The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework
Over the years, deep reinforcement learning (DRL) has shown great potential in mapless autonomous robot navigation and path planning. These DRL methods rely on robots equipped with different light detection and range (LiDAR) sensors with a wide field of view (FOV) configuration to perceive their env...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/24/9732 |
| _version_ | 1797379401447374848 |
|---|---|
| author | Kabirat Bolanle Olayemi Mien Van Sean McLoone Stephen McIlvanna Yuzhu Sun Jack Close Nhat Minh Nguyen |
| author_facet | Kabirat Bolanle Olayemi Mien Van Sean McLoone Stephen McIlvanna Yuzhu Sun Jack Close Nhat Minh Nguyen |
| author_sort | Kabirat Bolanle Olayemi |
| collection | DOAJ |
| description | Over the years, deep reinforcement learning (DRL) has shown great potential in mapless autonomous robot navigation and path planning. These DRL methods rely on robots equipped with different light detection and range (LiDAR) sensors with a wide field of view (FOV) configuration to perceive their environment. These types of LiDAR sensors are expensive and are not suitable for small-scale applications. In this paper, we address the performance effect of the LiDAR sensor configuration in DRL models. Our focus is on avoiding static obstacles ahead. We propose a novel approach that determines an initial FOV by calculating an angle of view using the sensor’s width and the minimum safe distance required between the robot and the obstacle. The beams returned within the FOV, the robot’s velocities, the robot’s orientation to the goal point, and the distance to the goal point are used as the input state to generate new velocity values as the output action of the DRL. The cost function of collision avoidance and path planning is defined as the reward of the DRL model. To verify the performance of the proposed method, we adjusted the proposed FOV by ±10° giving a narrower and wider FOV. These new FOVs are trained to obtain collision avoidance and path planning DRL models to validate the proposed method. Our experimental setup shows that the LiDAR configuration with the computed angle of view as its FOV performs best with a success rate of 98% and a lower time complexity of 0.25 m/s. Additionally, using a Husky Robot, we demonstrate the model’s good performance and applicability in the real world. |
| first_indexed | 2024-03-08T20:22:42Z |
| format | Article |
| id | doaj.art-0b24b30f6eb44136b6eddf2bb37068a9 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T20:22:42Z |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-0b24b30f6eb44136b6eddf2bb37068a92023-12-22T14:40:26ZengMDPI AGSensors1424-82202023-12-012324973210.3390/s23249732The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning FrameworkKabirat Bolanle Olayemi0Mien Van1Sean McLoone2Stephen McIlvanna3Yuzhu Sun4Jack Close5Nhat Minh Nguyen6School of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT9 5AG, UKSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT9 5AG, UKSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT9 5AG, UKSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT9 5AG, UKSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT9 5AG, UKSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT9 5AG, UKSchool of Electronics, Electrical Engineering and Computer Science, Queen’s University Belfast, Belfast BT9 5AG, UKOver the years, deep reinforcement learning (DRL) has shown great potential in mapless autonomous robot navigation and path planning. These DRL methods rely on robots equipped with different light detection and range (LiDAR) sensors with a wide field of view (FOV) configuration to perceive their environment. These types of LiDAR sensors are expensive and are not suitable for small-scale applications. In this paper, we address the performance effect of the LiDAR sensor configuration in DRL models. Our focus is on avoiding static obstacles ahead. We propose a novel approach that determines an initial FOV by calculating an angle of view using the sensor’s width and the minimum safe distance required between the robot and the obstacle. The beams returned within the FOV, the robot’s velocities, the robot’s orientation to the goal point, and the distance to the goal point are used as the input state to generate new velocity values as the output action of the DRL. The cost function of collision avoidance and path planning is defined as the reward of the DRL model. To verify the performance of the proposed method, we adjusted the proposed FOV by ±10° giving a narrower and wider FOV. These new FOVs are trained to obtain collision avoidance and path planning DRL models to validate the proposed method. Our experimental setup shows that the LiDAR configuration with the computed angle of view as its FOV performs best with a success rate of 98% and a lower time complexity of 0.25 m/s. Additionally, using a Husky Robot, we demonstrate the model’s good performance and applicability in the real world.https://www.mdpi.com/1424-8220/23/24/9732reinforcement learningdeep-reinforcement learningcollision avoidancehuskygazeboLiDAR |
| spellingShingle | Kabirat Bolanle Olayemi Mien Van Sean McLoone Stephen McIlvanna Yuzhu Sun Jack Close Nhat Minh Nguyen The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework Sensors reinforcement learning deep-reinforcement learning collision avoidance husky gazebo LiDAR |
| title | The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework |
| title_full | The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework |
| title_fullStr | The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework |
| title_full_unstemmed | The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework |
| title_short | The Impact of LiDAR Configuration on Goal-Based Navigation within a Deep Reinforcement Learning Framework |
| title_sort | impact of lidar configuration on goal based navigation within a deep reinforcement learning framework |
| topic | reinforcement learning deep-reinforcement learning collision avoidance husky gazebo LiDAR |
| url | https://www.mdpi.com/1424-8220/23/24/9732 |
| work_keys_str_mv | AT kabiratbolanleolayemi theimpactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT mienvan theimpactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT seanmcloone theimpactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT stephenmcilvanna theimpactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT yuzhusun theimpactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT jackclose theimpactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT nhatminhnguyen theimpactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT kabiratbolanleolayemi impactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT mienvan impactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT seanmcloone impactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT stephenmcilvanna impactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT yuzhusun impactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT jackclose impactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework AT nhatminhnguyen impactoflidarconfigurationongoalbasednavigationwithinadeepreinforcementlearningframework |