Humanlike Decision and Motion Planning for Expressway Lane Changing Based on Artificial Potential Field

Ping Wu,Feng Gao,Keqiang Li

doi:10.1109/access.2022.3141075

Abstract

The autonomous vehicles (AVs) need to share the driving environment with the human driving vehicles (HDVs) on expressway in the future. The non-humanlike lane changing (LC) behavior of AVs can mislead human drivers, which brings potential risks. Stronger humanlike ability requires a more complex algorithm. However, the requirement of the on-board vehicle computation resources limits the humanlike ability of LC algorithms. In this context, considering environmental risks, driver speed requirements and driver focus shifting process, this paper proposes a new type of LC algorithm based on artificial potential field (APF) aiming to improve the humanlike ability. The coupling relationship between the longitudinal and the lateral potential field forces is analyzed theoretically based on environmental risk APF. Based on the relationship, we proposed a conversion mechanism of the driver between the lateral and longitudinal potential field forces to mimic the driver’s speed requirement. Then a target lane selection strategy is designed to trade-off the driver’s speed requirement and safety between multiple lanes. Finally, to mimic the driver’s focus transfer process, the lateral forces of the ego vehicle are analyzed theoretically to further propose a moving virtual lane lines algorithm to build the lateral space varying potential field. The algorithm proposed in this paper is validated by comparing with other LC algorithms in the real traffic scenarios. The results indicate that the proposed algorithm has a better ability to mimic human driver’s LC decision-making and provides a smoother and safer humanlike trajectory.

Highlights

As automatic driving technologies mature gradually, more and more automated vehicles (AVs) begin to drive on the expressway [1], [2]. This makes the expressway traffic scenarios evolve into a mixed one including both AVs and human-driven vehicles (HDVs), and this state will last for a long time because of the limitation of key technologies [3], [4]
In this paper, a new humanlike lane changing (LC) decision-making and motion planning algorithm is proposed based on artificial potential field (APF), which considers environment risk, driver’s speed requirement, and driver’s focus transfer process
driver tolerance force (DTF) is defined to explain the influence of longitudinal force on LC lateral behavior

Summary

INTRODUCTION

As automatic driving technologies mature gradually, more and more automated vehicles (AVs) begin to drive on the expressway [1], [2]. The unified potential field is divided into three parts: environment risk design, driver’s speed requirement and target lane choice for LC decision making and driver’s focus shifting as FIGURE 2 These three key parts in the framework above are described in detail as following: A. The driver’s decision-making process is based on the driver’s comprehensive consideration of the current lateral and longitudinal environmental potential field forces It mainly includes two key points: (1) establishing the mapping relationship between the longitudinal forces and lateral motion and (2) designing the trade-off mechanism of target lane choice between multiple lanes. VIRTUAL SPRING-DAMPING BASED APF DESIGN To design the potential field function, we need to find the key influential factors based on the social force analysis of the interaction process between the EV and the environment with NDD. The results of parameters identification klon and clon are 109.7 N/m and 254.7 N·s/m, respectively

VEHICLE-LANE LINES APF DESIGN

LANE CHANGING DECISION MAKING MECHANISM

MOVING VIRTUAL LANE LINES BASED LC MOTION PLANNING

ALGORITHM VALIDATION AND ANALYSIS

CONCLUSION