We focus on robot navigation in crowded environments. To navigate safely and efficiently within crowds, robots need models for crowd motion prediction. Building such models is hard due to the high dimensionality of multiagent domains and the challenge of collecting or simulating interaction-rich crowd-robot demonstrations. While there has been important progress on models for offline pedestrian motion forecasting, transferring their performance on real robots is nontrivial due to close interaction settings and novelty effects on users. In this paper, we investigate the utility of a recent state-of-the-art motion prediction model (S-GAN) for crowd navigation tasks. We incorporate this model into a model predictive controller (MPC) and deploy it on a self-balancing robot which we subject to a diverse range of crowd behaviors in the lab. We demonstrate that while S-GAN motion prediction accuracy transfers to the real world, its value is not reflected on navigation performance, measured with respect to safety and efficiency; in fact, the MPC performs indistinguishably even when using a simple constant-velocity prediction model, suggesting that substantial model improvements might be needed to yield significant gains for crowd navigation tasks. Footage from our experiments can be found at https://youtu.be/mzFiXg8KsZ0.
翻译:我们的重点是在拥挤环境中的机器人导航。 要安全有效地在人群中航行,机器人需要人群运动预测模型。 由于多试剂领域的高度维度以及收集或模拟互动丰富人群机器人演示的挑战, 建立这种模型非常困难。 虽然在离线行人运动预测模型上取得了重要进展, 但是在真实机器人上将其性能转换到真实的机器人上并不具有边际作用, 这是因为密切的互动设置和对用户的新影响。 在本文中, 我们调查最近最先进的运动预测模型(S- GAN)在人群导航任务中的效用。 我们把这个模型纳入一个模型预测控制器(MPC)中, 并把它部署在实验室内一个自我平衡的机器人上, 我们受到各种人群行为的影响。 我们证明, 虽然S- GAN运动向真实世界移动预测准确性转移时, 其价值并没有反映在导航性能上, 以安全和效率来衡量; 事实上, MPC 即使在使用简单的持续速度预测模型(S- GAN) 中, 也表现得分不易的。 我们的模型可能需要进行实质性的改进, 才能在 MAZ/FIK8 上发现我们在 MAZ/FI 的导航任务上取得显著的实验。</s>