A rise of frail patients in hospitals and high patient-to-nurse ratios can be a significant problem in healthcare. Robots capable of assisting patients in moving and preventing falls can help to ensure the safety of patients. A recent study proposes a risk-aware planning framework. It combines learning-based and model-based methods to predict the trajectory of a patient.
A novel risk-aware cost function is used to evaluate the optimal time and place to provide mobility aid. Even low probability events are penalized if fall risk is high. A simulated patient model that provides patient trajectories and probabilistic predictions are also introduced. The results show that the model successfully recognizes high-risk events and acts accordingly. It outperforms a deterministic baseline. The application of the method could be extended to other types of robots, like home robots.
Planning under uncertainty is a crucial capability for autonomous systems to operate reliably in uncertain and dynamic environments. The concern of patient safety becomes even more critical in healthcare settings where robots interact with humans. In this paper, we propose a novel risk-aware planning framework to minimize the risk of patient falls by providing a patient with an assistive device. Our approach combines learning-based prediction with model-based control to plan for the fall prevention tasks. This provides advantages compared to end-to-end learning methods in which the robot’s performance is limited to specific scenarios, or purely model-based approaches that use relatively simple function approximators and are prone to high modeling errors. We compare two different risk metrics and the combination of them and report the results from various simulated scenarios. The results show that using the proposed cost function, the robot can plan interventions to avoid high fall score events.