A method of state recognition of dressing clothes based on dynamic state matching

Abstract

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.

“Elbows Out”—Predictive Tracking of Partially Occluded Pose for Robot-Assisted Dressing

“…Although limited to a single axis HMM models that classify dressing have demonstrated >98% accuracy trained on time-series force data of the end effector. Many other scenarios may experience problems with occlusions in real operating conditions such as in t-shirt [17] or trouser [26] dressing tasks.…”

A method of grasp point selection from an item of clothing using hem element relations

“…To overcome the issue, we can find encouraging previous researches: e.g. shape estimation method, [10] dressing-phase estimation, [3] a grasping hand shifting from one hand to the other, [11] and pinch slip motion for unfolding a fabric product. [22] In the future, we believe that these improvements and combination with each other yield a robot system performing clothing manipulation.…”

“…The authors have conducted studies relevant to robotic clothing manipulation, and corresponded to some tasks: clothing detection, [1] classification, [2] and state recognition. [3] This paper describes a method to search for grasp points to unfold a clothing item efficiently.…”

An assistive robot to support dressing - strategies for planning and error handling

“…Yamazaki et al [9] present a leg dressing method with a failure detection and recovery function. This is implemented through a technique which recognizes the state of the dressing clothes based on dynamic state matching presented in [11]. The emphasis of this research was on the determining the state of the manipulated garment by supplying a mix of visual and force sensory information.…”