Robots for humanity: User-centered design for assistive mobile manipulation

Abstract

The Robots for Humanity project aims to enable people with severe motor impairments to interact with their own bodies and their environment through the use of an assistive mobile manipulator, thereby improving their quality of life. Assistive mobile manipulators (AMMs) are mobile robots that physically manipulate the world in order to provide assistance to people with disabilities. They present an exciting frontier for assistive technology, as they can operate away from the user, have a large dexterous workspace (due to their mobility), and not directly encumber their users. The cornerstone of this project is an ongoing, interactive design process with a quadriplegic user, Henry Evans, and his wife and primary caregiver, Jane Evans. Henry has been enabled, through the use of a PR2 robot, to scratch his own face, shave, fetch a towel from his kitchen, and hand out Halloween candy to trick-ortreating children at a local mall.

An autonomous robotic assistant for drinking

“…Chen et al [3] developed an assistive mobile manipulation robot in close collaboration with a patient suffering from tetraplegia and investigated different scenarios for assistance. These included collecting items from cupboards, distributing halloween candy to children, or scratching and shaving the user.…”

“…Several previous systems demonstrate that patients may carry out useful tasks without the help of a caregiver using a robotic assistant. Depending on the severity of the user's disability, different modes of interaction and control of the robot can be considered, for instance, via a joystick, via head-or eye-tracking, or via brain-machine interfaces (BMIs) [7,4,3]. While some BMI approaches aim at a high-dimensional motor control of robotic devices, in which all aspects of the movement are directly decoded from brain activity, other so-called shared control approaches delegate a part of the control task to the robotic device.…”

Context-Aware Assistive Interfaces for Persons with Severe Motor Disabilities

“…More recently, the "clickable world" framework [4] used a laser pointer to direct a robot assistant in pick-and-place tasks such as, "bring me that object." More recently, our lab has been involved with the Robots for Humanity Project [2], which has a threeyear history working with Henry to develop interfaces between himself and a PR2 robot in his home. A colleague has adapted the "clickable world" framework to take head pose as an input [3].…”

Grasp detection for assistive robotic manipulation

“…Goals are the locations where a robotic gripper could be placed ( grasp poses ) to perform some sort of interaction with the object. In some works, the user specifies the intended goal using interfaces, such as a GUI [2], [3] or a laser pointer [6], or the system predicts the goal based on the users control signals and the object's position. Others use markers or fiducials on objects to facilitate object and grasp pose detection [7] and thus deal only with labeled goals.…”