Articles | Volume 16, issue 1
https://doi.org/10.5194/ms-16-87-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/ms-16-87-2025
© Author(s) 2025. This work is distributed under
the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Interactive trajectory prediction for autonomous driving based on Transformer
Rui Xu
School of Mechanotronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, 400074, China
Jun Li
CORRESPONDING AUTHOR
School of Mechanotronics and Vehicle Engineering, Chongqing Jiaotong University, Chongqing, 400074, China
Shiyi Zhang
School of Shipping and Naval Architecture, Chongqing Jiaotong University, Chongqing, 400074, China
Institute of Agricultural Machinery, Chongqing Academy of Agricultural Sciences, Chongqing, 400074, China
Hulin Li
School of Traffic and Transportation, Chongqing Jiaotong University, Chongqing, 400074, China
Guiying Ren
Institute of Agricultural Machinery, Chongqing Academy of Agricultural Sciences, Chongqing, 400074, China
Xinglong Tang
Institute of Agricultural Machinery, Chongqing Academy of Agricultural Sciences, Chongqing, 400074, China
Related authors
No articles found.
Lei Li, Jun Li, and Shiyi Zhang
Mech. Sci., 12, 419–432, https://doi.org/10.5194/ms-12-419-2021, https://doi.org/10.5194/ms-12-419-2021, 2021
Short summary
Short summary
This paper reviews the state-of-the-art trajectory tracking of autonomous vehicles. Autonomous vehicles have become more and more popular with the development of artificial intelligence and automatic control. If you have any interest in the trajectory tracking of autonomous vehicles, this paper is the one that you can not miss. It will give you a brief concept of the current development of the trajectory tracking of autonomous vehicles.
Related subject area
Subject: Mechanisms and Robotics | Techniques and Approaches: Optimization
Thermomechanical coupled topology optimization of parameterized lattice structures
Kinematic analysis and bearing capacity optimization of fully decoupled two-rotation mechanisms
Multi-objective optimization design of parallel manipulators using a neural network and principal component analysis
Topology optimization for thermal structures considering design-dependent convection boundaries based on the bidirectional evolutionary structural optimization method
Parameter optimization of a pure electric sweeper dust port by a backpropagation neural network combined with a whale algorithm
Structural design of multi-body heave wave energy conversion system and analysis of energy efficiency of floating body on water surface
Multi-objective optimization of a redundantly actuated parallel robot mechanism for special machining
Evolutionary multi-objective trajectory optimization for a redundant robot in Cartesian space considering obstacle avoidance
Bionic design and analysis of a multi-posture wheelchair
Design and motion analysis of a small motor stator multi-wire paralleled winding hybrid robot
Structure optimization design of a thin-film diffraction imaging system based on the Kriging model and the improved particle swarm optimization algorithm
Study on compliant actuator based on compliance features of flexible hinges
Scheme optimization for a turbine blade under multiple working conditions based on the entropy weight vague set
Topology optimization design of a lightweight integrated manifold with low pressure loss in a hydraulic quadruped robot actuator
Spatial cellular robot in orbital truss collision-free path planning
Review article: Performance measures of parallel kinematics manipulators
Multi-objective optimization of a type of ellipse-parabola shaped superelastic flexure hinge
Successive dynamic programming and subsequent spline optimization for smooth time optimal robot path tracking
On understanding of design problem formulation for compliant mechanisms through topology optimization
Design and optimization of a XY compliant mechanical displacement amplifier
Hongyi Zhang, Yang Wang, Shuyou Zhang, Xiaojian Liu, and Xuewei Zhang
Mech. Sci., 15, 555–566, https://doi.org/10.5194/ms-15-555-2024, https://doi.org/10.5194/ms-15-555-2024, 2024
Short summary
Short summary
This paper presents an optimization approach to improving the performance of lattice structures subjected to thermal and mechanical loads. The proposed method is demonstrated through examples of battery packs, L-brackets, and machine tool headstocks. The results of numerical verification show that the proposed method enhances the performance of designed structures greatly compared with traditional solid-design and temperature constraints.
