Risk-Aware Local Traffic Safety Evaluation for Autonomous New Energy Vehicles Based on Virtual Force Modeling

Huilan Li^1,2*Yun Wan²Junning Shang²Xiangyang Xu¹

• ¹Chongqing Jiaotong University, Chongqing, China
• ²Chongqing City Vocational College, Chongqing, China

Ensuring safe driving and effective risk control is vital for the dynamic operation of autonomous new energy vehicles (NEVs), especially under complex traffic conditions. This paper presents a local traffic risk evaluation framework tailored for NEVs, addressing the critical challenge of unifying risk assessment across diverse driving scenarios. Grounded in the principle of least action, the proposed method constructs a virtual force system centered on the autonomous NEV. This system integrates a virtual risk force to capture vehicle-to-vehicle interaction risks, a virtual driving force reflecting the vehicle's motion intention, and a virtual regulatory force to enforce traffic rule compliance. By modeling the action of this force system, a novel metric for local traffic safety is formulated, enabling real-time assessment of driving risks and informing control strategies. The effectiveness of the proposed method is validated through simulations across typical hazardous scenarios including rearend collisions, emergency deceleration, lane changes, and intersection conflicts. Results show that timely risk perception and adaptive control behaviors-such as braking or evasive lane changessubstantially improve the driving safety of NEVs. This work provides a unified and computationally efficient tool for enhancing risk-aware decision-making and control in autonomous NEVs, contributing to their safer deployment and more intelligent traffic integration.