Abstract: An AI-assisted, data driven, real time posture detection system for physiotherapy, fall prevention, and/or frailty assessments. The system uses a pre-trained pose detection model and video images from multiple angles captured by multiple cameras to determine the three-dimensional locations of user joints in real time. In embodiments, the system calculates qualitative metrics (e.g., range of motion, ankle dorsiflexion, Q-angle, hip-knee-ankle alignment, gait speed, etc.) to determine whether the user has suffered or is at risk of an injury (e.g., ACL tear, patellar tendonitis, hip fracture, etc.) and/or whether a physiological condition has worsened or improved over time (e.g., after surgery or physical therapy). In some embodiments, the system constructs a digital twin of the user and displays a visual representation of the digital twin performing idealized movements (e.g.

Abstract: A life-assisting system to enhance the quality of life for people with visual impairment. The system integrates state-of-the-art sensing and sensory stimulation with light detection and ranging (LiDAR), machine learning, and advanced haptic navigation to provide the visually impaired population with a real-time haptic map of the three-dimensional environment and auditory descriptions of objects within that environment. By allowing the visually impaired population to sense objects in the surrounding environment through haptic and auditory feedback, the disclosed system has the potential to promote individual independence, reduce anxiety and stress, facilitate access to educational and employment opportunities, and reduce social and economic gaps. To provide those benefits, the system uses multi-modal learning to convert higher dimensional (e.g., four-dimensional) scene data into lower dimensional (e.g., one-dimensional) auditory data and (e.g., two- or three-dimensional) haptic data.

Abstract: A device for generating forces or motions in accordance with sensor data. The device includes one or more compliant mechanism units and an electromagnetic actuator configured to actuate each compliant mechanism unit. By actuating a compliant mechanism unit using an electromagnetic actuator, the device can generate a force or motion in accordance with received sensor data using hardware components that are much smaller than the servo motors used in existing systems. In various embodiments, the device may actuate one or more compliant mechanism units to control the shape of a haptic meta-surface, activate and deactivate microswitches, open and close microfluidic channels, etc. In various embodiments, the device may actuate one or more compliant mechanism units in accordance with pixel values extracted from light detection and ranging (LiDAR) data, two-dimensional image data, or other sensor data.

Abstract: An image processing system receives a digital image and analyzes the digital image to determine a resolution limit, referred to herein as “feature resolution,” for measuring a metric for features of the image within an acceptable margin of error. Specifically, the system segments a digital image and calculates the error associated with the segmented data when features within a certain range a measured metric (e.g., size range) are removed from the segmented data. This analysis can be repeatedly performed with different cutoff values for the metric until at least a threshold amount of error is reached, thereby indicating a resolution limit at the boundary of an acceptable amount of error.

Abstract: A fall prevention system that monitors the real-time pose of a user and provides alerts in response to a determination that the user may be likely to fall. To accurately determine whether the user is in an unstable pose, the fall prevention system receives video images of the user (and, in some instances, depth information) captured by multiple image capture systems from multiple angles. To process multiple video streams with sufficient speed to provide alerts in near real-time, the fall prevention system uses a pose estimation and stability evaluation process that is optimized to reduce computational expense. For example, the fall prevention process may be realized by a local controller (e.g., worn by the user) that receives video images via a local connection and processes those images locally using pre-trained machine learning models that are uniquely capable of quickly capturing and evaluating the pose of the user.

Abstract: A life-assisting system to enhance the quality of life for people with visual impairment. The system integrates state-of-the-art sensing and sensory stimulation with light detection and ranging (LiDAR), machine learning, and advanced haptic navigation to provide the visually impaired population with a real-time haptic map of the three-dimensional environment and auditory descriptions of objects within that environment. By allowing the visually impaired population to sense objects in the surrounding environment through haptic and auditory feedback, the disclosed system has the potential to promote individual independence, reduce anxiety and stress, facilitate access to educational and employment opportunities, and reduce social and economic gaps. To provide those benefits, the system uses multi-modal learning to convert higher dimensional (e.g., four-dimensional) scene data into lower dimensional (e.g., one-dimensional) auditory data and (e.g., two- or three-dimensional) haptic data.