Sen Wang, Xueyan Han, Haoran Li, Hongyu Xu, and Shihua Li
Mech. Sci., 15, 111–121, https://doi.org/10.5194/ms-15-111-2024, https://doi.org/10.5194/ms-15-111-2024, 2024
Short summary
Short summary
In order to meet the need for high accuracy in road spectrum reproduction of vehicle durability tests, this paper is based on analysis of factors affecting the accuracy of a test platform. The large load capacity and fully decoupled mechanism proposed in the research work of this paper can improve the road spectrum reproduction accuracy of the vehicle durability test platform and has good application prospects in the field of vehicle durability tests.
Chao Yang, Peijiao Li, Yang Wang, Wei Ye, Tianze Sun, Fengli Huang, and Hui Zhang
Mech. Sci., 14, 361–370, https://doi.org/10.5194/ms-14-361-2023, https://doi.org/10.5194/ms-14-361-2023, 2023
Short summary
Short summary
The main contribution of this work is to propose a multi-objective optimization design method in terms of factor analysis, a back-propagation (BP) neural network, principal component analysis (PCA), and a particle swarm optimization (PSO) algorithm to achieve optimal comprehensive performance of a mechanism. The computational cost of the proposed approach was reduced by 96.95 % compared with the PSO algorithm, and the comprehensive performance increased by 118.92 %.
Yanding Guo, Dong Wei, Tieqiang Gang, Xining Lai, Xiaofeng Yang, Guangming Xiao, and Lijie Chen
Mech. Sci., 14, 223–235, https://doi.org/10.5194/ms-14-223-2023, https://doi.org/10.5194/ms-14-223-2023, 2023
Short summary
Short summary
This research provides a topology optimization method for thermal structures considering design-dependent convection boundaries. The effectiveness of the proposed method is illustrated using cases with reasonable configurations under complex thermal boundary conditions.
Jiabao Pan, Jin Ye, Hejin Ai, Jiamei Wang, and You Wan
Mech. Sci., 14, 47–60, https://doi.org/10.5194/ms-14-47-2023, https://doi.org/10.5194/ms-14-47-2023, 2023
Short summary
Short summary
Optimizing the structure of the dust extraction port is the key to effectively improving the operational performance of the sweeper. CFD methods are used to analyze the influence of parameters on the sweeping effect in combination with a gas–solid two-phase flow model. The data set is established with the help of orthogonal test methods, and a BP neural network is used to fit the structural parameters and evaluation indexes.
Dongsheng Cong, Hao Jing, Ruijun Zhang, Zhongyue Lu, Jianzhong Shang, and Zirong Luo
Mech. Sci., 13, 411–425, https://doi.org/10.5194/ms-13-411-2022, https://doi.org/10.5194/ms-13-411-2022, 2022
Short summary
Short summary
Due to the defects of the internal structure and energy supply carrier, conventional deep sea unoccupied marine equipment cannot meet the requirements of low power consumption. The energy efficiency characteristics of floating bodies with different shapes were simulated, and the amplitude response operator (RAO), radiation damping, added mass and Froude–Krylov force of floating bodies with different shapes were compared.
Haiqiang Zhang, Jianglong Tang, Qing Gao, Guohua Cui, Kan Shi, and Yan'an Yao
Mech. Sci., 13, 123–136, https://doi.org/10.5194/ms-13-123-2022, https://doi.org/10.5194/ms-13-123-2022, 2022
Short summary
Short summary
Compared with the two traditional intelligent optimization algorithms, the results show that the particle swarm optimization configuration algorithm, based on an improved orthogonal experiment design, has a better optimization effect, and the results are improved to a certain extent. The evaluation indexes of a multi-objective optimization design are often contradictory. The designer needs to compromise and select an appropriate parameter design value.
Yong Liu, Xiang Li, Peiyang Jiang, Zhe Du, Zhe Wu, Boxi Sun, and Xinyan Huang
Mech. Sci., 13, 41–53, https://doi.org/10.5194/ms-13-41-2022, https://doi.org/10.5194/ms-13-41-2022, 2022
Short summary
Short summary
First, we calculated the trajectory of the end effector of manipulator. This trajectory enables the end effector to reach the desired pose. At the same time, collision detection algorithm was employed to calculate the distance between each link of the manipulator and obstacle. We utilized the multi-objective particle swarm optimization algorithm to optimize the trajectory to minimize joint motor energy consumption and reduce joint velocity and joint impact during the movement of the manipulator.
