TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents
TrafficPredict: Trajectory Prediction for Heterogeneous Traffic-Agents
复制标题
DOI：
--
复制
发表时间：
2018
期刊：
影响因子：
--
通讯作者：
Yuexin Ma;Xinge Zhu;Sibo Zhang;R. Yang;Wenping Wang;Dinesh Manocha
中科院分区：
文献类型：
--
作者：
Yuexin Ma;Xinge Zhu;Sibo Zhang;R. Yang;Wenping Wang;Dinesh Manocha
为了在复杂的城市交通中安全有效地导航，Au-车辆必须对周围的交通代理（车辆、自行车、步行者等）做出负责任的预测。一个具有挑战性和关键性的任务是探索不同的交通智能体的运动模式，并准确预测其未来的轨迹，以帮助自主车辆做出合理的导航决策。为了解决这个问题，我们提出了一种基于长短期内存（LSTM）的实时流量预测算法Traf ficPredict。我们的方法使用实例层来学习实例的移动和交互，并具有类别层来学习属于同一类型的实例的相似性以细化预测。为了评估其性能，我们在一个大城市收集了由不同条件和交通密度组成的轨迹数据集。该数据集包括许多车辆、自行车和行人相互移动的挑战场景。我们评估了Traf ficPredict在新数据集上的性能，并通过与先前的预测方法进行比较，强调了其更高的轨迹预测准确性。
To safely and efficiently navigate in complex urban traffic, au- tonomous vehicles must make responsible predictions in relation to surrounding traffic-agents (vehicles, bicycles, pedes- trians, etc.). A challenging and critical task is to explore the movement patterns of different traffic-agents and predict their future trajectories accurately to help the autonomous vehicle make reasonable navigation decision. To solve this problem, we propose a long short-term memory-based (LSTM-based) realtime traffic prediction algorithm, TrafficPredict. Our ap- proach uses an instance layer to learn instances’ movements and interactions and has a category layer to learn the simi- larities of instances belonging to the same type to refine the prediction. In order to evaluate its performance, we collected trajectory datasets in a large city consisting of varying conditions and traffic densities. The dataset includes many chal- lenging scenarios where vehicles, bicycles, and pedestrians move among one another. We evaluate the performance of TrafficPredict on our new dataset and highlight its higher accuracy for trajectory prediction by comparing with prior pre- diction methods.