Trajectory prediction plays a crucial role in improving the safety and reliability of autonomous vehicles, serving as an intermediate link between perception and planning. However, due to the highly dynamic and multimodal nature of the task, accurately predicting the future trajectory of a target vehicle remains a significant challenge. To address these challenges, we propose an Ego vehicle Planning-informed Network (EPN) for multimodal trajectory prediction. Current trajectory prediction methods typically use the historical trajectory and vehicle attributes as inputs, focusing primarily on how historical information influences the future trajectory of the target vehicle. In real-world driving scenarios, however, the future trajectory of a vehicle is influenced not only by its own historical data but also by the behavior of other vehicles on the road. To address this, we incorporate the future planned trajectory of the ego vehicle as an additional input to simulate the mutual influence between the ego vehicle's planned trajectory and the predicted trajectory of the target vehicle. Furthermore, to tackle the challenges of intention ambiguity and large prediction errors often encountered in methods based on driving intentions, we propose a target's endpoint prediction module. This module first predicts the possible endpoints of the target vehicle, then refines these predictions through a correction mechanism, and finally generates a complete multimodal predicted trajectory based on the corrected endpoints. Experimental results demonstrate that, compared to other trajectory prediction methods, EPN achieves an average reduction of 34.9%, 30.7%, and 30.4% in RMSE, ADE, and FDE evaluation metrics on the NGSIM dataset, and an average reduction of 64.6%, 64.5%, and 64.3% in RMSE, ADE, and FDE on the HighD dataset. These results highlight the strong performance of EPN in trajectory prediction.

翻译：轨迹预测在提升自动驾驶车辆的安全性与可靠性方面起着至关重要的作用，是连接感知与规划的中间环节。然而，由于任务本身具有高度动态性和多模态特性，准确预测目标车辆的未来轨迹仍然是一项重大挑战。为应对这些挑战，我们提出了一种用于多模态轨迹预测的融合自车规划信息的网络（EPN）。当前的轨迹预测方法通常使用历史轨迹和车辆属性作为输入，主要关注历史信息如何影响目标车辆的未来轨迹。然而，在实际驾驶场景中，车辆的未来轨迹不仅受其自身历史数据影响，还受到道路上其他车辆行为的影响。为此，我们将自车的未来规划轨迹作为额外输入，以模拟自车规划轨迹与目标车辆预测轨迹之间的相互影响。此外，为应对基于驾驶意图的方法中常见的意图模糊性和预测误差大的挑战，我们提出了一个目标端点预测模块。该模块首先预测目标车辆可能的端点，然后通过校正机制对这些预测进行细化，最后基于校正后的端点生成完整的多模态预测轨迹。实验结果表明，与其他轨迹预测方法相比，EPN在NGSIM数据集上的RMSE、ADE和FDE评估指标平均分别降低了34.9%、30.7%和30.4%，在HighD数据集上的RMSE、ADE和FDE平均分别降低了64.6%、64.5%和64.3%。这些结果突显了EPN在轨迹预测方面的强大性能。