Qiaoling Meng, Mingpeng Jiang, Zongqi Jiao, and Hongliu Yu
Mech. Sci., 13, 1–13, https://doi.org/10.5194/ms-13-1-2022, https://doi.org/10.5194/ms-13-1-2022, 2022
Short summary
Short summary
This paper proposes a bionic, multi-posture wheelchair, based on the proposed human–wheelchair coupling model, according to the movement characteristics and requirements. The two key factors in designing the multi-posture wheelchair, the consistency of the motion center and the compensation of the shifting center of gravity, are analyzed in this paper. The novel multi-posture wheelchair can implement the sit-to-lie and sit-to-stand transformations with a maximum slipping distance of 10.5 mm.
Yanling Zhao, Enwen Zhou, Jingwei Zhang, Chunya Wu, and Chuang Yang
Mech. Sci., 12, 1005–1016, https://doi.org/10.5194/ms-12-1005-2021, https://doi.org/10.5194/ms-12-1005-2021, 2021
Short summary
Short summary
Small motor stator winding at the same time is difficult to guarantee the uniform arrangement of enameled wire. This paper proposes a three-phase parallel equivalent multi-wire winding robot. The manipulator structure is designed, and the joint motion planning simulation is carried out to verify the feasibility of the multi-wire parallel winding hybrid robot. The research results of this paper provide a theoretical reference for multi-wire parallel winding equipment control.
Yitian Wang, Liu Zhang, Huanyu Zhao, and Fan Zhang
Mech. Sci., 12, 875–889, https://doi.org/10.5194/ms-12-875-2021, https://doi.org/10.5194/ms-12-875-2021, 2021
Short summary
Short summary
This paper aims to investigate the problem of the complex structure optimization of a thin-film diffraction imaging system. A method based on the Kriging model and the improved particle swarm algorithm is proposed to optimize the structure of the thin-film diffraction imaging system. After optimization, the flexible vibration of the improved thin-film diffraction imaging system is effectively suppressed, and the stiffness and stability of the supporting structure are significantly improved.
Qian Lu, Chengyang Wang, Kaikai Zhang, and Hong Gao
Mech. Sci., 12, 837–846, https://doi.org/10.5194/ms-12-837-2021, https://doi.org/10.5194/ms-12-837-2021, 2021
Short summary
Short summary
In this paper, a new parameter, the compliance ratio λ, which could reflect the sensitivity of the main form of the flexible hinge's output displacement, is proposed and discussed in detail. The optimization of the compliant actuator is carried out analyzing the compliance features of different types of flexible hinges. Finally, an actual precision linear position platform will be taken as an example, to prove the key performance of the compliant actuator is much better.
Guodong Yi, Huifang Zhou, Yang Wang, Jingli Wu, and Jundi Wu
Mech. Sci., 12, 615–624, https://doi.org/10.5194/ms-12-615-2021, https://doi.org/10.5194/ms-12-615-2021, 2021
Short summary
Short summary
The deformation of blades under complex loads of multiple working conditions reduces the energy conversion efficiency. To reduce the deviation of the blade shape in practical working conditions, a combination and optimization method of blade design schemes under multiple working conditions, based on the entropy weight vague sets, is proposed. The results show that the proposed design scheme has a smaller blade shape deviation than the traditional design scheme under multiple working conditions.
Hsinpu Huang, Junhui Zhang, Bing Xu, Gan Liu, Qingyou Luo, and Ximeng Wang
Mech. Sci., 12, 249–257, https://doi.org/10.5194/ms-12-249-2021, https://doi.org/10.5194/ms-12-249-2021, 2021
Short summary
Short summary
Robots are a hot topic of research nowadays. Making robot action more accurate and faster is the direction of scholars' efforts. Based on the hydraulic quadruped robot designed by the State Key Laboratory of Fluid Power & Mechatronic System, Zhejiang University, this article discusses the lightweight design for manifold mounted on the hydraulic actuator. Through topology optimization and channel optimization, the part is lighter and the drag loss is less.
