Probabilistic Real-Time User Posture Tracking for Personalized Robot-Assisted Dressing

Abstract

Robotic solutions to dressing assistance have the potential to provide tremendous support for elderly and disabled people. However, unexpected user movements may lead to dressing failures or even pose a risk to the user. Tracking such user movements with vision sensors is challenging due to severe visual occlusions created by the robot and clothes. We propose a probabilistic tracking method using Bayesian networks in latent spaces, which fuses robot end-effector positions and force information to enable camera-less and real-time estimation of the user postures during dressing. The latent spaces are created before dressing by modeling the user movements with a Gaussian Process Latent Variable Model, taking the user's movement limitations into account. We introduce a robot-assisted dressing system that combines our tracking method with hierarchical multi-task control to minimize the force between the user and the robot. The experimental results demonstrate the robustness and accuracy of our tracking method. The proposed method enables the Baxter robot to provide personalized dressing assistance in putting on a sleeveless jacket for users with (simulated) upperbody impairments.

Learning Grasping Points for Garment Manipulation in Robot-Assisted Dressing

“…Force information has been considered in [17] to adjust the robot motions to minimize the interaction force between the robot and the user. User movements have been tracked during the dressing process to plan the dressing trajectory in real-time [8,18]. While these different studies have led to promising results of dressing, they usually simplify the setup of their experiments by positioning the robot end-effector, with the garment manually attached on, close to the user's arm.…”

“…Recent studies on robot-assisted dressing usually simplify the setup of the initial robot configuration before dressing sequences by manually attaching the garments on the robot end-effector [3][4][5][6][7][8]. Although these works successfully enable the robots to provide users with dressing assistance in putting on various types of garments, their experiments are usually initiated with the user's arm already in or close to the sleeve opening.…”

Safety Assessment Review of a Dressing Assistance Robot

“…User modeling seems to be a key aspect to address their needs, and to understand their limitations through a personalized interaction, as depicted by some publications ( García-Soler et al, 2018 ). For instance, user modeling studies involving kinematic evaluation tests can determine the user safe workspace in the robot’s movement envelope ( Zhang et al, 2019 ). Similarly, an estimation of the range of physical forces exerted by a modeled arm during a simulated assisted dressing task was performed by Erickson et al (2017) .…”

User Modelling Using Multimodal Information for Personalised Dressing Assistance

“…The robot was able to update the dressing trajectory based on a user-specific movement model whenever the user suddenly moved their arm for a secondary task. Later Zhang [35] combined the hierarchical multi-task control with a probabilistic filtering method to estimate user postures when the user performed unexpected movements such as pulling or pushing. Gao et al [7] used vision data to model the movement space of the human upper-body joints for each user to enable more natural postures of users in the dressing assistance.…”