Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle
This paper investigates a novel reinforcement learning (RL)-based quadratic programming (QP) method for the safety-critical trajectory tracking control of autonomous underwater vehicles (AUVs). The proposed approach addresses the substantial challenge posed by model uncertainty, which may hinder the...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Drones |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-446X/9/1/65 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588607890653184 |
|---|---|
| author | Tianli Li Jiaming Tao Yu Hu Shiyu Chen Yue Wei Bo Zhang |
| author_facet | Tianli Li Jiaming Tao Yu Hu Shiyu Chen Yue Wei Bo Zhang |
| author_sort | Tianli Li |
| collection | DOAJ |
| description | This paper investigates a novel reinforcement learning (RL)-based quadratic programming (QP) method for the safety-critical trajectory tracking control of autonomous underwater vehicles (AUVs). The proposed approach addresses the substantial challenge posed by model uncertainty, which may hinder the safety and performance of AUVs operating in complex underwater environments. The RL framework can learn the inherent model uncertainties that affect the constraints in Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). These learned uncertainties are subsequently integrated for formulating a novel RL-CBF-CLF Quadratic Programming (RL-CBF-CLF-QP) controller. Corresponding simulations are demonstrated under diverse trajectory tracking scenarios with high levels of model uncertainties. The simulation results show that the proposed RL-CBF-CLF-QP controller can significantly improve the safety and accuracy of the AUV’s tracking performance. |
| format | Article |
| id | doaj-art-1baa6b215f434c5699cc894593b6d2d0 |
| institution | Kabale University |
| issn | 2504-446X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Drones |
| spelling | doaj-art-1baa6b215f434c5699cc894593b6d2d02025-01-24T13:29:50ZengMDPI AGDrones2504-446X2025-01-01916510.3390/drones9010065Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater VehicleTianli Li0Jiaming Tao1Yu Hu2Shiyu Chen3Yue Wei4Bo Zhang5The College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaThe College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518107, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518107, ChinaGuangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen 518107, ChinaThe College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, ChinaThis paper investigates a novel reinforcement learning (RL)-based quadratic programming (QP) method for the safety-critical trajectory tracking control of autonomous underwater vehicles (AUVs). The proposed approach addresses the substantial challenge posed by model uncertainty, which may hinder the safety and performance of AUVs operating in complex underwater environments. The RL framework can learn the inherent model uncertainties that affect the constraints in Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). These learned uncertainties are subsequently integrated for formulating a novel RL-CBF-CLF Quadratic Programming (RL-CBF-CLF-QP) controller. Corresponding simulations are demonstrated under diverse trajectory tracking scenarios with high levels of model uncertainties. The simulation results show that the proposed RL-CBF-CLF-QP controller can significantly improve the safety and accuracy of the AUV’s tracking performance.https://www.mdpi.com/2504-446X/9/1/65CBFCLFAUVsafety-critical control |
| spellingShingle | Tianli Li Jiaming Tao Yu Hu Shiyu Chen Yue Wei Bo Zhang Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle Drones CBF CLF AUV safety-critical control |
| title | Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle |
| title_full | Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle |
| title_fullStr | Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle |
| title_full_unstemmed | Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle |
| title_short | Safety-Critical Trajectory Tracking Control with Safety-Enhanced Reinforcement Learning for Autonomous Underwater Vehicle |
| title_sort | safety critical trajectory tracking control with safety enhanced reinforcement learning for autonomous underwater vehicle |
| topic | CBF CLF AUV safety-critical control |
| url | https://www.mdpi.com/2504-446X/9/1/65 |
| work_keys_str_mv | AT tianlili safetycriticaltrajectorytrackingcontrolwithsafetyenhancedreinforcementlearningforautonomousunderwatervehicle AT jiamingtao safetycriticaltrajectorytrackingcontrolwithsafetyenhancedreinforcementlearningforautonomousunderwatervehicle AT yuhu safetycriticaltrajectorytrackingcontrolwithsafetyenhancedreinforcementlearningforautonomousunderwatervehicle AT shiyuchen safetycriticaltrajectorytrackingcontrolwithsafetyenhancedreinforcementlearningforautonomousunderwatervehicle AT yuewei safetycriticaltrajectorytrackingcontrolwithsafetyenhancedreinforcementlearningforautonomousunderwatervehicle AT bozhang safetycriticaltrajectorytrackingcontrolwithsafetyenhancedreinforcementlearningforautonomousunderwatervehicle |