Vehicle Lane-Changes Trajectory Prediction Model Considering External Parameters
The ability to predict the motion of vehicles is essential for autonomous vehicles. Aiming at the problem that existing models cannot make full use of the external parameters including the outline of vehicles and the lane, we proposed a model to use the external parameters thoroughly when predicting the trajectory in the straight-line and non-free flow state. Meanwhile, dynamic sensitive area is proposed to filter out inconsequential surrounding vehicles. The historical trajectory of the vehicles and their external parameters are used as inputs. A shared Long Short-Term Memory (LSTM) cell is proposed to encode the explicit states obtained by mapping historical trajectory and external parameters. The hidden states of vehicles obtained from the last step are used to extract latent driving intent. Then, a convolution layer is designed to fuse hidden states to feed into the next prediction circle and a decoder is used to decode the hidden states of the vehicles to predict trajectory. The experiment result shows that the dynamic sensitive area can shorten the training time to 75.86% of the state-of-the-art work. Compared with other models, the accuracy of our model is improved by 23.7%. Meanwhile, the model's ability of anti-interference of external parameters is also improved.
Deo N, Trivedi MM. Convolutional social pooling for vehicle trajectory prediction. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 2018;1805: 1468-76. DOI: 10.1109/CVPRW.2018.00196
Ji X, et al. Driving intention recognition and vehicle trajectory prediction based on LSTM network. Journal of China Highway. 2019;32(6): 34-42.
Barth A, Franke U. Where will the oncoming vehicle be the next second? 2008 IEEE Intelligent Vehicles Symposium, 4-6 June 2008, Eindhoven, The Netherlands; 2018. p. 1068-1073. DOI: 10.1109/IVS.2008.4621210
Toledo-Moreo R, Zamora-Izquierdo MA. IMM-based lane-change prediction in highways with low-cost GPS/INS. IEEE Transactions on Intelligent Transportation Systems. 2009;10(1): 180-5. DOI: 10.1109/TITS.2008.2011691
Schubert R, et al. Empirical evaluation of vehicular models for ego motion estimation. 2011 IEEE Intelligent Vehicles Symposium (IV), 5-9 June 2011, Baden-Baden, Germany; 2011. p. 534-539. DOI: 10.1109/IVS.2011.5940526
Houenou A, Bonnifait P, Cherfaoui V, Yao W. Vehicle trajectory prediction based on motion model and maneuver recognition. 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems, 3-7 Nov. 2013, Tokyo, Japan; 2013. p. 4363-4369. DOI: 10.1109/IROS.2013.6696982
Singh K, Li B. Estimation of traffic densities for multilane roadways using a Markov model approach. IEEE Transactions on Industrial Electronics. 2012;59(11): 4369-76. DOI: 10.1109/TIE.2011.2180271
Berndt H, Emmert J, Dietmayer K. Continuous driver intention recognition with hidden Markov models. 2008 11th International Conference on Intelligent Transportation Systems, 12-15 Oct. 2008, Beijing, China; 2008. p. 1189-1194. DOI: 10.1109/ITSC.2008.4732630
Huang L, Guo H, Zhang R, Wu J. Lane-changing behavior model of unmanned vehicles based on LSTM in human-machine hybrid driving environment. Journal of China Highway. 2020;33(07): 156-66.
Tang J, et al. Lane-changes prediction based on adaptive fuzzy neural network. Expert Systems with Applications. 2018;91: 452-63. DOI: 10.1016/j.eswa.2017.09.025
Wissing C, Nattermann T, Glander K, Bertram T. Probabilistic time-to-lane-change prediction on highways. 2017 IEEE Intelligent Vehicles Symposium (IV), 11-14 June 2017, Los Angeles, CA, USA; 2017. p. 1452-1457. DOI: 10.1109/IVS.2017.7995914
Zyner A, Worrall S, Ward J, Nebot E. Long short term memory for driver intent prediction. 2017 IEEE Intelligent Vehicles Symposium (IV), 11-14 June 2017, Los Angeles, CA, USA; 2017. p. 1484-1489. DOI: 10.1109/IVS.2017.7995919
Phillips DJ, Wheeler TA, Kochenderfer MJ. Generalizable intention prediction of human drivers at intersections. 2017 IEEE Intelligent Vehicles Symposium (IV), 11-14 June 2017, Los Angeles, CA, USA; 2017. p. 1665-1670. DOI: 10.1109/IVS.2017.7995948
Kuefler A, Morton J, Wheeler TA, Kochenderfer MJ. Imitating driver behavior with generative adversarial networks. 2017 IEEE Intelligent Vehicles Symposium (IV), 11-14 June 2017, Los Angeles, CA, USA; 2017. p. 204-211. DOI: 10.1109/IVS.2017.7995721
Liu Z, Wu X, Ni J, Zhang T. Driving intention recognition based on the cascade algorithm of HMM and SVM. Automotive Engineering. 2018;40(07): 858-64.
Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8): 1735-80. DOI: 10.1162/neco.19188.8.131.525
Alahi A, et al. Social LSTM: Human trajectory prediction in crowded spaces. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 27-30 June 2016, Las Vegas, NV, USA; 2016. p. 961-971. DOI: 10.1109/CVPR.2016.110
Liu C, Liang J. Vehicle trajectory prediction based on attention mechanism. Journal of Zhejiang University (Engineering Science Edition). 2019;14: 1-8.
Wang Y, Yang S, Pan B. Research on vehicle trajectory of highway straight section. Highway Traffic Technology. 2016;33(02): 111-9.
Spacek P. Track behavior in curve areas: Attempt at typology. Journal of Transportation Engineering. 2005;131: 669-76. DOI: 10.1061/(ASCE)0733-947X(2005)131:9(669)
Institution CS. GB/T 51328-2018. Stand for urban comprehensive transport system planning. Ministry of Housing and Urban-Rural Development, PRC; 2003. p. 33-41.
NGSIM: Next generation simulation. In: DataHub I; 2016.
Ren S, He K, Girshick R, Sun J. Faster R-CNN: Towards real-time object detection with region proposal networks. Neural Information Processing Systems. 2015: 91-9.
Copyright (c) 2021 Xuchuan Li, Lingkun Fan, Tao Chen, Shuaicong Guo
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).