A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robots
IntroductionRedundant robots offer greater flexibility compared to non-redundant ones but are susceptible to increased collision risks when the end-effector approaches the robot's own links. Redundant degrees of freedom (DoFs) present an opportunity for collision avoidance; however, selecting a...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2024-03-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1375309/full |
| _version_ | 1797238655142592512 |
|---|---|
| author | Tinghe Hong Weibing Li Kai Huang |
| author_facet | Tinghe Hong Weibing Li Kai Huang |
| author_sort | Tinghe Hong |
| collection | DOAJ |
| description | IntroductionRedundant robots offer greater flexibility compared to non-redundant ones but are susceptible to increased collision risks when the end-effector approaches the robot's own links. Redundant degrees of freedom (DoFs) present an opportunity for collision avoidance; however, selecting an appropriate inverse kinematics (IK) solution remains challenging due to the infinite possible solutions.MethodsThis study proposes a reinforcement learning (RL) enhanced pseudo-inverse approach to address self-collision avoidance in redundant robots. The RL agent is integrated into the redundancy resolution process of a pseudo-inverse method to determine a suitable IK solution for avoiding self-collisions during task execution. Additionally, an improved replay buffer is implemented to enhance the performance of the RL algorithm.ResultsSimulations and experiments validate the effectiveness of the proposed method in reducing the risk of self-collision in redundant robots.ConclusionThe RL enhanced pseudo-inverse approach presented in this study demonstrates promising results in mitigating self-collision risks in redundant robots, highlighting its potential for enhancing safety and performance in robotic systems. |
| first_indexed | 2024-04-24T17:39:05Z |
| format | Article |
| id | doaj.art-f789a595db414e5c90af00f40fd91ede |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-04-24T17:39:05Z |
| publishDate | 2024-03-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-f789a595db414e5c90af00f40fd91ede2024-03-28T04:26:40ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182024-03-011810.3389/fnbot.2024.13753091375309A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robotsTinghe HongWeibing LiKai HuangIntroductionRedundant robots offer greater flexibility compared to non-redundant ones but are susceptible to increased collision risks when the end-effector approaches the robot's own links. Redundant degrees of freedom (DoFs) present an opportunity for collision avoidance; however, selecting an appropriate inverse kinematics (IK) solution remains challenging due to the infinite possible solutions.MethodsThis study proposes a reinforcement learning (RL) enhanced pseudo-inverse approach to address self-collision avoidance in redundant robots. The RL agent is integrated into the redundancy resolution process of a pseudo-inverse method to determine a suitable IK solution for avoiding self-collisions during task execution. Additionally, an improved replay buffer is implemented to enhance the performance of the RL algorithm.ResultsSimulations and experiments validate the effectiveness of the proposed method in reducing the risk of self-collision in redundant robots.ConclusionThe RL enhanced pseudo-inverse approach presented in this study demonstrates promising results in mitigating self-collision risks in redundant robots, highlighting its potential for enhancing safety and performance in robotic systems.https://www.frontiersin.org/articles/10.3389/fnbot.2024.1375309/fullreinforcement learninginverse kinematicsredundant robotsself-collision avoidancesim to real |
| spellingShingle | Tinghe Hong Weibing Li Kai Huang A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robots Frontiers in Neurorobotics reinforcement learning inverse kinematics redundant robots self-collision avoidance sim to real |
| title | A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robots |
| title_full | A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robots |
| title_fullStr | A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robots |
| title_full_unstemmed | A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robots |
| title_short | A reinforcement learning enhanced pseudo-inverse approach to self-collision avoidance of redundant robots |
| title_sort | reinforcement learning enhanced pseudo inverse approach to self collision avoidance of redundant robots |
| topic | reinforcement learning inverse kinematics redundant robots self-collision avoidance sim to real |
| url | https://www.frontiersin.org/articles/10.3389/fnbot.2024.1375309/full |
| work_keys_str_mv | AT tinghehong areinforcementlearningenhancedpseudoinverseapproachtoselfcollisionavoidanceofredundantrobots AT weibingli areinforcementlearningenhancedpseudoinverseapproachtoselfcollisionavoidanceofredundantrobots AT kaihuang areinforcementlearningenhancedpseudoinverseapproachtoselfcollisionavoidanceofredundantrobots AT tinghehong reinforcementlearningenhancedpseudoinverseapproachtoselfcollisionavoidanceofredundantrobots AT weibingli reinforcementlearningenhancedpseudoinverseapproachtoselfcollisionavoidanceofredundantrobots AT kaihuang reinforcementlearningenhancedpseudoinverseapproachtoselfcollisionavoidanceofredundantrobots |