Emergent Road Rules In Multi-Agent Driving Environments
This work offers a scalable alternative for developing autonomous vehicle behavior by allowing road rules to emerge, which could benefit the entire autonomous driving industry.
This paper explores an alternative to hard-coding road rules for autonomous vehicles, proposing that these rules can emerge as optimal solutions for maximizing traffic flow in multi-agent environments. The authors identify noisy perception and agent spatial density as crucial factors for the emergence of seven social driving behaviors, including obeying traffic signals and following lanes.
For autonomous vehicles to safely share the road with human drivers, autonomous vehicles must abide by specific "road rules" that human drivers have agreed to follow. "Road rules" include rules that drivers are required to follow by law -- such as the requirement that vehicles stop at red lights -- as well as more subtle social rules -- such as the implicit designation of fast lanes on the highway. In this paper, we provide empirical evidence that suggests that -- instead of hard-coding road rules into self-driving algorithms -- a scalable alternative may be to design multi-agent environments in which road rules emerge as optimal solutions to the problem of maximizing traffic flow. We analyze what ingredients in driving environments cause the emergence of these road rules and find that two crucial factors are noisy perception and agents' spatial density. We provide qualitative and quantitative evidence of the emergence of seven social driving behaviors, ranging from obeying traffic signals to following lanes, all of which emerge from training agents to drive quickly to destinations without colliding. Our results add empirical support for the social road rules that countries worldwide have agreed on for safe, efficient driving.