Incentivizing Efficient Equilibria in Traffic Networks With Mixed Autonomy

Traffic congestion has large economic and social costs. The introduction of autonomous vehicles can potentially reduce this by increasing road capacity via vehicle platooning creating an avenue for influencing people's choice routes. We consider a network parallel roads with two modes transportation: 1) human drivers, who will choose the quickest route available to them, 2) ride hailing service, which provides array options, each different prices, users. formalize model flow in mixed autonomy how service users make choices between routes prices latencies. Developing algorithm learn preferences users, we formulate planning optimization that chooses maximize objective. demonstrate benefit proposed scheme comparing results theoretical benchmarks that, show, be efficiently calculated.