Predicting the future motion of road participants is crucial for autonomous driving but is extremely challenging due to staggering motion uncertainty. Recently, most motion forecasting methods resort to the goal-based strategy, i.e., predicting endpoints of motion trajectories as conditions to regress the entire trajectories, so that the search space of solution can be reduced. However, accurate goal coordinates are hard to predict and evaluate. In addition, the point representation of the destination limits the utilization of a rich road context, leading to inaccurate prediction results in many cases. Goal area, i.e., the possible destination area, rather than goal coordinate, could provide a more soft constraint for searching potential trajectories by involving more tolerance and guidance. In view of this, we propose a new goal area-based framework, named Goal Area Network (GANet), for motion forecasting, which models goal areas rather than exact goal coordinates as preconditions for trajectory prediction, performing more robustly and accurately. Specifically, we propose a GoICrop (Goal Area of Interest) operator to effectively extract semantic lane features in goal areas and model actors' future interactions, which benefits a lot for future trajectory estimations. GANet ranks the 1st on the leaderboard of Argoverse Challenge among all public literature (till the paper submission), and its source codes will be released.

翻译：准确预测道路参与者的未来运动对自动驾驶至关重要，但由于运动不确定性极为显著，这一任务极具挑战性。近年来，多数运动预测方法采用基于目标的策略，即预测运动轨迹的端点作为条件，进而回归整条轨迹，从而缩小解空间。然而，精确的目标坐标难以预测与评估。此外，将终点表示为点形式限制了丰富道路上下文的利用，导致许多情况下预测结果不准确。与目标坐标不同，目标区域（即可能的终点区域）可通过包含更多容错性与引导性，为搜索潜在轨迹提供更柔性的约束。鉴于此，我们提出一种基于目标区域的新框架——GANet（目标区域网络）用于运动预测。该框架将目标区域而非精确目标坐标作为轨迹预测的前提条件，具有更强的鲁棒性与准确性。具体而言，我们提出GoICrop（目标感兴趣区域）算子，用于高效提取目标区域内的语义车道特征并建模参与者未来交互，这对未来轨迹估计大有裨益。GANet在所有公开文献中（截至论文提交时）位列Argoverse挑战赛排行榜首位，其源代码将开源发布。