Q&A: Researchers discuss using AI to encourage carpooling and shared transportation

The study published in Transportation Research Part C found that the HumanLight technology, which uses reinforcement learning to prioritize and reward passengers of high-occupancy vehicles with more green lights, resulted in travel time savings. This created a strong incentive for people to choose transit options over single-occupancy cars. The findings suggest that HumanLight could potentially provide a more democratic and sustainable traffic management solution.

The primary goal of the HumanLight traffic signal control system developed by Berkeley researchers is to maximize the throughput of people, rather than vehicles, at intersections. This is achieved by using reinforcement learning, a type of artificial intelligence, to prioritize and reward passengers of high-occupancy vehicles (HOVs) with more green lights, resulting in travel time savings. This encourages people to choose transit options over single-occupancy cars, promoting a more environmentally friendly and efficient transportation system.