Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation
This study presents an approach to autonomous navigation for wheeled robots, combining radar-based dynamic obstacle detection with a BiGRU-based deep reinforcement learning (DRL) framework. Using filtering and tracking algorithms, the proposed system leverages radar sensors to cluster object points...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/1/295 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841549398699409408 |
|---|---|
| author | Nabih Pico Estrella Montero Maykoll Vanegas Jose Miguel Erazo Ayon Eugene Auh Jiyou Shin Myeongyun Doh Sang-Hyeon Park Hyungpil Moon |
| author_facet | Nabih Pico Estrella Montero Maykoll Vanegas Jose Miguel Erazo Ayon Eugene Auh Jiyou Shin Myeongyun Doh Sang-Hyeon Park Hyungpil Moon |
| author_sort | Nabih Pico |
| collection | DOAJ |
| description | This study presents an approach to autonomous navigation for wheeled robots, combining radar-based dynamic obstacle detection with a BiGRU-based deep reinforcement learning (DRL) framework. Using filtering and tracking algorithms, the proposed system leverages radar sensors to cluster object points and track dynamic obstacles, enhancing precision by reducing noise and fluctuations. A BiGRU-enabled DRL model is introduced, allowing the robot to process sequential environmental data and make informed decisions in dynamic and unpredictable environments, achieving collision-free paths and reaching the goal. Simulation and experimental results validate the proposed method’s efficiency and adaptability, highlighting its potential for real-world applications in dynamic scenarios. |
| format | Article |
| id | doaj-art-205c7ef93a7b433e928bdae11f2cad7f |
| institution | Kabale University |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-205c7ef93a7b433e928bdae11f2cad7f2025-01-10T13:15:04ZengMDPI AGApplied Sciences2076-34172024-12-0115129510.3390/app15010295Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous NavigationNabih Pico0Estrella Montero1Maykoll Vanegas2Jose Miguel Erazo Ayon3Eugene Auh4Jiyou Shin5Myeongyun Doh6Sang-Hyeon Park7Hyungpil Moon8Department of Mechanical Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Republic of KoreaDepartment of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si 16419, Republic of KoreaFacultad de Ingeniería Mecánica y Ciencias de la Producción, Escuela Superior Politécnica del Litoral (ESPOL), Campus Gustavo Galindo, Guayaquil P.O. Box 09-01-5863, EcuadorFaculty of Engineering, Catholic University of Santiago de Guayaquil, Guayaquil 090603, EcuadorDepartment of Mechanical Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Republic of KoreaDepartment of Mechanical Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Republic of KoreaDepartment of Mechanical Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Republic of KoreaDepartment of Mechanical Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Republic of KoreaDepartment of Mechanical Engineering, Sungkyunkwan University, 2066 Seobu-ro, Jangan-gu, Suwon-si 16419, Republic of KoreaThis study presents an approach to autonomous navigation for wheeled robots, combining radar-based dynamic obstacle detection with a BiGRU-based deep reinforcement learning (DRL) framework. Using filtering and tracking algorithms, the proposed system leverages radar sensors to cluster object points and track dynamic obstacles, enhancing precision by reducing noise and fluctuations. A BiGRU-enabled DRL model is introduced, allowing the robot to process sequential environmental data and make informed decisions in dynamic and unpredictable environments, achieving collision-free paths and reaching the goal. Simulation and experimental results validate the proposed method’s efficiency and adaptability, highlighting its potential for real-world applications in dynamic scenarios.https://www.mdpi.com/2076-3417/15/1/295autonomous navigationradar sensorsdynamic obstaclesdeep reinforcement learning |
| spellingShingle | Nabih Pico Estrella Montero Maykoll Vanegas Jose Miguel Erazo Ayon Eugene Auh Jiyou Shin Myeongyun Doh Sang-Hyeon Park Hyungpil Moon Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation Applied Sciences autonomous navigation radar sensors dynamic obstacles deep reinforcement learning |
| title | Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation |
| title_full | Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation |
| title_fullStr | Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation |
| title_full_unstemmed | Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation |
| title_short | Integrating Radar-Based Obstacle Detection with Deep Reinforcement Learning for Robust Autonomous Navigation |
| title_sort | integrating radar based obstacle detection with deep reinforcement learning for robust autonomous navigation |
| topic | autonomous navigation radar sensors dynamic obstacles deep reinforcement learning |
| url | https://www.mdpi.com/2076-3417/15/1/295 |
| work_keys_str_mv | AT nabihpico integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT estrellamontero integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT maykollvanegas integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT josemiguelerazoayon integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT eugeneauh integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT jiyoushin integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT myeongyundoh integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT sanghyeonpark integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation AT hyungpilmoon integratingradarbasedobstacledetectionwithdeepreinforcementlearningforrobustautonomousnavigation |