From reinforcement learning to classical path planning: motion planning with obstacle avoidance
This project investigates the comparative performance of Reinforcement Learning (RL) and sampling-based motion planning methods in robotics, focusing on obstacle avoidance, illustrated in a 3D and 2D environment respectively with a singular agent and obstacle present. This is broken down into two ph...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
Nanyang Technological University
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/181149 |
| _version_ | 1826110030284324864 |
|---|---|
| author | Ng, Tze Minh |
| author2 | Yeo Chai Kiat |
| author_facet | Yeo Chai Kiat Ng, Tze Minh |
| author_sort | Ng, Tze Minh |
| collection | NTU |
| description | This project investigates the comparative performance of Reinforcement Learning (RL) and sampling-based motion planning methods in robotics, focusing on obstacle avoidance, illustrated in a 3D and 2D environment respectively with a singular agent and obstacle present. This is broken down into two phases. The approach involves first replicating the results of a chosen research paper on Soft Actor Critic with Prioritised Experience Replay (SACPER) and running it on a simulation software. Then, a comparative analysis of different sampling-based motion planning algorithms is generated. Through this process, insights into how differing scenarios and tasks call for different methods for optimal performance will be uncovered.
Phase 1 involving the implementation of SACPER was unable to learn due to a stagnant reward curve, which necessitated the need for increased time and computing resources. Phase 2 investigated how sampling-based methods performed in a 2D environment based on slight changes in the environment.
Overall, this project contributes to the understanding of motion planning for robotics, emphasizing the strengths and limitations of learning and sampling-based strategies. Future developments in considering a hybrid approach between learning and sampling-based strategies could be pioneered. |
| first_indexed | 2025-03-09T09:57:14Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/181149 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T09:57:14Z |
| publishDate | 2024 |
| publisher | Nanyang Technological University |
| record_format | dspace |
| spelling | ntu-10356/1811492024-11-18T00:46:50Z From reinforcement learning to classical path planning: motion planning with obstacle avoidance Ng, Tze Minh Yeo Chai Kiat College of Computing and Data Science ASCKYEO@ntu.edu.sg Computer and Information Science Reinforcement learning Motion planning This project investigates the comparative performance of Reinforcement Learning (RL) and sampling-based motion planning methods in robotics, focusing on obstacle avoidance, illustrated in a 3D and 2D environment respectively with a singular agent and obstacle present. This is broken down into two phases. The approach involves first replicating the results of a chosen research paper on Soft Actor Critic with Prioritised Experience Replay (SACPER) and running it on a simulation software. Then, a comparative analysis of different sampling-based motion planning algorithms is generated. Through this process, insights into how differing scenarios and tasks call for different methods for optimal performance will be uncovered. Phase 1 involving the implementation of SACPER was unable to learn due to a stagnant reward curve, which necessitated the need for increased time and computing resources. Phase 2 investigated how sampling-based methods performed in a 2D environment based on slight changes in the environment. Overall, this project contributes to the understanding of motion planning for robotics, emphasizing the strengths and limitations of learning and sampling-based strategies. Future developments in considering a hybrid approach between learning and sampling-based strategies could be pioneered. Bachelor's degree 2024-11-18T00:46:50Z 2024-11-18T00:46:50Z 2024 Final Year Project (FYP) Ng, T. M. (2024). From reinforcement learning to classical path planning: motion planning with obstacle avoidance. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/181149 https://hdl.handle.net/10356/181149 en SCSE23-1186 application/pdf Nanyang Technological University |
| spellingShingle | Computer and Information Science Reinforcement learning Motion planning Ng, Tze Minh From reinforcement learning to classical path planning: motion planning with obstacle avoidance |
| title | From reinforcement learning to classical path planning: motion planning with obstacle avoidance |
| title_full | From reinforcement learning to classical path planning: motion planning with obstacle avoidance |
| title_fullStr | From reinforcement learning to classical path planning: motion planning with obstacle avoidance |
| title_full_unstemmed | From reinforcement learning to classical path planning: motion planning with obstacle avoidance |
| title_short | From reinforcement learning to classical path planning: motion planning with obstacle avoidance |
| title_sort | from reinforcement learning to classical path planning motion planning with obstacle avoidance |
| topic | Computer and Information Science Reinforcement learning Motion planning |
| url | https://hdl.handle.net/10356/181149 |
| work_keys_str_mv | AT ngtzeminh fromreinforcementlearningtoclassicalpathplanningmotionplanningwithobstacleavoidance |