Ye Dai, Zhaoxu Liu, Yunshan Qi, Hanbo Zhang, Bindi You, and Yufei Gao
Mech. Sci., 11, 233–250, https://doi.org/10.5194/ms-11-233-2020, https://doi.org/10.5194/ms-11-233-2020, 2020
Short summary
Short summary
Aiming at the problem of moving path planning of a cellular robot on trusses in space station, a triangular prism truss is taken as the research object, and an optimized ant colony algorithm incorporating a gravitational search algorithm is proposed. The simulation results show that the path and planning time of the cellular robot can be effectively reduced when choosing truss path.
Abdur Rosyid, Bashar El-Khasawneh, and Anas Alazzam
Mech. Sci., 11, 49–73, https://doi.org/10.5194/ms-11-49-2020, https://doi.org/10.5194/ms-11-49-2020, 2020
Short summary
Short summary
This extensive review paper, which involves 204 papers, discusses comprehensively a number of performance indices that are instrumental in the design of parallel kinematics manipulators. These indices measure the workspace as well as its quality including the distance to singularity, dexterity, manipulability, force transmission, accuracy, stiffness, and dynamic performance. This paper would benefit designers, practitioners and researchers in better understanding parallel manipulators.
Zhijiang Du, Miao Yang, and Wei Dong
Mech. Sci., 7, 127–134, https://doi.org/10.5194/ms-7-127-2016, https://doi.org/10.5194/ms-7-127-2016, 2016
M. Oberherber, H. Gattringer, and A. Müller
Mech. Sci., 6, 245–254, https://doi.org/10.5194/ms-6-245-2015, https://doi.org/10.5194/ms-6-245-2015, 2015
Short summary
Short summary
The time optimal path following problem for industrial robots regards the problem of generating trajectories that follow predefined end-effector paths in shortest time possible, taking into account kinematic and dynamic constraints. This paper proposes an approach to deal with arbitrary long geometric paths. Further a method is presented to achieve suitable smooth trajectories for an implementation on a real robot, in an easy way.
L. Cao, A. Dolovich, and W. J. Zhang
Mech. Sci., 4, 357–369, https://doi.org/10.5194/ms-4-357-2013, https://doi.org/10.5194/ms-4-357-2013, 2013
A. Eskandari and P. R. Ouyang
Mech. Sci., 4, 303–310, https://doi.org/10.5194/ms-4-303-2013, https://doi.org/10.5194/ms-4-303-2013, 2013
Cited articles
Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., and Savarese, S.: Social LSTM: Human Trajectory Prediction in Crowded Spaces, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016, IEEE, 961–971, https://doi.org/10.1109/CVPR.2016.110, 2016.
Bhat, M., Francis, J., and Oh, J.: Trajformer: Trajectory Prediction with Local Self-Attentive Contexts for Autonomous Driving, arXiv [preprint], https://doi.org/10.48550/arXiv.2011.14910, 30 November 2020.
Chang, M. F., Lambert, J., Sangkloy, P., Singh, J., Bak, S., Hartnett, A., Wang, D., Carr, P., Lucey, S., and Ramanan, D.: Argoverse: 3D Tracking and Forecasting With Rich Maps, arXiv [preprint], https://doi.org/10.48550/arXiv.1911.02620, 6 November 2019.
Cui, Z., Henrickson, K., Ke, R., and Wang, Y.: Traffic graph convolutional recurrent neural network: A deep learning framework for network-scale traffic learning and forecasting, IEEE T. Intell. Transp., 21, 4883–4894, https://doi.org/10.1109/TITS.2019.2950416, 2020.
Dai, S., Li, L., and Li, Z.: Modeling vehicle interactions via modified LSTM models for trajectory prediction, IEEE Access, 7, 38287–38296, https://doi.org/10.1109/ACCESS.2019.2907000, 2019.
Deo, N. and Trivedi, M. M.: Convolutional social pooling for vehicle trajectory prediction, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, UT, USA, 1–22 June 2018, IEEE, 1549–1548, https://doi.org/10.1109/CVPRW.2018.00196, 2018.
