Bütepage Judith, Ghadirzadeh Ali, Öztimur Karadaǧ Özge, Björkman Mårten, Kragic Danica
Robotics, Perception and Learning, School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden.
Intelligent Robotics Research Group, Aalto University, Espoo, Finland.
Front Robot AI. 2020 Apr 16;7:47. doi: 10.3389/frobt.2020.00047. eCollection 2020.
To coordinate actions with an interaction partner requires a constant exchange of sensorimotor signals. Humans acquire these skills in infancy and early childhood mostly by imitation learning and active engagement with a skilled partner. They require the ability to predict and adapt to one's partner during an interaction. In this work we want to explore these ideas in a human-robot interaction setting in which a robot is required to learn interactive tasks from a combination of observational and kinesthetic learning. To this end, we propose a deep learning framework consisting of a number of components for (1) human and robot motion embedding, (2) motion prediction of the human partner, and (3) generation of robot joint trajectories matching the human motion. As long-term motion prediction methods often suffer from the problem of regression to the mean, our technical contribution here is a novel probabilistic latent variable model which does not predict in joint space but in latent space. To test the proposed method, we collect human-human interaction data and human-robot interaction data of four interactive tasks "hand-shake," "hand-wave," "parachute fist-bump," and "rocket fist-bump." We demonstrate experimentally the importance of predictive and adaptive components as well as low-level abstractions to successfully learn to imitate human behavior in interactive social tasks.
要与交互伙伴协调行动，需要不断交换感觉运动信号。人类在婴儿期和幼儿期主要通过模仿学习以及与熟练伙伴的积极互动来获得这些技能。在互动过程中，他们需要具备预测并适应伙伴的能力。在这项工作中，我们希望在人机交互环境中探索这些理念，其中要求机器人通过观察学习和动觉学习相结合的方式来学习交互任务。为此，我们提出了一个深度学习框架，该框架由多个组件组成，用于（1）人类和机器人运动嵌入，（2）人类伙伴的运动预测，以及（3）生成与人类运动相匹配的机器人关节轨迹。由于长期运动预测方法常常存在均值回归问题，我们在此的技术贡献是一种新颖的概率潜在变量模型，该模型不在关节空间而是在潜在空间中进行预测。为了测试所提出方法，我们收集了“握手”“挥手”“降落伞式碰拳”和“火箭式碰拳”这四项交互任务的人与人交互数据和人机交互数据。我们通过实验证明了预测和自适应组件以及低级抽象对于在交互式社交任务中成功学习模仿人类行为的重要性。
