Robot Motion planning using Deep Reinforcement Learning / (Record no. 614873)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02215nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 629.8 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Khan, Zahra |
| 245 ## - TITLE STATEMENT | |
| Title | Robot Motion planning using Deep Reinforcement Learning / |
| Statement of responsibility, etc. | Zahra Khan |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2025. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 62p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Effective motion planning is needed for autonomous robots in challenging environments.<br/>Sampling-based algorithms sample random points in high-dimensional spaces but struggle<br/>to work well in complex environments due to slow convergence and inefficiencies.<br/>Improvements in Deep Reinforcement Learning (DRL) overcome this strategy through<br/>learning optimal policies from acting in the environment, reducing reliance on<br/>environmental data and faster rates of convergence. But DRL resorts to sparse reward<br/>functions to produce suboptimal paths and poor exploration. To advance beyond such<br/>shortcomings, we propose an active SLAM-sourced information reward function. SLAMweighted reward enhances navigation efficiency with richer environment perception and<br/>robustness in unexplored areas. It comprises distance-to-target and smoothness terms over<br/>trajectory that encourage reduced distances, reduced oscillation, and more stable robot<br/>performance. We use the Soft Actor-Critic (SAC) algorithm in our reward function,<br/>because it is best to perform well in new environments. Comparison experiments using<br/>Twin Delayed Deep Deterministic Policy Gradient (TD3) and Deep Deterministic Policy<br/>Gradient (DDPG) in cluttered and sparse environments demonstrated the superior<br/>performance of SAC. In sparse settings, SAC was 100% successful, performing 9.4%<br/>better than TD3 and 14.1% better than DDPG, and using 35% fewer steps than TD3 and<br/>63% fewer than DDPG. In chaotic settings, SAC was 87.5% successful, performing 40.6%<br/>better than TD3 and 71.9% better than DDPG. These performances attest to the<br/>unprecedented effectiveness of the SAC algorithm in the direction of autonomous robots. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Robotics and Intelligent Machine Engineering |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Fahad Iqbal |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/55263">http://10.250.8.41:8080/xmlui/handle/123456789/55263</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 09/25/2025 | 629.8 | SMME-TH-1179 | Thesis |