No abstract

This paper describes an autonomous robot's method of dressing a subject in clothing. Our target task is to dress a person in the sitting pose. We especially focus on the action whereby a robot automatically pulls a pair of trousers up the subject's legs, an action frequently needed in dressing assistance. To avoid injuring the subject's legs, the robot should be able to recognize the state of the manipulated clothing. Therefore, while handling the clothing, the robot is supplied with both visual and tactile sensory information. A dressing failure is detected by the visual sensing of the behaviour of optical flows extracted from the clothing's movements. The effectiveness of the proposed approach is implemented and validated in a life-sized humanoid robot.

This paper describes a method of clothing recognition using dynamic state matching. One purpose of this research is to develop a function that is used to observe the progress of dressing a bottom at a toilet or a bedside. In this dressing, although we just have to do is to put my or others' legs on the bottom. some undesirable situations may occur. For instance, the feet gets hung up on the part of the bottom, and so on.Assuming to use a single camera, we propose a method that distinguishes whether or not a behavior of dressing a bottom is working in order. The input data is an image stream that captures a dressing sequence. Optical flow is calculated from two consecutive images, and then the distribution of the flows is used to distinguish the present clothing state by matching the optical flow with training dataset. The method outputs whether or not the present clothing is in a successful situation. The effectiveness of the proposed method was proven by means of real image data.

No abstract