EMERGENT HORIZONS: THE CONVERGENCE OF AUTONOMOUS VEHICLES AND ADVANCED LEARNING IN POST-PANDEMIC TRANSPORT RESILIENCE

Abstract

The unprecedented challenges posed by the COVID-19 pandemic to the road and transport sectors necessitated an in-depth exploration of innovative solutions to address disruptions. Through a quantitative approach involving a purposive sampling of professionals from a webinar series, we assessed the pandemic's impact and the potential of emergent technologies, chiefly Connected and Autonomous Vehicles (CAVs) and reinforcement learning. The structured questionnaire, focusing particularly on the pandemic’s ramifications, unveiled considerable operational disturbances across the sector. Notably, the integration of CAVs revealed improvements in traffic management, safety, and environmental sustainability. Additionally, the adoption of reinforcement learning, simulated using Python and the PyTorch framework, demonstrated significant enhancements in ambulance dispatch efficiency. In simulations, the model adeptly reduced response times, especially during high-traffic periods, and showcased improved decision-making accuracy when integrated with CAV capabilities. However, alongside these promising findings, challenges related to the broad-scale implementation of CAVs and potential biases in reinforcement learning models emerged as areas requiring further investigation. In essence, this research delineates a promising technological landscape for the transport sector, emphasizing the balance between innovation and practical, holistic considerations in a post-pandemic world.