Reinforcement learning based control design for mobile robot motion control
The reinforcement learning (RL) based methods show people an alternative way to solve multiple problems in robot motion control. RL based algorithms have the ability to autonomously learn the law of controller through the interaction with environments, especially with the combination with the neuron...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis-Master by Coursework |
| Language: | English |
| Published: |
Nanyang Technological University
2021
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/152345 |
| _version_ | 1811691941724684288 |
|---|---|
| author | Wu, Tanghong |
| author2 | Hu Guoqiang |
| author_facet | Hu Guoqiang Wu, Tanghong |
| author_sort | Wu, Tanghong |
| collection | NTU |
| description | The reinforcement learning (RL) based methods show people an alternative way to solve multiple problems in robot motion control. RL based algorithms have the ability to autonomously learn the law of controller through the interaction with environments, especially with the combination with the neuronal network, the deep RL based methods attended its’ ability in continuous state-space and action-space control problems instead of solving nonlinear kinematic equations compared with the traditional method. In this thesis, we study three advanced deep Reinforcement Learning algorithms and achieve the simulation on the Minitaur robot model and Pybulet physics engine to control the motion. Furthermore, we discuss the performance of each algorithm considering the best result and overall result from multiple epochs of simulations. Finally, we assess the advantages and disadvantages of those reinforcement learning algorithms via statistical analysis based on the average reward from the simulations. |
| first_indexed | 2024-10-01T06:27:54Z |
| format | Thesis-Master by Coursework |
| id | ntu-10356/152345 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:27:54Z |
| publishDate | 2021 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1523452023-07-04T17:34:58Z Reinforcement learning based control design for mobile robot motion control Wu, Tanghong Hu Guoqiang School of Electrical and Electronic Engineering GQHu@ntu.edu.sg Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics The reinforcement learning (RL) based methods show people an alternative way to solve multiple problems in robot motion control. RL based algorithms have the ability to autonomously learn the law of controller through the interaction with environments, especially with the combination with the neuronal network, the deep RL based methods attended its’ ability in continuous state-space and action-space control problems instead of solving nonlinear kinematic equations compared with the traditional method. In this thesis, we study three advanced deep Reinforcement Learning algorithms and achieve the simulation on the Minitaur robot model and Pybulet physics engine to control the motion. Furthermore, we discuss the performance of each algorithm considering the best result and overall result from multiple epochs of simulations. Finally, we assess the advantages and disadvantages of those reinforcement learning algorithms via statistical analysis based on the average reward from the simulations. Master of Science (Computer Control and Automation) 2021-08-05T05:53:35Z 2021-08-05T05:53:35Z 2021 Thesis-Master by Coursework Wu, T. (2021). Reinforcement learning based control design for mobile robot motion control. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/152345 https://hdl.handle.net/10356/152345 en application/pdf Nanyang Technological University |
| spellingShingle | Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics Wu, Tanghong Reinforcement learning based control design for mobile robot motion control |
| title | Reinforcement learning based control design for mobile robot motion control |
| title_full | Reinforcement learning based control design for mobile robot motion control |
| title_fullStr | Reinforcement learning based control design for mobile robot motion control |
| title_full_unstemmed | Reinforcement learning based control design for mobile robot motion control |
| title_short | Reinforcement learning based control design for mobile robot motion control |
| title_sort | reinforcement learning based control design for mobile robot motion control |
| topic | Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics |
| url | https://hdl.handle.net/10356/152345 |
| work_keys_str_mv | AT wutanghong reinforcementlearningbasedcontroldesignformobilerobotmotioncontrol |