A behavior-based mobile robot navigation method with deep reinforcement learning
Deep reinforcement learning-based mobile robot navigation has attracted some recent interest. In the single-agent case, a robot can learn to navigate autonomously without a map of the environment. In the multi-agent case, robots can learn to avoid collisions with each other. In this work, we propose...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2022
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/159859 |
| _version_ | 1811697002633756672 |
|---|---|
| author | Li, Juncheng Ran, Maopeng Wang, Han Xie, Lihua |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Li, Juncheng Ran, Maopeng Wang, Han Xie, Lihua |
| author_sort | Li, Juncheng |
| collection | NTU |
| description | Deep reinforcement learning-based mobile robot navigation has attracted some recent interest. In the single-agent case, a robot can learn to navigate autonomously without a map of the environment. In the multi-agent case, robots can learn to avoid collisions with each other. In this work, we propose a behavior-based mobile robot navigation method which directly maps the raw sensor data and goal information to the control command. The learned navigation policy can be applied in both single-agent and multi-agent scenarios. Two basic navigation behaviors are considered in our method, which are goal reaching and collision avoidance. The two behaviors are fused based on the risklevel estimation of the current state. The navigation task is decomposed using the behavior-based framework, which is capable of reducing the complexity of the learning process. The simulations and real-world experiments demonstrate that the proposed method can enable the collision-free autonomous navigation of multiple mobile robots in unknown environments. |
| first_indexed | 2024-10-01T07:48:20Z |
| format | Journal Article |
| id | ntu-10356/159859 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T07:48:20Z |
| publishDate | 2022 |
| record_format | dspace |
| spelling | ntu-10356/1598592022-07-04T08:57:32Z A behavior-based mobile robot navigation method with deep reinforcement learning Li, Juncheng Ran, Maopeng Wang, Han Xie, Lihua School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Autonomous Navigation Mobile Robots Deep reinforcement learning-based mobile robot navigation has attracted some recent interest. In the single-agent case, a robot can learn to navigate autonomously without a map of the environment. In the multi-agent case, robots can learn to avoid collisions with each other. In this work, we propose a behavior-based mobile robot navigation method which directly maps the raw sensor data and goal information to the control command. The learned navigation policy can be applied in both single-agent and multi-agent scenarios. Two basic navigation behaviors are considered in our method, which are goal reaching and collision avoidance. The two behaviors are fused based on the risklevel estimation of the current state. The navigation task is decomposed using the behavior-based framework, which is capable of reducing the complexity of the learning process. The simulations and real-world experiments demonstrate that the proposed method can enable the collision-free autonomous navigation of multiple mobile robots in unknown environments. 2022-07-04T08:57:31Z 2022-07-04T08:57:31Z 2021 Journal Article Li, J., Ran, M., Wang, H. & Xie, L. (2021). A behavior-based mobile robot navigation method with deep reinforcement learning. Unmanned Systems, 9(3), 201-209. https://dx.doi.org/10.1142/S2301385021410041 2301-3850 https://hdl.handle.net/10356/159859 10.1142/S2301385021410041 2-s2.0-85100631250 3 9 201 209 en Unmanned Systems © 2021 World Scientific Publishing Company. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Autonomous Navigation Mobile Robots Li, Juncheng Ran, Maopeng Wang, Han Xie, Lihua A behavior-based mobile robot navigation method with deep reinforcement learning |
| title | A behavior-based mobile robot navigation method with deep reinforcement learning |
| title_full | A behavior-based mobile robot navigation method with deep reinforcement learning |
| title_fullStr | A behavior-based mobile robot navigation method with deep reinforcement learning |
| title_full_unstemmed | A behavior-based mobile robot navigation method with deep reinforcement learning |
| title_short | A behavior-based mobile robot navigation method with deep reinforcement learning |
| title_sort | behavior based mobile robot navigation method with deep reinforcement learning |
| topic | Engineering::Electrical and electronic engineering Autonomous Navigation Mobile Robots |
| url | https://hdl.handle.net/10356/159859 |
| work_keys_str_mv | AT lijuncheng abehaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning AT ranmaopeng abehaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning AT wanghan abehaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning AT xielihua abehaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning AT lijuncheng behaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning AT ranmaopeng behaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning AT wanghan behaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning AT xielihua behaviorbasedmobilerobotnavigationmethodwithdeepreinforcementlearning |