Lane-Change Initiation and Planning Approach for Highly Automated Driving on Freeways

TL;DR

This paper introduces a low-complexity, data-driven lane-change planning method for highly automated freeway driving, accurately mimicking human decisions without predefined rules.

Contribution

It presents a novel approach that learns driver preferences from naturalistic data, eliminating the need for engineered objective functions or expert rules.

Findings

Achieves up to 92% accuracy in replicating human lane-change decisions.

Demonstrates successful overtaking maneuver simulation in dynamic environments.

Uses a finite-horizon optimization with safety constraints.

Abstract

Quantifying and encoding occupants' preferences as an objective function for the tactical decision making of autonomous vehicles is a challenging task. This paper presents a low-complexity approach for lane-change initiation and planning to facilitate highly automated driving on freeways. Conditions under which human drivers find different manoeuvres desirable are learned from naturalistic driving data, eliminating the need for an engineered objective function and incorporation of expert knowledge in form of rules. Motion planning is formulated as a finite-horizon optimisation problem with safety constraints. It is shown that the decision model can replicate human drivers' discretionary lane-change decisions with up to 92% accuracy. Further proof of concept simulation of an overtaking manoeuvre is shown, whereby the actions of the simulated vehicle are logged while the dynamic environment evolves as per ground truth data recordings.