With the rapid development of machine learning, autonomous driving has become a hot issue, making urgent demands for more intelligent perception and planning systems. Self-driving cars can avoid traffic crashes with precisely predicted future trajectories of surrounding vehicles. In this work, we review and categorize existing learning-based trajectory forecasting methods from perspectives of representation, modeling, and learning. Moreover, we make our implementation of Target-driveN Trajectory Prediction publicly available at https://github.com/Henry1iu/TNT-Trajectory-Predition, demonstrating its outstanding performance whereas its original codes are withheld. Enlightenment is expected for researchers seeking to improve trajectory prediction performance based on the achievement we have made.

翻译：随着机器学习的迅速发展,自主驾驶已成为一个热点问题,对更明智的认知和规划系统提出了紧迫的要求。驾驶汽车可以避免交通事故,精确预测周围车辆的未来轨迹。在这项工作中,我们从代表、建模和学习的角度审查和分类现有的基于学习的轨迹预测方法。此外,我们还在https://github.com/Henry1iu/TNT-Trajectory-Predition上公布我们实施的目标驱动轨迹预测的情况,以显示其出色业绩,而其原始代码则被扣留。预计研究人员可根据我们取得的成就来改进轨迹预测业绩。