With a globally aging population, visual impairment is an increasingly pressing problem for our society. Visual disability drastically reduces quality of life and constitutes a large cost to the health care system. Mobility of the visually impaired is one of the most critical aspects affected by this disability, and yet, it relies on low-tech solutions, such as the white cane. Many avoid solutions entirely. In part, reluctance to use these solutions may be explained by their obtrusiveness, a strong deterrent for the adoption of many new devices. Here, we leverage new advancements in artificial intelligence, sensor systems, and soft electroactive materials toward an electronic travel aid with an obstacle detection and avoidance system for the visually impaired. The travel aid incorporates a stereoscopic camera platform, enabling computer vision, and a wearable haptic device that can stimulate discrete locations on the user’s abdomen to signal the presence of surrounding obstacles. The proposed technology could be integrated into commercial backpacks and support belts, thereby guaranteeing a discreet and unobtrusive solution.

Pressure sores are a costly, painful problem for wheelchair users, caused by prolonged periods of mechanical loading. A common location of pressure sores in wheelchair users is the tissue between the ischial tuberosities and the seating surface. The pressure exerted on the tissue, or interface pressure, can be measured using piezoresistive fabric. This work demonstrates the use of the Goertzel algorithm for efficiently acquiring interface pressure data from a fabric assembly consisting of a layer of piezoresistive fabric between two layers of fabric with conducting and non-conducting stripes. The Goertzel algorithm was used to sample sums of sine waves from the conductive columns of the fabric assembly and calculate the amplitudes of each component sine wave corresponding to the local interface pressure. The Goertzel algorithm is more efficient for this application than a fast Fourier transform due to the limited number of calculated frequency bins needed for this application and more freedom in choice of sample size. The algorithm was successfully used to generate two-dimensional, 32 × 32 sensel interface pressure maps once per second. The Goertzel algorithm can be used in tandem with generated sine waves to measure interface pressure from piezoresistive fabric. Low-cost, accurate interface pressure measurements will help lessen the risk of pressure sores in wheelchair users.

In human–robot collaborative tasks, the performance of robot path planning has a direct impact on the robot-to-human hand-over process, or even the collaboration quality. In this work, we propose an evaluation study on multiple robot path planners with different metrics and reveal their pros and cons in representative human–robot collaborative manufacturing contexts. Afterward, based on the proposed metrics, we define a cost function for the dual-arm robot to choose optimized path planning solutions with maximum efficiency for its human partner in human–robot collaboration. We implement the proposed evaluation and optimization approaches to multiple realistic human–robot collaborative manufacturing contexts. Experimental results and evaluations suggest that our approaches are able to provide positive solutions for the robot path planner selection and also open a window for exploring more complicated and general robot path planning applications to human–robot collaborative tasks in smart manufacturing contexts.

Although soft robotic assistive gloves have high potential for restoring functional independence for individuals with motor impairment, their lack of rigid components makes it difficult to obtain accurate position sensing to validate their performance. To track soft device motion, standard practice relies on costly optical motion capture techniques, which have reduced accuracy due to limitations in marker occlusion and device deformation. We propose the Instrumented Hand as a low-cost, open-source measurement tool to serve as a standard solution for acquiring joint-level position and torque measurements from magnetoresistive sensors. Shown in a case study, the Instrumented Hand can be used to validate soft wearable devices and evaluate range of motion (ROM) and torque capabilities.