Search papers, labs, and topics across Lattice.
This paper introduces a layered risk mapping framework that integrates multiple environmental hazards to enhance the safety of autonomous patient transport in expeditionary medical facilities. By employing a Noisy-OR fusion model, the approach significantly reduces collision rates from over 73% to under 32% and more than doubles obstacle clearance compared to a risk-unaware baseline. The framework was validated through Monte-Carlo evaluations and real-world deployments, showcasing its effectiveness in navigating complex and dynamic environments.
Risk-informed navigation for autonomous patient transport can cut collision rates by over 40%, revolutionizing safety in medical emergencies.
In expeditionary medical facilities, routine patient transport imposes a compounding burden of personal protective equipment consumption, staff diversion, and elevated infection risk that becomes unsustainable under surge conditions. While autonomous wheelchairs could absorb this operational load, the safety-critical nature of patient transit within these highly unstructured and dynamic environments poses complex navigational challenges. To address this, we present a layered risk mapping framework that fuses four heterogeneous environmental hazards (terrain slope, static and dynamic obstacles, and semantic traversability) into a unified probabilistic cost surface via a Noisy-OR fusion model. In a paired Monte-Carlo evaluation, risk-informed fusion reduces collision rates from over 73% to under 32% and more than doubles obstacle clearance relative to a risk-unaware baseline. Additionaly, Noisy-OR achieves the highest clearance to obstacles and the lowest conditional peak risk across all tested hazard densities. We further validate the framework on a commercial powered wheelchair across three representative mission profiles in indoor and outdoor deployments, demonstrating that this architecture successfully meets the planning requirements of this previously unaddressed operational regime.