Deo, N., Rangesh, A., and Trivedi, M. M.: How would surround vehicles move? a unified framework for maneuver classification and motion prediction, IEEE Transactions on Intelligent Vehicles, 3, 129–140, https://doi.org/10.1109/TIV.2018.2804159, 2018.
Djuric, N., Radosavljevic, V., Cui, H., Nguyen, T., Chou, F.-C., Lin, T.-H., Singh, N., and Schneider, J.: Uncertainty-aware short-term motion prediction of traffic actors for autonomous driving, in: 2020 IEEE Winter Conference on Applications of Computer Vision (WACV), Snowmass, CO, USA, 1–5 March 2020, IEEE, 2084–2093, https://doi.org/10.1109/WACV45572.2020.9093332, 2020.
Gao, J., Sun, C., Zhao, H., Shen, Y., Anguelov, D., Li, C., and Schmid, C.: Vectornet: Encoding hd maps and agent dynamics from vectorized representation, in: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–16 june 2020, IEEE, 11525–11530, https://doi.org/10.1109/CVPR42600.2020.01154, 2020.
Hou, L., Xin, L., Li, S. E., Cheng, B., and Wang, W.: Interactive trajectory prediction of surrounding road users for autonomous driving using structural-LSTM network, IEEE T. Intell. Transp., 21, 4615–4625, https://doi.org/10.1109/TITS.2019.2942089, 2019.
Hubmann, C., Schulz, J., Becker, M., Althoff, D., and Stiller, C.: Automated driving in uncertain environments: Planning with interaction and uncertain maneuver prediction, IEEE Transactions on Intelligent Vehicles, 3, 5–17, https://doi.org/10.1109/TIV.2017.2788208, 2018.
Jeong, Y., Kim, S., and Yi, K.: Surround vehicle motion prediction using LSTM-RNN for motion planning of autonomous vehicles at multi-lane turn intersections, IEEE Open Journal of Intelligent Transportation Systems, 1, 2–14, https://doi.org/10.1109/OJITS.2020.2965969, 2020.
Keller, C. G. and Gavrila, D. M.: Will the pedestrian cross? A study on pedestrian path prediction, IEEE T. Intell. Transp., 15, 494–506, https://doi.org/10.1109/TITS.2013.2280766, 2013.
Lee, N., Choi, W., Vernaza, P., Choy, C. B., Torr, P. H., and Chandraker, M.: Desire: DESIRE:Distant future prediction in dynamic scenes with interacting agents, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, 21–26 July 2017, IEEE, 2165–2174, https://doi.org/10.1109/CVPR.2017.233, 2017.
Li, L. L., Yang, B., Liang, M., Zeng, W., Ren, M., Segal, S., and Urtasun, R.: End-to-end contextual perception and prediction with interaction transformer, in: 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, 24 October 2020–24 January 2021, IEEE, 5784–5791, https://doi.org/10.1109/IROS45743.2020.9341392, 2020.
Min, K., Yeon, K., Jo, Y., Sim, G., Sunwoo, M., and Han, M.: Vehicle deceleration prediction based on deep neural network at braking conditions, Int. J. Automot. Techn., 21, 91–102, https://doi.org/10.1007/s12239-020-0010-2, 2020.
Mo, X., Xing, Y., and Lv, C.: Interaction-aware trajectory prediction of connected vehicles using cnn-lstm networks, in: IECON 2020 The 46th Annual Conference of the IEEE Industrial Electronics Society, Singapore, 18–21 October 2020, IEEE, 5057–5062, https://doi.org/10.1109/IECON43393.2020.9255162, 2020.
Mozaffari, S., Al-Jarrah, O. Y., Dianati, M., Jennings, P., and Mouzakitis, A.: Deep learning-based vehicle behavior prediction for autonomous driving applications: A review, IEEE T. Intell. Transp., 23, 33–47, https://doi.org/10.1109/TITS.2020.3012034, 2020.
Neto, F. D. N., de Souza Baptista, C., and Campelo, C. E.: Combining Markov model and prediction by partial matching compression technique for route and destination prediction, Knowl.-Based Syst., 154, 81–92, https://doi.org/10.1016/j.knosys.2018.05.007, 2018.
