Recent advances in motion and behavior planning techniques for software architecture of autonomous vehicles: A state-of-the-art survey

Abstract

Autonomous vehicles (AVs) have now drawn significant attentions in academic and industrial research because of various advantages such as safety improvement, lower energy and fuel consumption, exploitation of road network, reduced traffic congestion and greater mobility. In critical decision making process during motion of an AV, intelligent motion planning takes an important and challenging role for obstacle avoidance, searching for the safest path to follow, generation of suitable behavior and comfortable trajectory generation by optimization while keeping road boundaries and traffic rules as important concerns. An AV should also be able to decide the safest behavior (such as overtaking in case of highway driving) at each moment during driving. The behavior planning techniques anticipate the behaviors of all traffic participants; then it reasonably decides the best and safest behavior for AV. For this highly challenging task, many different motion and behavior planning techniques for AVs have been developed over past few decades. The purpose of this paper is to present an exhaustive and critical review of these existing approaches on motion and behavior planning for AVs in terms of their feasibility, capability in handling dynamic constraints and obstacles, and optimality of motion for comfort. A critical evaluation of the existing behavior planning techniques highlighting their advantages, ability in handling of static and dynamic obstacles, vehicle constraints and limitations in operational environments has also been presented.