通过世界模型规划的可控人群生成
Controllable Crowd Generation through World-Model Planning
浏览论文内容
中文总结 AI 辅助
本文提出Ctrl-CWM，一种基于世界模型规划的多智能体可控人群生成方法，通过编码器、演员、评论家和规划器实现运行时控制，在真实感和碰撞指标上优于现有方法，并能适应新用户目标。
中文摘要 AI 辅助
人群模拟在机器人导航、自动驾驶和城市规划中扮演着核心角色。对于这些应用，逼真的模拟要求人群能够适应环境变化和用户目标。然而，现有依赖预定义控制设置的方法在适应新的用户指定目标方面灵活性有限。为了解决这一局限性，我们提出了Ctrl-CWM，一个多智能体可控人群世界模型，它整合了人群生成和运行时控制。我们的关键思想是将世界模型中使用想象未来进行规划的原则应用于人群模拟。为此，Ctrl-CWM由一个学习人体运动动态表示的编码器、一个提议行人位移的演员、一个评估想象人群轨迹的评论家以及一个选择动作的规划器组成。我们首先通过在真实世界行人视频上的轨迹预测来学习人体运动动态，然后冻结编码器以保留这些动态。利用这一表示，演员通过重复的状态更新生成想象的人群轨迹，规划器将评论家的分数与用户成本相结合以选择动作。重复规划推进模拟人群，而额外的用户成本在不重新训练的情况下引入新的控制目标。我们广泛评估了在不同智能体到达条件下的群体生成以及跨越避让和吸引场景的运行时控制。Ctrl-CWM在大多数人群真实感和碰撞指标上优于最先进的方法，并适应模拟过程中引入的用户指定目标来调整人群行为。项目页面可在以下https URL访问。
英文摘要
Crowd simulation plays a central role in robot navigation, autonomous driving, and urban planning. For these applications, realistic simulation requires crowds to adapt their behavior to environmental changes and user objectives. However, existing methods that rely on predefined control settings have limited flexibility in accommodating new user-specified objectives. To address this limitation, we propose Ctrl-CWM, a multi-agent Controllable Crowd World Model that integrates crowd generation and run-time control. Our key idea is to adapt the world-model principle of planning using imagined futures to crowd simulation. To this end, Ctrl-CWM consists of an encoder that learns a representation of human motion dynamics, an actor that proposes pedestrian displacements, a critic that evaluates imagined crowd trajectories, and a planner that selects actions. We first learn human motion dynamics through trajectory prediction on real-world pedestrian videos and then freeze the encoder to preserve them. Using this representation, the actor generates imagined crowd trajectories through repeated state updates, and the planner combines the critic's scores with user costs to select actions. Repeated planning advances the simulated crowd, while additional user costs introduce new control objectives without retraining. We extensively evaluate crowd generation under varied agent arrival conditions and run-time control across avoidance and attraction scenarios. Ctrl-CWM outperforms the state-of-the-art method on most crowd realism and collision metrics, and adapts crowd behaviors to user-specified objectives introduced during simulation. The project page is available at https://jungyu0413.github.io/Ctrl-CWM
发表机构
- Yonsei University（延世大学）
- GIST（光州科学技术院）
机构由 AI 辅助整理，请以论文原文为准。
