Academic Journal of Computing & Information Science, 2026, 9(1); doi: 10.25236/AJCIS.2026.090104.
Xi Chen1
1School of Transportation and Logistics, Southwest Jiaotong University, Chengdu, 610031, China
In highway autonomous driving, data-driven trajectory prediction models suffer from Long-tailed Distributions, where straight-driving samples (>90%) dominate the expected gradient (termed Gradient Dominance), suppressing the learning of rare but critical intentions like lane changes. This leads to Intention Collapse, where models default to conservative straight trajectories. We propose an Intention-Aware Class-Balanced Framework to resolve this. Our approach introduces an Intention-Guided Distribution Rebalancing strategy using inverse-frequency weighting to break the gradient dominance, and an Intention-Conditioned Recurrent Decoder that maps discrete intentions to a continuous latent space for controllable generation. Experiments on the HighD dataset show our method reduces the Average Displacement Error (ADE) in safety-critical lane-changing scenarios by 21% (1.15m → 0.91m) compared to the Standard Encoder-Decoder, demonstrating superior robustness in tail events, and validating the efficacy of class-balancing in regression tasks.
Trajectory Prediction, Long-tailed Distribution, Gradient Dominance, Intention Awareness, Class Balancing
Xi Chen. Intention-Aware Trajectory Prediction with Class-Balanced Learning for Highway Scenarios. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 1: 33-40. https://doi.org/10.25236/AJCIS.2026.090104.
[1] Rudenko, A., Palmieri, L., Herman, M., Kitani, K.M., Gavrila, D.M. and Arras, K.O. (2020) Human Motion Trajectory Prediction: A Survey. The International Journal of Robotics Research, 39, 895-935.
[2] Mozaffari, S., Al-Jarrah, O.Y., Dianati, M., Jennings, P. and Mouzakitis, A. (2020) Deep Learning-Based Vehicle Behavior Prediction for Autonomous Driving Applications: A Review. IEEE Transactions on Intelligent Transportation Systems, 23, 33-47.
[3] Makansi, O., Çiçek, Ö., Marrakchi, Y. and Brox, T. (2021) On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors. IEEE/CVF International Conference on Computer Vision (ICCV), 13147-13157.
[4] Treiber, M., Hennecke, A. and Helbing, D. (2000) Congested Traffic States in Empirical Observations and Microscopic Simulations. Physical Review E, 62, 1805-1824.
[5] Alahi, A., Goel, K., Ramanathan, V., Robicquet, A., Fei-Fei, L. and Savarese, S. (2016) Social LSTM: Human Trajectory Prediction in Crowded Spaces. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 961-971.
[6] Zhou, Z., Ye, L., Wang, J., Wu, K. and Lu, K. (2022) HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 8823-8833.
[7] Nayakanti, N., Al-Rfou, R., Zhou, A., Goel, K., Refaat, K.S. and Sapp, B. (2022) Wayformer: Motion Forecasting via Simple & Efficient Attention Networks. International Conference on Robotics and Automation (ICRA), 2980-2987.
[8] Salzmann, T., Ivanovic, B., Chakravarty, P. and Pavone, M. (2020) Trajectron++: Dynamically-Feasible Trajectory Forecasting with Heterogeneous Data. European Conference on Computer Vision (ECCV), 683-700.
[9] Liang, M., Yang, B., Hu, R., Chen, Y., Liao, R., Feng, S. and Urtasun, R. (2020) Learning Lane Graph Representations for Motion Forecasting. European Conference on Computer Vision (ECCV), 541-556.
[10] Liu, M., et al. (2024) LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2039-2049.
[11] Gupta, A., Johnson, J., Fei-Fei, L., Savarese, S. and Alahi, A. (2018) Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2255-2264.
[12] Bronars, M., Cheng, S. and Xu, D. (2024) Legibility Diffuser: Offline Imitation for Intent Expressive Motion. IEEE Robotics and Automation Letters, 9, 10161-10168.
[13] Zhao, H., Gao, J., Lan, T., Sun, C., Sapp, B., Varadarajan, B., Shen, Y., Shen, Y., Chai, Y., Schmid, C. and Li, C. (2020) TNT: Target-Driven Trajectory Prediction. Conference on Robot Learning (CoRL), 1359-1368.
[14] Varadarajan, B., Hefny, A., Srivastava, A., Kshetramade, K.S., Voelz, J., Covert, J., Kim, E., Hu, C., Bronstein, A. and Anguelov, D. (2022) MultiPath++: Efficient Information Fusion and Trajectory Aggregation for Behavior Prediction. International Conference on Robotics and Automation (ICRA), 7814-7821.
[15] Cui, Y., Jia, M., Lin, T.Y., Song, Y. and Belongie, S. (2019) Class-Balanced Loss Based on Effective Number of Samples. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9268-9277.
[16] Kang, B., Xie, S., Rohrbach, M., Yan, Z., Gordo, A., Feng, J. and Kalantidis, Y. (2020) Decoupling Representation and Classifier for Long-Tailed Recognition. International Conference on Learning Representations (ICLR).
[17] Lin, T.Y., Goyal, P., Girshick, R., He, K. and Dollár, P. (2017) Focal Loss for Dense Object Detection. IEEE International Conference on Computer Vision (ICCV), 2980-2988.
[18] Krajewski, R., Bock, J., Kloeker, L. and Eckstein, L. (2018) The HighD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems. 21st International Conference on Intelligent Transportation Systems (ITSC), 2118-2125.
[19] Deo, N. and Trivedi, M.M. (2018) Convolutional Social Pooling for Vehicle Trajectory Prediction. IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 1549-1558.
[20] Marchetti, F., Becattini, F., Seidenari, L. and Del Bimbo, A. (2020) MANTRA: Memory Augmented Networks for Multiple Trajectory Prediction. IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 7141-7150.
[21] Gu, J., Sun, C. and Zhao, H. (2021) DenseTNT: End-to-End Trajectory Prediction from Dense Goal Sets. IEEE/CVF International Conference on Computer Vision (ICCV), 15303-15312.