Recently, there has been an increased interest in autonomous vehicles by various automotive companies. Future advanced transportation systems are envisaged to have thousands of autonomous vehicles which detect objects, avoid collisions, and predict accidents, whilst collectively traversing optimal paths through highways and road networks. Such a distributed control approach does not rely on any external control system and leaves behavioural autonomy to the individual vehicles (Martinoli et al. 2002).
In this case, the sensory configurations (number and type of sensors) and controllers (behaviours) of individual vehicles plays a critical role in the safe collective flow of traffic (Zhang et al. 2003). However, current engineering design methods are not appropriate for the design of autonomous vehicles that must elicit a collective behaviour (Zhang et al. 2003). That is, the safe and constant flow of traffic at given speeds for a vast range of roads and highways.
In such cases, traffic systems can be viewed as complex systems where it is difficult, using traditional engineering methods, to ascertain what the exact sensory configuration and controller for each individual vehicle should be in order that an optimal collective behaviour is synthesized. This research investigates the co-adaptation of the sensory configurations and controllers for autonomous cars using neuro-evolution and cooperative co-evolution approaches to automate the autonomous vehicle design process.
Evolved behaviours, using Neuro-Evolution of Augmenting Topologies (NEAT) on various sensor morphologies (configurations).
Huang, A., and Nitschke, G. (2017). Evolving Collective Driving Behaviors. In Proceedings of the International Conference on Autonomous Agents and Multi-agent Systems (AAMAS 2017), to appear, ACM, São Paulo, Brazil. [PDF].
Huang, A., Nitschke, G., and Shorten, D. (2015). Searching for Novelty in Pole Balancing. In Proceedings of the IEEE Congress on Evolutionary Computation (IEEE CEC 2015), pages 1792-1798, IEEE Press, Sendai, Japan. [PDF].