A paper, from the Ergonomics & Safety Program, has been accepted for the 2018 International Conference on Intelligent Robots (IROS 2018) entitled Dynamics Model Learning and Manipulation Planning for Objects in Hospitals Using a Patient Assistant Mobile (PAM) Robot, by Roya Sabbagh Novin, Amir Yazdani, Tucker Hermans, and Andrew Merryweather. This conference will be held in Madrid, Spain on October 1-5, 2018.
One of the most concerning and high-cost problems in hospitals is patients falls. We address this problem by introducing PAM, a patient assistant mobile robot that delivers a mobility aid and helps with fall prevention. Common objects found in indoor environments such as hospitals include objects with legs (i.e. walkers, tables, chairs, equipment stands). For a mobile robot operating in such environments, safely maneuvering these objects without collision is essential. Since providing the robot with dynamic models of all possible legged objects that may exist in such environments is not feasible, learning models that can be used in manipulation planning that estimate an object’s dynamics is useful. We describe a probabilistic method for this by fitting pre-categorized object models learned from minimal force and motion interactions with an object. The multiple options for grasping legs requires a control system comprised by a hybrid of discrete grasping legs and continuous applied forces. To do this, a model of a simple one-wheel point-mass is used. A hybrid MPC-based manipulation planning algorithm was developed to compensate for modeling errors. While the proposed algorithm is developed for a wider range of legged objects, we will focus on the case of a 2-wheel walker in this paper. Simulation and experimental tests show that the obtained dynamic model is sufficiently accurate for safe and collision-free manipulation. When combined with the proposed manipulation planning algorithm, the robot can successfully move the object to a desired position.