Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections
© 2019 IEEE. Predicting the motion of a driver's vehicle is crucial for advanced driving systems, enabling detection of potential risks towards shared control between the driver and automation systems. In this paper, we propose a variational neural network approach that predicts future driver t...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2021
|
| Online Access: | https://hdl.handle.net/1721.1/135898 |
| _version_ | 1826204297599123456 |
|---|---|
| author | Huang, Xin McGill, Stephen G Williams, Brian C Fletcher, Luke Rosman, Guy |
| author2 | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory |
| author_facet | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Huang, Xin McGill, Stephen G Williams, Brian C Fletcher, Luke Rosman, Guy |
| author_sort | Huang, Xin |
| collection | MIT |
| description | © 2019 IEEE. Predicting the motion of a driver's vehicle is crucial for advanced driving systems, enabling detection of potential risks towards shared control between the driver and automation systems. In this paper, we propose a variational neural network approach that predicts future driver trajectory distributions for the vehicle based on multiple sensors.Our predictor generates both a conditional variational distribution of future trajectories, as well as a confidence estimate for different time horizons. Our approach allows us to handle inherently uncertain situations, and reason about information gain from each input, as well as combine our model with additional predictors, creating a mixture of experts.We show how to augment the variational predictor with a physics-based predictor, and based on their confidence estimations, improve overall system performance. The resulting combined model is aware of the uncertainty associated with its predictions, which can help the vehicle autonomy to make decisions with more confidence. The model is validated on real-world urban driving data collected in multiple locations. This validation demonstrates that our approach improves the prediction error of a physics-based model by 25% while successfully identifying the uncertain cases with 82% accuracy. |
| first_indexed | 2024-09-23T12:52:04Z |
| format | Article |
| id | mit-1721.1/135898 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T12:52:04Z |
| publishDate | 2021 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/1358982023-02-23T16:41:35Z Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections Huang, Xin McGill, Stephen G Williams, Brian C Fletcher, Luke Rosman, Guy Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory © 2019 IEEE. Predicting the motion of a driver's vehicle is crucial for advanced driving systems, enabling detection of potential risks towards shared control between the driver and automation systems. In this paper, we propose a variational neural network approach that predicts future driver trajectory distributions for the vehicle based on multiple sensors.Our predictor generates both a conditional variational distribution of future trajectories, as well as a confidence estimate for different time horizons. Our approach allows us to handle inherently uncertain situations, and reason about information gain from each input, as well as combine our model with additional predictors, creating a mixture of experts.We show how to augment the variational predictor with a physics-based predictor, and based on their confidence estimations, improve overall system performance. The resulting combined model is aware of the uncertainty associated with its predictions, which can help the vehicle autonomy to make decisions with more confidence. The model is validated on real-world urban driving data collected in multiple locations. This validation demonstrates that our approach improves the prediction error of a physics-based model by 25% while successfully identifying the uncertain cases with 82% accuracy. 2021-10-27T20:29:51Z 2021-10-27T20:29:51Z 2019 2021-05-05T13:53:10Z Article http://purl.org/eprint/type/ConferencePaper https://hdl.handle.net/1721.1/135898 en 10.1109/ICRA.2019.8794282 Proceedings - IEEE International Conference on Robotics and Automation Creative Commons Attribution-Noncommercial-Share Alike http://creativecommons.org/licenses/by-nc-sa/4.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) arXiv |
| spellingShingle | Huang, Xin McGill, Stephen G Williams, Brian C Fletcher, Luke Rosman, Guy Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections |
| title | Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections |
| title_full | Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections |
| title_fullStr | Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections |
| title_full_unstemmed | Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections |
| title_short | Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections |
| title_sort | uncertainty aware driver trajectory prediction at urban intersections |
| url | https://hdl.handle.net/1721.1/135898 |
| work_keys_str_mv | AT huangxin uncertaintyawaredrivertrajectorypredictionaturbanintersections AT mcgillstepheng uncertaintyawaredrivertrajectorypredictionaturbanintersections AT williamsbrianc uncertaintyawaredrivertrajectorypredictionaturbanintersections AT fletcherluke uncertaintyawaredrivertrajectorypredictionaturbanintersections AT rosmanguy uncertaintyawaredrivertrajectorypredictionaturbanintersections |