Start Date
1-5-2026 12:00 PM
End Date
1-5-2026 1:00 PM
Description
Mobility limitations in older adults are expected to become increasingly prevalent, along with the larger proportion of the world’s elderly population over the next decades [1]. Among these problems is the difficulty many elderly individuals face when transitioning from a seated to a standing pose. Loss of lower-body strength and balance makes this daily activity near impossible without assistance. To address this motor impairment, solutions were developed. For example, the Elderly Bodily Assistance Robot (E-BAR) provides body-weight support using handles, pulleys, and frames [2]. While these systems demonstrate the feasibility of robotic assistance, they present key limitations. Firstly, mechanical designs lack flexibility and scalability, often requiring significant physical redesign to modify or improve features. Secondly, these systems are not well-suited to individual variability. Differences in physique measurements mean that a single, fixed mechanical configuration cannot efficiently serve all users. The system may perform well on a group of individuals, but fail to provide equal support for others. To address these unmet needs, we propose an AI-driven methodology centered on high-fidelity simulation and data-driven hardware design. Using the MuJoCo physics engine, we simulate complex humanoid behaviors. Micro-movements of joints and the whole body movements during sit-to-stand phases are thoroughly analyzed. We increase limitations on physical strength of body parts to simulate different hardships experienced by elder individuals in performing this physical task. Once the simulation model is completely established and studied as a whole, we aim to determine the precise assistance needed to compensate for the humanoid’s specific strength deficits, which serves the goal of providing adaptability for different user needs. The final product is the design of a physical robot informed by the data gathered from simulations, which will be flexibly engineered to apply the various situations identified, ensuring not only capable of providing necessary support, but the robot will also be optimized for specific physical characteristics of the user. Overall, RISA will be an intelligent and personalized system, giving easier access to mobility assistance for the increasing elderly population.
RISA: Robotic Interface for Sit-to-stand Assistance
Mobility limitations in older adults are expected to become increasingly prevalent, along with the larger proportion of the world’s elderly population over the next decades [1]. Among these problems is the difficulty many elderly individuals face when transitioning from a seated to a standing pose. Loss of lower-body strength and balance makes this daily activity near impossible without assistance. To address this motor impairment, solutions were developed. For example, the Elderly Bodily Assistance Robot (E-BAR) provides body-weight support using handles, pulleys, and frames [2]. While these systems demonstrate the feasibility of robotic assistance, they present key limitations. Firstly, mechanical designs lack flexibility and scalability, often requiring significant physical redesign to modify or improve features. Secondly, these systems are not well-suited to individual variability. Differences in physique measurements mean that a single, fixed mechanical configuration cannot efficiently serve all users. The system may perform well on a group of individuals, but fail to provide equal support for others. To address these unmet needs, we propose an AI-driven methodology centered on high-fidelity simulation and data-driven hardware design. Using the MuJoCo physics engine, we simulate complex humanoid behaviors. Micro-movements of joints and the whole body movements during sit-to-stand phases are thoroughly analyzed. We increase limitations on physical strength of body parts to simulate different hardships experienced by elder individuals in performing this physical task. Once the simulation model is completely established and studied as a whole, we aim to determine the precise assistance needed to compensate for the humanoid’s specific strength deficits, which serves the goal of providing adaptability for different user needs. The final product is the design of a physical robot informed by the data gathered from simulations, which will be flexibly engineered to apply the various situations identified, ensuring not only capable of providing necessary support, but the robot will also be optimized for specific physical characteristics of the user. Overall, RISA will be an intelligent and personalized system, giving easier access to mobility assistance for the increasing elderly population.