Space-Time Tree Search for Long-Term Trajectory Prediction
The pedestrian trajectory prediction is critical for autonomous driving, intelligent navigation, and abnormal behavior detection. With the booming of artificial intelligence (AI), many researchers have employed deep learning technologies to solve the pedestrian trajectory prediction problem and obta...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9915574/ |
| _version_ | 1828130315148722176 |
|---|---|
| author | Tingyong Wu Peizhi Lei Fuqiang Li Jienan Chen |
| author_facet | Tingyong Wu Peizhi Lei Fuqiang Li Jienan Chen |
| author_sort | Tingyong Wu |
| collection | DOAJ |
| description | The pedestrian trajectory prediction is critical for autonomous driving, intelligent navigation, and abnormal behavior detection. With the booming of artificial intelligence (AI), many researchers have employed deep learning technologies to solve the pedestrian trajectory prediction problem and obtained relatively better performance in the short-term trajectory prediction. However, long-term trajectory prediction is still challenging to achieve high prediction accuracy. In this work, we propose a space-time tree search (STTS) method for long-term pedestrian trajectory prediction. Compared with existing methods only considering the problem from the space dimension, the proposed method formulates the trajectory prediction problem as a joint space-time tree search process by mapping the environment to a grid map. Since the human’s trajectory is relative to space and time dimensions, the trajectory prediction accuracy can be improved by the two dimensions. Then, a space-time reward trained neural network is employed to extract the pedestrian’s intent with both the scene image and the historical trajectory as input and outputs the prior search probabilities. Finally, the tree search can obtain the optimal predicted trajectory according to the prior probabilities, significantly improving the tree search efficiency. After testing, our proposed method can perform better than existing methods. |
| first_indexed | 2024-04-11T16:32:14Z |
| format | Article |
| id | doaj.art-1a9a8d5af0454d28a1653f8670aca3a9 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-11T16:32:14Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-1a9a8d5af0454d28a1653f8670aca3a92022-12-22T04:13:59ZengIEEEIEEE Access2169-35362022-01-011011774511775610.1109/ACCESS.2022.32136919915574Space-Time Tree Search for Long-Term Trajectory PredictionTingyong Wu0https://orcid.org/0000-0002-2228-7992Peizhi Lei1Fuqiang Li2Jienan Chen3https://orcid.org/0000-0003-1265-0775National Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, ChinaNational Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, ChinaKey Laboratory of Technology on Datalink, China Electronics Technology Group Corporation (CETC), 20th Institute, Xi’an, ChinaNational Key Laboratory of Science and Technology on Communications, University of Electronic Science and Technology of China, Chengdu, ChinaThe pedestrian trajectory prediction is critical for autonomous driving, intelligent navigation, and abnormal behavior detection. With the booming of artificial intelligence (AI), many researchers have employed deep learning technologies to solve the pedestrian trajectory prediction problem and obtained relatively better performance in the short-term trajectory prediction. However, long-term trajectory prediction is still challenging to achieve high prediction accuracy. In this work, we propose a space-time tree search (STTS) method for long-term pedestrian trajectory prediction. Compared with existing methods only considering the problem from the space dimension, the proposed method formulates the trajectory prediction problem as a joint space-time tree search process by mapping the environment to a grid map. Since the human’s trajectory is relative to space and time dimensions, the trajectory prediction accuracy can be improved by the two dimensions. Then, a space-time reward trained neural network is employed to extract the pedestrian’s intent with both the scene image and the historical trajectory as input and outputs the prior search probabilities. Finally, the tree search can obtain the optimal predicted trajectory according to the prior probabilities, significantly improving the tree search efficiency. After testing, our proposed method can perform better than existing methods.https://ieeexplore.ieee.org/document/9915574/Long-term trajectory predictionspace-time rewardtree searchneural network |
| spellingShingle | Tingyong Wu Peizhi Lei Fuqiang Li Jienan Chen Space-Time Tree Search for Long-Term Trajectory Prediction IEEE Access Long-term trajectory prediction space-time reward tree search neural network |
| title | Space-Time Tree Search for Long-Term Trajectory Prediction |
| title_full | Space-Time Tree Search for Long-Term Trajectory Prediction |
| title_fullStr | Space-Time Tree Search for Long-Term Trajectory Prediction |
| title_full_unstemmed | Space-Time Tree Search for Long-Term Trajectory Prediction |
| title_short | Space-Time Tree Search for Long-Term Trajectory Prediction |
| title_sort | space time tree search for long term trajectory prediction |
| topic | Long-term trajectory prediction space-time reward tree search neural network |
| url | https://ieeexplore.ieee.org/document/9915574/ |
| work_keys_str_mv | AT tingyongwu spacetimetreesearchforlongtermtrajectoryprediction AT peizhilei spacetimetreesearchforlongtermtrajectoryprediction AT fuqiangli spacetimetreesearchforlongtermtrajectoryprediction AT jienanchen spacetimetreesearchforlongtermtrajectoryprediction |