Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers

Key points

• To address this, we introduce a social component, the marginal cost, to the selfish travel time AV reward.1
• We study AV route choice in mixed-autonomy traffic settings using Multi-Agent Reinforcement Learning (MARL), where AVs learn routing policies through repeated interactions with the traffic environment.1
• Experiments on the real-world networks of Ingolstadt and Provins show that incorporating marginal cost into the AV reward not only limits the increase in HDV travel times and shortens AV travel times relative to selfish AV routing, but also improves overall system performance.1
• For a more scalable approach to social AV routing in mixed-autonomy traffic, we compute the marginal cost only for the AVs whose route choices most affect the traffic system.1

Sources (1)

• [1]Collective Autonomous Vehicle Routing Needs Social Awareness for Coexistence with Human Drivers
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 9, 11:37 AM

  Collective Autonomous Vehicle (AV) route choices in real-world traffic networks can create externalities for Human-Driven Vehicles (HDVs), as routes that benefit AVs may increase travel times for other road users.

  To address this, we introduce a social component, the marginal cost, to the selfish travel time AV reward.

Extractive summary: sentences quoted from the sources.