Abstract-This study aims at robotic clothing assistance as it is yet an open field for robotics despite it is one of the basic and important assistance activities in daily life of elderly as well as disabled people. The clothing assistance is a challenging problem since robots must interact with non-rigid clothes generally represented in a high-dimensional space, and with the assisted person whose posture can vary during the assistance. Thus, the robot is required to manage two difficulties to perform the task of the clothing assistance: 1) handling of non-rigid materials and 2) adaptation of the assisting movements to the assisted person's posture. To overcome these difficulties, we propose to use reinforcement learning with the cloth's state which is low-dimensionally represented in topology coordinates, and with the reward defined in the low-dimensional coordinates. With our developed experimental system, for T-shirt clothing assistance, including an anthropomorphic dual-arm robot and a soft mannequin, we demonstrate the robot quickly learns a suitable arm motion for putting the mannequin's head into a T-shirt.

No abstract

With the advancement of robotics, machine learning, and machine perception, increasingly more robots will enter human environments to assist with daily tasks. However, dynamically-changing human environments requires reactive motion plans. Reactivity can be accomplished through replanning, e.g. model-predictive control, or through a reactive feedback policy that modifies on-going behavior in response to sensory events. In this paper, we investigate how to use machine learning to add reactivity to a previously learned nominal skilled behavior. We approach this by learning a reactive modification term for movement plans represented by nonlinear differential equations. In particular, we use dynamic movement primitives (DMPs) to represent a skill and a neural network to learn a reactive policy from human demonstrations. We use the well explored domain of obstacle avoidance for robot manipulation as a test bed. Our approach demonstrates how a neural network can be combined with physical insights to ensure robust behavior across different obstacle settings and movement durations. Evaluations on an anthropomorphic robotic system demonstrate the effectiveness of our work. * both authors contributed equally to this work