Learning Human Navigation Behavior Using Measured Human Trajectories in Crowded Spaces
Learning Human Navigation Behavior Using Measured Human Trajectories in Crowded Spaces
复制标题
DOI：
10.1109/iros45743.2020.9341038
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
M. Fahad;Guang Yang;Yi Guo
中科院分区：
文献类型：
--
作者：
M. Fahad;Guang Yang;Yi Guo
随着人类和移动机器人越来越多地在公共空间共存，它们的近距离要求机器人遵循与人类相似的导航策略进行导航。这可以通过在机器学习框架中直接学习人类演示轨迹来实现。在本文中，我们提出了一种使用基于生成对抗性模仿学习（GAIL）的模仿学习方法来学习人类导航行为的方法，该方法具有直接提取导航策略的能力。具体来说，我们使用在拥挤的公共空间中通过实验收集的大型开放人类轨迹数据集。然后，我们在 3D 机器人模拟器中重新创建这些人体轨迹，并使用机器人上的 LIDAR 传感器生成演示数据，让机器人遵循测量的人体轨迹。然后，我们提出了一种基于 GAIL 的算法，该算法使用 LIDAR 数据生成的占用图作为输入，并输出机器人导航的导航策略。进行了模拟实验，性能评估表明，学习的导航策略生成的轨迹在定性和定量上与人类轨迹相似。与使用分析模型（例如社会力模型）生成人类演示轨迹的现有作品相比，我们的方法直接从内在的人类轨迹中学习，从而表现出更类似于人类的导航行为。
As humans and mobile robots increasingly coexist in public spaces, their close proximity demands that robots navigate following navigation strategies similar to those exhibited by humans. This could be achieved by learning directly from human demonstration trajectories in a machine learning framework. In this paper, we present a method to learn human navigation behaviors using an imitation learning approach based on generative adversarial imitation learning (GAIL), which has the ability of directly extracting navigation policy. Specifically, we use a large open human trajectory dataset that was experimentally collected in a crowded public space. We then recreate these human trajectories in a 3D robotic simulator, and generate demonstration data using a LIDAR sensor onboard a robot with the robot following the measured human trajectories. We then propose a GAIL based algorithm, which uses occupancy maps generated using LIDAR data as the input, and outputs the navigation policy for robot navigation. Simulation experiments are conducted, and performance evaluation shows that the learned navigation policy generates trajectories qualitatively and quantitatively similar to human trajectories. Compared with existing works using analytical models (such as social force model) to generate human demonstration trajectories, our method learns directly from intrinsic human trajectories, thus exhibits more human-like navigation behaviors.