Learning to perform everyday tasks, using a complex robot, presents a nested problem. It is nested, because, on the surface, there is a problem of robot control---but within it, there lies a deeper, more challenging problem that demands the control nuances necessary to perform complicated functional tasks. For individuals with limited mobility, such as those with cervical spinal cord injuries, the addition of physical burden is added to this motor learning burden. An explicit training regime can be designed to accelerate and aid the learning process, with the long-term aim to help individuals (injured or uninjured) acquire the skill of complex robot control. However, such training regimes are not well-established nor are the methods of evaluation. In this paper, we gain a baseline understanding of how humans learn to control a 7 degree-of-freedom assistive robotic arm, using a novel high-dimensional interface, in the absence of explicit training. We examine how participants transition between distinct workspace zones to extract their learning possibilities. We gain additional granularity in individual learning, based on how participants spend their time in the workspace, with the robot, and how the time spent is distributed across trials. These analyses highlight the high diversity of learning. Lastly, we provide benefits and opportunities for targeted training regimes that are explicit and heavily favor individualized support.

Individuals who suffer from severe paralysis often lose the capacity to perform fundamental body movements and everyday activities. Empowering these individuals with the ability to operate robotic arms, in high-dimensions, helps to maximize both functional utility and human agency. However, high-dimensional robot teleoperation currently lacks accessibility due to the challenge in capturing high-dimensional control signals from the human, especially in the face of motor impairments. Body-machine interfacing is a viable option that offers the necessary high-dimensional motion capture, and it moreover is noninvasive, affordable, and promotes movement and motor recovery. Nevertheless, to what extent body-machine interfacing is able to scale to high-dimensional robot control, and whether it is feasible for humans to learn, remains an open question. In this exploratory multi-session study, we demonstrate the feasibility of human learning to operate a body-machine interface to control a complex, assistive robotic arm in reaching and Activities of Daily Living tasks. Our results suggest the manner of control space mapping, from interface to robot, to play a critical role in the evolution of human learning.

Human body motions can be captured as a high-dimensional continuous signal using motion sensor technologies. The resulting data can be surprisingly rich in information, even when captured from persons with limited mobility. In this work, we explore the use of limited upper-body motions, captured via motion sensors, as inputs to control a 7 degree-of-freedom assistive robotic arm. It is possible that even dense sensor signals lack the salient information and independence necessary for reliable high-dimensional robot control. As the human learns over time in the context of this limitation, intelligence on the robot can be leveraged to better identify key learning challenges, provide useful feedback, and support individuals until the challenges are managed. In this short paper, we examine two uninjured participants' data from an ongoing study, to extract preliminary results and share insights. We observe opportunities for robot intelligence to step in, including the identification of inconsistencies in time spent across all control dimensions, asymmetries in individual control dimensions, and user progress in learning. Machine reasoning about these situations may facilitate novel interface learning in the future.