Predictive neural motion planner for autonomous driving using graph networks
Recent advances in digital twin and parallel intelligence (DTPI) enable the mapping of the physical world to a high-fidelity virtual representation and facilitate intelligent prediction and decision-making for autonomous vehicles and intelligent transportation systems. In the context of DTPI, in thi...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/178356 |
| _version_ | 1826114310910246912 |
|---|---|
| author | Mo, Xiaoyu Lv, Chen |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Mo, Xiaoyu Lv, Chen |
| author_sort | Mo, Xiaoyu |
| collection | NTU |
| description | Recent advances in digital twin and parallel intelligence (DTPI) enable the mapping of the physical world to a high-fidelity virtual representation and facilitate intelligent prediction and decision-making for autonomous vehicles and intelligent transportation systems. In the context of DTPI, in this study, we investigate trajectory-prediction-enabled motion planning for autonomous vehicles using deep neural networks. We first implement a motion planner using a neural network as an approximation of traditional planners. The inputs to the baseline planner include the current states of the ego and its surrounding agents and a shared map. The planner produces a five-second trajectory for the ego vehicle considering the current situation. Subsequently, we generalize the baseline to consider the historical states of the ego and its surrounding agents. Using the generalized planner, we investigate the impacts of the history horizon on planning performance. We next investigate how the future motions of the surrounding agents of the ego affect the planner and observe improvement in planning. This demonstrates that knowledge of the future trajectories of other agents is useful for planning. However, we do not have access to ground-truth future motions for inference. Finally, we investigate how the future can be approximated through prediction and how the prediction quality affects planning performance. |
| first_indexed | 2024-10-01T03:37:04Z |
| format | Journal Article |
| id | ntu-10356/178356 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:37:04Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1783562024-06-15T16:48:14Z Predictive neural motion planner for autonomous driving using graph networks Mo, Xiaoyu Lv, Chen School of Mechanical and Aerospace Engineering Engineering Autonomous vehicles Graph neural networks Recent advances in digital twin and parallel intelligence (DTPI) enable the mapping of the physical world to a high-fidelity virtual representation and facilitate intelligent prediction and decision-making for autonomous vehicles and intelligent transportation systems. In the context of DTPI, in this study, we investigate trajectory-prediction-enabled motion planning for autonomous vehicles using deep neural networks. We first implement a motion planner using a neural network as an approximation of traditional planners. The inputs to the baseline planner include the current states of the ego and its surrounding agents and a shared map. The planner produces a five-second trajectory for the ego vehicle considering the current situation. Subsequently, we generalize the baseline to consider the historical states of the ego and its surrounding agents. Using the generalized planner, we investigate the impacts of the history horizon on planning performance. We next investigate how the future motions of the surrounding agents of the ego affect the planner and observe improvement in planning. This demonstrates that knowledge of the future trajectories of other agents is useful for planning. However, we do not have access to ground-truth future motions for inference. Finally, we investigate how the future can be approximated through prediction and how the prediction quality affects planning performance. Agency for Science, Technology and Research (A*STAR) Nanyang Technological University Submitted/Accepted version This work was supported in part by the Start-Up Grant of Nanyang Technological University, Singapore, and in part by the Agency for Science, Technology and Research (A∗STAR) through Advanced Manufacturing and Engineering (AME) Young Individual Research under Grant A2084c0156. 2024-06-13T06:19:24Z 2024-06-13T06:19:24Z 2023 Journal Article Mo, X. & Lv, C. (2023). Predictive neural motion planner for autonomous driving using graph networks. IEEE Transactions On Intelligent Vehicles, 8(2), 1983-1993. https://dx.doi.org/10.1109/TIV.2023.3234370 2379-8858 https://hdl.handle.net/10356/178356 10.1109/TIV.2023.3234370 2 8 1983 1993 en NTU-SUG A2084c0156 IEEE Transactions on Intelligent Vehicles © 2023 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/TIV.2023.3234370. application/pdf |
| spellingShingle | Engineering Autonomous vehicles Graph neural networks Mo, Xiaoyu Lv, Chen Predictive neural motion planner for autonomous driving using graph networks |
| title | Predictive neural motion planner for autonomous driving using graph networks |
| title_full | Predictive neural motion planner for autonomous driving using graph networks |
| title_fullStr | Predictive neural motion planner for autonomous driving using graph networks |
| title_full_unstemmed | Predictive neural motion planner for autonomous driving using graph networks |
| title_short | Predictive neural motion planner for autonomous driving using graph networks |
| title_sort | predictive neural motion planner for autonomous driving using graph networks |
| topic | Engineering Autonomous vehicles Graph neural networks |
| url | https://hdl.handle.net/10356/178356 |
| work_keys_str_mv | AT moxiaoyu predictiveneuralmotionplannerforautonomousdrivingusinggraphnetworks AT lvchen predictiveneuralmotionplannerforautonomousdrivingusinggraphnetworks |