Task-centric optimization of configurations for assistive robots

Robots can provide assistance to a human by moving objects to locations around the person’s body. With a well-chosen initial configuration, a robot can better reach locations important to an assistive task despite model error, pose uncertainty, and other sources of variation. However, finding effective configurations can be challenging due to complex geometry, a large number of degrees of freedom, task complexity, and other factors. We present task-centric optimization of robot configurations (TOC), which is an algorithm that finds configurations from which the robot can better reach task-relevant locations and handle task variation. Notably, TOC can return one or two configurations to be used sequentially while assisting with a task. TOC performs computationally demanding optimizations offline to generate a function that rapidly outputs the configurations online based on the robot’s observations. TOC explicitly models the task, environment, and user, and implicitly handles error using representations of robot dexterity. We evaluated TOC with a software simulation of a mobile manipulator (a PR2) providing assistance with 9 activities of daily living to a user in a wheelchair and a robotic bed. TOC had an overall average success rate of 90.6% compared to 50.4%, 43.5%, and 58.9% for three baseline algorithms based on state-of-the-art methods from the literature. We additionally demonstrate how TOC can find configurations for more than one robot and can help with the optimization of environments for assistance.