Enhanced obstacle avoidance for autonomous underwater vehicles via path integral control based on guiding vector field
- Jintao Zhao 1, Tao Liu 2, Junhao Huang 1
- Jintao Zhao 1, Tao Liu 2, Junhao Huang 1
- 1School of Ocean Engineering and Technology, Sun Yat-sen University & Southern Marine Science and Engineering Guangdong Laboratory, Zhuhai 519000, China.
- 2School of Ocean Engineering and Technology, Sun Yat-sen University & Southern Marine Science and Engineering Guangdong Laboratory, Zhuhai 519000, China; Zhuhai Research Center, Hanjiang National Laboratory, Zhuhai 519000, China; Guangdong Provincial Key Laboratory of Information Technology for Deep Water Acoustics, Zhuhai 519000, China.
- 0School of Ocean Engineering and Technology, Sun Yat-sen University & Southern Marine Science and Engineering Guangdong Laboratory, Zhuhai 519000, China.
Related Experiment Videos
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.This study introduces a novel navigation method for Autonomous Underwater Vehicles (AUVs) by integrating Guiding Vector Fields (GVF) and Model Predictive Path Integral (MPPI) control, significantly enhancing obstacle avoidance and path tracking in complex underwater environments.
Area Of Science
- Robotics
- Marine Engineering
- Control Systems
Background
- Autonomous Underwater Vehicles (AUVs) require advanced navigation for complex tasks.
- Challenges include precise tracking, real-time navigation, and obstacle avoidance in dynamic underwater environments.
Purpose Of The Study
- To develop and validate a new navigation technique for AUVs.
- To improve the precision and efficiency of AUV operations in challenging underwater settings.
Main Methods
- Integration of Guiding Vector Field (GVF) concepts for global path planning and obstacle avoidance.
- Application of Model Predictive Path Integral (MPPI) control for precise trajectory tracking and dynamic constraint management.
- Utilizing AUV relative positioning and environmental data for GVF generation and MPPI optimization.
Main Results
- Achieved a 64% reduction in path tracking error.
- Successfully navigated complex scenarios with non-convex obstacles while maintaining safe distances.
- Demonstrated robust performance under disturbance conditions with a minimal tracking error of 0.017 µm.
Conclusions
- The combined GVF and MPPI approach effectively integrates global planning with local optimization for AUV navigation.
- This method enhances AUV efficiency, safety, and reliability in intricate underwater environments.
- The research advances AUV capabilities for applications such as marine surveying and underwater search and rescue.
Related Experiment Videos
Contact us if these videos are not relevant.
Contact us if these videos are not relevant.