Phan-Minh, T., Grigore, E. C., Boulton, F. A., Beijbom, O., and Wolff, E. M.: CoverNet: Multimodal behavior prediction using trajectory sets, arXiv [preprint], https://doi.org/10.48550/arXiv.1911.10298, 1 April 2020.
Quintanar, A., Fernández-Llorca, D., Parra, I., Izquierdo, R., and Sotelo, M.: Predicting vehicles trajectories in urban scenarios with transformer networks and augmented information, in: 2021 IEEE Intelligent Vehicles Symposium (IV), Nagoya, Japan, 11–17 July 2021, IEEE, 1051–1056, https://doi.org/10.1109/IV48863.2021.9575242, 2021.
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., and Polosukhin, I.: Attention is all you need, Advances in neural information processing systems, arXiv [preprint], https://doi.org/10.48550/arXiv.1706.03762, 2 August 2023.
Wang, L.-l., Chen, Z.-g., and Wu, J.: Vehicle trajectory prediction algorithm in vehicular network, Wirel. Netw., 25, 2143–2156, https://doi.org/10.1007/s11276-018-1803-3, 2019.
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., and Philip, S. Y.: A comprehensive survey on graph neural networks, IEEE T. Neur. Net. Lear., 32, 4–24, https://doi.org/10.1109/TNNLS.2020.2978386, 2020.
Xie, G., Gao, H., Qian, L., Huang, B., Li, K., and Wang, J.: Vehicle trajectory prediction by integrating physics-and maneuver-based approaches using interactive multiple models, IEEE T. Ind. Electron., 65, 5999–6008, https://doi.org/10.1109/TIE.2017.2782236, 2017.
Xin, L., Wang, P., Chan, C.-Y., Chen, J., Li, S. E., and Cheng, B.: Intention-aware long horizon trajectory prediction of surrounding vehicles using dual LSTM networks, in: 2018 21st International Conference on Intelligent Transportation Systems (ITSC), Maui, HI, USA, 4–7 November 2018, IEEE, 1441–1446, https://doi.org/10.1109/ITSC.2018.8569595, 2018.
Xu, J., Xiao, L., Zhao, D., Nie, Y., and Dai, B.: Trajectory Prediction for Autonomous Driving with Topometric Map, arXiv [preprint], https://doi.org/10.48550/arXiv.2105.03869, 9 May 2021.
Yao, Y., Atkins, E., Johnson-Roberson, M., Vasudevan, R., and Du, X.: BiTraP: Bi-directional pedestrian trajectory prediction with multi-modal goal estimation, IEEE Robotics and Automation Letters, 6, 1463–1470, https://doi.org/10.1109/LRA.2021.3056339, 2021.
Ye, N., Wang, Z.-Q., Malekian, R., Lin, Q., and Wang, R.-C.: A method for driving route predictions based on hidden Markov model, Math. Probl. Eng., 2015, 1–12, https://doi.org/10.1155/2015/824532, 2015.
Yeon, K., Min, K., Shin, J., Sunwoo, M., and Han, M.: Ego-vehicle speed prediction using a long short-term memory based recurrent neural network, Int. J. Automot. Techn., 20, 713–722, https://doi.org/10.1007/s12239-019-0067-y, 2019.
Zeng, W., Liang, M., Liao, R., and Urtasun, R.: LaneRCNN: Distributed representations for graph-centric motion forecasting, in: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic, 27 September–1 October 2021, IEEE, 532–539, https://doi.org/10.1109/IROS51168.2021.9636035, 2021.
Zhao, H., Gao, J., Lan, T., Sun, C., Sapp, B., Varadarajan, B., Shen, Y., Shen, Y., Chai, Y., and Schmid, C.: TNT: Target-driveN Trajectory Prediction, arXiv [preprint], https://doi.org/10.48550/arXiv.2008.08294, 21 August 2020.
Short summary
A trajectory prediction model based on Transfomer has been proposed to address the issue of long-term prediction accuracy in complex traffic environments. Optimizing multi-head attention based on knowledge of the scene context and vehicle position generates interactions between maps and agents, as well as between agents themselves. Its effectiveness has been evaluated on the basis of the outdoor dataset, and higher precision was achieved.
A trajectory prediction model based on Transfomer has been proposed to address the issue of...