The long-term goal of this project is to develop personal robots that share a workspace with humans. To achieve the goal of personal robots in homes, the robots must adapt to the humans' living space, not vice-versa. Unfortunately, most human living spaces appear cluttered and unstructured to a robot. Much of this "clutter" is in fact structure, but structure for humans, not robots. The preliminary work proposed in this revised project addresses preliminary work in robot manipulation in the presence of clutter and uncertainty. The demonstrator task is a canonical example of human-robot coexistence: sharing a refrigerator. The robot must be able to extract specified items from a refrigerator that may also be accessed and altered by humans. We will develop the beginnings of a solution based on the following principles: such manipulation tasks can be solved by a hierarchical two-level planning strategy, consisting of a high-level metaplanner making use of low-level primitives; the low-level primitives should include push-grasping, sweeping, and other nonprehensile actions that take advantage of mechanics to manipulate cluttered environments when simple grasp-and-carry is impeded; and uncertainty in the state of the environment and its physical properties should be accounted for at both the metaplanner and primitive levels.
Broader Impacts: Although not all outreach goals can be completed within the revised scope, cluttered tasks are critically important for an aging population of about 35 million people (one in eight) in the United States. Furthermore, graduate students involved in this project will benefit from an ongoing collaboration with TU Munich, a world leader in robot control and personal robotics. TUM, CMU, and Northwestern have a history of graduate student exchange and have agreed to host exchange students under this project. Undergraduates will participate in the research as REU students or in other capacities. Several recent undergraduates working in the labs at CMU and Northwestern have gone on to PhD study in robotics, some with NSF graduate fellowships. Graduate students on this project will participate in internships at the Museum of Science and Industry during its upcoming Robot Revolution exhibit. They will interact with the public and help develop a robot manipulation demonstration for the exhibit main stage. These students will provide technical expertise to the exhibit while benefitting from a valuable outreach experience. Other planned outreach activities include lab tours and talks at local high schools. Both PIs serve as mentors in research programs for underrepresented undergraduate students. These students would have an opportunity to work on state-of-the-art manipulation hardware as part of this project.
Our long-term goal is to develop personal robots that share a workspace with humans. To achieve the goal of personal robots in homes, the robots must adapt to the humans’ living space, not vice-versa. Unfortu- nately, most human living spaces appear cluttered and unstructured to a robot. Much of this "clutter" is in fact structure, but structure for humans. Clutter permeates human environments. Clutter impedes robot manipulators in a manner not affecting more dexterous humans. Clutter also produces uncertainty in several ways—for example, objects may be occluded from view, or other nearby objects may influence the motion of the object that the robot is attempting to manipulate. We have developed a solution based on the following principles: such manipulation tasks can be solved by a hierarchical two-level planning strategy, consisting of a high-level metaplanner making use of low-level primitives; the low-level primitives should include push-grasping, sweeping, and other nonprehensile actions that take advantage of mechanics to manipulate cluttered environments when simple grasp-and-carry is impeded; and uncertainty in the state of the environment and its physical properties should be accounted for at both the metaplanner and primitive levels. Clutter and uncertainty are key barriers preventing assistive robots in the home from per- forming useful manipulation tasks like cleaning and meal preparation. These tasks are critically important for an aging population of about 35 million people (one in eight) in the United States.
