Motion planning is a computational problem that finds a sequence of valid trajectories, often based on surrounding agents' forecasting, environmental understanding, and historical and future contexts. It can also be viewed as a game in which agents continuously plan their next move according to other agents' intentions and the encountering environment, further achieving their ultimate goals through incremental actions. To model the dynamic planning and interaction process, we propose a novel framework, DeepEMplanner, which takes the stepwise interaction into account for fine-grained behavior learning. The ego vehicle maximizes each step motion to reach its eventual driving outcome based on the stepwise expectation from agents and its upcoming road conditions. On the other hand, the agents also follow the same philosophy to maximize their stepwise behavior under the encountering environment and the expectations from ego and other agents. Our DeepEMplanner models the interactions among ego, agents, and the dynamic environment in an autoregressive manner by interleaving the Expectation and Maximization processes. Further, we design ego-to-agents, ego-to-map, and ego-to-BEV interaction mechanisms with hierarchical dynamic key objects attention to better model the interactions. Experiments on the nuScenes benchmark show that our approach achieves state-of-the-art results.

翻译：运动规划是一个计算问题，旨在根据周边智能体的预测、环境理解以及历史和未来上下文，寻找一系列有效的轨迹。它也可被视为一种博弈，其中智能体根据其他智能体的意图和遭遇的环境不断规划下一步行动，并通过增量动作逐步实现最终目标。为建模动态规划与交互过程，我们提出了一种新颖框架DeepEMplanner，该框架考虑了逐步交互以实现细粒度行为学习。主车基于来自智能体的逐步期望及其即将面临的道路条件，最大化每一步的运动以达成最终驾驶结果。另一方面，智能体也遵循相同的原理，在遭遇的环境以及来自主车和其他智能体的期望下最大化其逐步行为。我们的DeepEMplanner通过交错期望和最大化过程，以自回归方式建模主车、智能体和动态环境之间的交互。此外，我们设计了主车到智能体、主车到地图以及主车到BEV的交互机制，并引入分层动态关键对象注意力以更好地建模交互。在nuScenes基准上的实验表明，我们的方法达到了最先进的结果。