We focus on the problem of planning safe and efficient motion for a ballbot (i.e., a dynamically balancing mobile robot), navigating in a crowded environment. The ballbot's design gives rise to human-readable motion which is valuable for crowd navigation. However, dynamic stabilization introduces kinematic constraints that severely limit the ability of the robot to execute aggressive maneuvers, complicating collision avoidance and respect for human personal space. Past works reduce the need for aggressive maneuvering by motivating anticipatory collision avoidance through the use of human motion prediction models. However, multiagent behavior prediction is hard due to the combinatorial structure of the space. Our key insight is that we can accomplish anticipatory multiagent collision avoidance without high-fidelity prediction models if we capture fundamental features of multiagent dynamics. To this end, we build a model predictive control architecture that employs a constant-velocity model of human motion prediction but monitors and proactively adapts to the unfolding homotopy class of crowd-robot dynamics by taking actions that maximize the pairwise winding numbers between the robot and each human agent. This results in robot motion that accomplishes statistically significantly higher clearances from the crowd compared to state-of-the-art baselines while maintaining similar levels of efficiency, across a variety of challenging physical scenarios and crowd simulators.

中文翻译：

---

球机器人预期碰撞避免的拓扑信息模型预测控制

我们专注于为在拥挤环境中导航的球机器人（即动态平衡移动机器人）规划安全有效的运动问题。Ballbot 的设计产生了人类可读的运动，这对于人群导航很有价值。然而，动态稳定引入了运动学约束，严重限制了机器人执行攻击性动作的能力，使避免碰撞和尊重人类个人空间变得复杂。过去的工作通过使用人体运动预测模型来激发预期的碰撞避免，从而减少了对激进机动的需求。然而，由于空间的组合结构，多智能体行为预测很困难。我们的主要见解是，如果我们捕获多智能体动力学的基本特征，我们可以在没有高保真预测模型的情况下实现预期的多智能体碰撞避免。为此，我们构建了一个模型预测控制架构，该架构采用人体运动预测的恒速模型，但通过采取最大化机器人和每个人类代理。与最先进的基线相比，这导致机器人运动在统计上显着更高的人群间隙，同时在各种具有挑战性的物理场景和人群模拟器中保持相似的效率水平。我们构建了一个模型预测控制架构，该架构采用人体运动预测的恒速模型，但通过采取最大化机器人和每个人类代理之间的成对缠绕数的动作来监控并主动适应人群机器人动力学的展开同伦类。与最先进的基线相比，这导致机器人运动在统计上显着更高的人群间隙，同时在各种具有挑战性的物理场景和人群模拟器中保持相似的效率水平。我们构建了一个模型预测控制架构，该架构采用人体运动预测的恒速模型，但通过采取最大化机器人和每个人类代理之间的成对缠绕数的动作来监控并主动适应人群机器人动力学的展开同伦类。与最先进的基线相比，这导致机器人运动在统计上显着更高的人群间隙，同时在各种具有挑战性的物理场景和人群模拟器中保持相似的效率水平。