发表机构
Moscow Institute of Physics and Technology; Artificial Intelligence Research Institute（莫斯科物理技术学院; 人工智能研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
MC-DeTra通过运动一致性机制，在鸟瞰图上联合优化目标检测与轨迹预测，利用辅助监督信号提升动态智能体预测精度，并公开实现与代码。
AI 中文摘要
用于目标检测和轨迹预测的统一模型旨在融合自动驾驶中的感知与预测，直接在由激光雷达和高清地图栅格化得到的共享鸟瞰图（BEV）图像上优化智能体轨迹。然而，它们在动态、移动智能体上的准确性仍然是任务中最困难的部分，而最强的此类模型DeTra没有公开实现。我们贡献了一个公开发布的DeTra重实现，并附有文档化的近似处理，在其之上构建了MC-DeTra：一系列运动一致性机制，通过两个源自标注的辅助信号——每个智能体观测到的过去运动以及构成其社会环境的周围交通占用情况——添加监督，并加入一个输出间一致性约束，将智能体的预测航向与其预测运动方向对齐。每个提出的损失都仅用于训练且对推理安全：它在训练期间塑造共享的BEV表示，并在测试时移除，不增加推理延迟。在Waymo开放数据集上，在严格的、以检测为条件的预测协议下评估，MC-DeTra改善了动态、社会情境下的轨迹预测，同时保持或提高了检测精度；基于梯度的损失校准分析揭示了辅助目标如何在共享主干上竞争，而我们的消融研究确定了哪些信号贡献最大。我们在https://这个网址发布了代码、配置和评估工具。
英文摘要
Unified models for object detection and trajectory forecasting aim to merge perception and prediction for autonomous driving, refining actor trajectories directly over shared bird's-eye-view (BEV) images rasterized from LiDAR and high-definition maps. Their accuracy on dynamic, moving actors, however, remains the hardest part of the task, and the strongest such model, DeTra, has no public implementation. We contribute an openly released DeTra reimplementation with documented approximations, and on top of it MC-DeTra: a family of motion-consistency mechanisms that add supervision through two annotation-derived auxiliary signals -- each actor's observed past motion and the occupancy of the surrounding traffic that forms its social context -- and one inter-output consistency constraint that aligns an actor's predicted heading with its predicted direction of motion. Every proposed loss is train-only and inference-safe: it shapes the shared BEV representation during training and is removed at test time, adding no inference latency. On the Waymo Open Dataset, evaluated under a strict, detection-conditioned forecasting protocol, MC-DeTra improves dynamic, socially-situated trajectory forecasting while preserving or improving detection accuracy; a gradient-based loss-calibration analysis exposes how the auxiliary objectives compete at the shared backbone, and our ablation identifies which signals contribute most. We release code, configurations, and evaluation tooling at https://github.com/diuzhevVlad/MC-DeTra.
Comments16 pages, 4 figures. Code: https://github.com/diuzhevVlad/MC-DeTra
