The aim is to improve certain public transportation services, such as ride-hailing and point-to-point shuttle services by mapping zones of affluence in real time and ultimately help predict demand for the shuttles. The research is being conducted at MIT’s Aerospace Controls Lab (ACL).
As part of the project, a fleet of on-demand electric vehicle shuttles will operate on both city roads and campus walkways on the university’s campus in Cambridge, Mass. The vehicles will use lidar sensors and cameras to measure pedestrian flow, helping researchers and drivers route shuttles toward areas with the highest demand to better accommodate riders.
The “predictive” shuttle service will be offered to a group of students and the faculty starting in September.
While sensors and cameras on-board vehicles typically serve anti-collision and ADAS features, here they will gather pedestrian data to estimate the flow of foot traffic, explained Ken Washington, vice president of research and advanced engineering at Ford.
“This helps us develop efficient algorithms that bring together relevant data. It improves mobility-on-demand services and aids ongoing pedestrian detection and mapping efforts for autonomous vehicle research.”
“Through the mobility-on-demand system being developed for MIT’s campus, ACL can investigate new planning and prediction algorithms in a complex, but controlled, environment, while simultaneously providing a testbed framework for researchers and a service to the MIT community,” said professor Jonathan How, ACL director.
Autonomous cars navigate in the dark: lights off
Sensor fusion: A critical step on the road to autonomous vehicles
Future urban mobility: Multi-modal and eco-friendly
Auto supplier ZF buys stake in lidar company
Smart mobility services coming to consumers