NSF Convergence Accelerator: Track H: Mobility Independence through Accelerated Wheelchair Intelligence

Northwestern University, Evanston IL

Investigators

Abstract

The most ubiquitous assistive machine is the power wheelchair. It endows independent mobility to many with motor impairments that result from disease or injury. Yet, there are millions for whom the independent operation of power wheelchairs remains overly burdensome, or even entirely inaccessible. For people with limited movement capabilities, current control interfaces struggle to effectively capture commands from their bodies, and there is a lack of driver assistance options that ensure safe and effective wheelchair driving. The result is a deprivation—for persons with disabilities, and their caregivers—of independence and engagement within the community and workforce. This project proposes to accelerate the accessibility and utility of power wheelchairs by radically changing how control inputs are captured from the human body and transferred to the machine, and by leveraging practical machine intelligence to enhance safety and facilitate independent wheelchair operation. The Phase 1 acceleration will develop an assistive wheelchair prototype, that greatly expands access to independent mobility by those with severe motor impairments—which is significant for both quality of life and participation in the workforce, and by both persons with disabilities and their caregivers. The partners on this convergence accelerator include stakeholders to provide hands-on use and clinical expertise that guides the prototype design, and engineers to realize and later translate that design. The partnership spans non-profits (Team Gleason, Shirley Ryan AbilityLab), academia (Northwestern University), and industry (LUCI, Relay Robotics, Function Engineering). The broadening participation plan engages wheelchair end-users who have ALS. The year 2020 saw the first commercially-available, FDA-registered driver assistance system for power wheelchairs enter the market (LUCI). There exists a gap, however, between their (subtractive-only) assistance and the automation achieved by autonomous robot companies within dynamic human environments. From active steering around obstacles to semi-autonomous navigation, the potential impact for active assistance is tremendous. The assistive wheelchair market is ready for the integration of such capabilities, and persons with degenerative diseases in particular need this greatly expanded scope of assistance without delay. The Phase 1 work will accomplish the following research thrusts, each of which will produce a hardware and software deliverable. • Thrust 1: Bridging the gap in accessible wheelchair control between drivers who can operate a joystick and those who cannot, through the contribution of a novel flexible control interface that conforms to the user and offers fully expressive wheelchair control. • Thrust 2: Modernizing and democratizing the development of future wheelchair input mechanisms, through the contribution of an open-source and digital API for bilateral communication between wheelchair control systems and input devices. • Thrust 3: Advancing safety and independence with wheelchair intelligence, through expanded wheelchair assistance that incorporates commercial-grade robot navigation capabilities into the only commercially-available, FDA-registered driver assistance system for power wheelchairs. By the end of Phase 1, two prototypes that integrate all deliverables will have been built, that consist of: (1) a robotic navigation and safety system, built atop a LUCI power wheelchair, that (2) shares control with the human driver, who provides control commands through (3) the novel flexible interface that communicates with the wheelchair control system via (4) the open-source drive interface. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.