@proceedings{9,
  keywords = {Autonomous Driving, Behaviour Planning, Expert System, Explainable AI, Rule Engine, Rule Learning, Structured Rule Base},
  author = {Frédéric Bouchard and Sean Sedwards and Krzysztof Czarnecki},
  title = {A Rule-Based Behaviour Planner for Autonomous Driving},
  abstract = {<p>Autonomous vehicles require highly sophisticated decision-making to determine their motion. This paper describes how such functionality can be achieved with a practical <em>rule engine</em> learned from expert driving decisions. We propose an algorithm to create and maintain a rule-based behaviour planner, using a two-layer <em>rule-based theory</em>. The first layer determines a set of feasible parametrized behaviours, given the perceived state of the environment. From these, a resolution function chooses the most conservative high-level maneuver. The second layer then reconciles the parameters into a single behaviour. To demonstrate the practicality of our approach, we report results of its implementation in a level-3 autonomous vehicle and its field test in an urban environment.</p>
},
  year = {2022},
  publisher = {Springer},
  address = {Berlin (virtual)},
}