, and trajectory simulations employed a Pure Pursuit controller. Key metrics, including coverage percentage, path distance, and subregion coverage, were analyzed. Results show that TTG-3 and RST-3 achieved the shortest paths and lowest computational time, demonstrating variability that benefits chaotic planning. This research highlights the potential of chaotic sequences in CPP, suggesting possibilities for refinement and integration with existing methods to enhance their real-world applicability.
Keyword:
Path planning
Chaotic sequences
Autonomous robots
Terrain coverage
A*
Probabilistic Roadmap
期刊
C
IF:
4.9
论文数:
6.7K
被引数:
1.3W
机构
引用论文
.png){kind=icon}
Nano-sized LaMnO3 powders prepared by spray pyrolysis from spray solution containing citric acid从含柠檬酸的喷雾溶液中通过喷雾热解制备纳米LaMnO3粉末
OAAI
OAAI分享收藏Token Economy to Improve Concentration among Students with Learning Disabilities in Primary School
OAAI
OAAI分享收藏分享收藏
查看更多内容