A Rule-Based Behaviour Planner for Autonomous Driving

TL;DR

This paper presents a rule-based behaviour planner for autonomous vehicles that uses a two-layer rule engine to select and parameterize driving maneuvers, demonstrated through real-world urban testing.

Contribution

It introduces a novel two-layer rule-based algorithm for autonomous driving decision-making, combining feasibility assessment and behavior reconciliation.

Findings

Successfully implemented in a level-3 autonomous vehicle

Demonstrated effective urban environment performance

Provides a practical approach for real-world autonomous driving

Abstract

Autonomous vehicles require highly sophisticated decision-making to determine their motion. This paper describes how such functionality can be achieved with a practical rule engine learned from expert driving decisions. We propose an algorithm to create and maintain a rule-based behaviour planner, using a two-layer rule-based theory. 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.