We introduce a method for generating realistic pedestrian trajectories and full-body animations that can be controlled to meet user-defined goals. We draw on recent advances in guided diffusion modeling to achieve test-time controllability of trajectories, which is normally only associated with rule-based systems. Our guided diffusion model allows users to constrain trajectories through target waypoints, speed, and specified social groups while accounting for the surrounding environment context. This trajectory diffusion model is integrated with a novel physics-based humanoid controller to form a closed-loop, full-body pedestrian animation system capable of placing large crowds in a simulated environment with varying terrains. We further propose utilizing the value function learned during RL training of the animation controller to guide diffusion to produce trajectories better suited for particular scenarios such as collision avoidance and traversing uneven terrain. Video results are available on the project page at https://nv-tlabs.github.io/trace-pace .

翻译：我们提出了一种生成逼真行人轨迹与全身动画的方法，该方法可被控制以满足用户定义的目标。我们借鉴了引导扩散建模的最新进展，以实现通常在基于规则系统中才具备的测试时轨迹可控性。我们的引导扩散模型允许用户通过目标航点、速度及指定社交群体来约束轨迹，同时考虑周围环境上下文。该轨迹扩散模型与一种新型的基于物理的人形控制器相结合，构成一个闭环的全身行人动画系统，能够将大规模人群放置在具有不同地形的模拟环境中。我们进一步提出利用动画控制器强化学习训练过程中习得的价值函数来引导扩散，从而生成更适用于特定场景（如碰撞规避与不平坦地形穿越）的轨迹。项目页面提供视频结果：https://nv-tlabs.github.io/trace-pace