ITSC 2025 Paper Abstract

Paper FR-LM-T39.4

Hu, Chengxi (Korea Advanced Institute of Science and Technology(KAIST)), Chen, Sikai (University of Wisconsin-Madison), Labi, Samuel (Purdue University), Ding, Honliang (Southwest Jiaotong University), Chung, Hyungchul (Xi'an Jiaotong-Liverpool University), Chen, Tiantian (KAIST)

Supplemental Taxonomy for SAE L3-L4: A Tri-Layer Environmental Grading Framework

Scheduled for presentation during the Regular Session "S39a-Data-Driven Optimization in Intelligent Transportation Systems" (FR-LM-T39), Friday, November 21, 2025, 11:30−11:50, Coolangata 3

2025 IEEE 28th International Conference on Intelligent Transportation Systems (ITSC), November 18-21, 2025, Gold Coast, Australia

This information is tentative and subject to change. Compiled on October 18, 2025

Keywords Infrastructure Requirements for Connected and Automated Vehicles, Autonomous Vehicle Safety and Performance Testing

Abstract

The SAE taxonomy classifies autonomous driving levels based on how driving responsibilities are allocated between human and automated systems. However, it fails to specify critical environmental influences, which result in safety concerns, ambiguous performance expectations, and barriers to commercialization. The purpose of this paper is to fill this gap by introducing a Tri-layer Environmental Grading Framework (TEGF), which is a structured system that evaluates autonomous vehicle adaptability across built, natural, and traffic environments. The TEGF maps environmental favorability against the perception capabilities that are required for safe autonomous operation by quantifying environmental favorability through expert assessments. Our framework focuses specifically on SAE Levels 3 and 4, which we categorize into five tiers of adaptability (A-E). The supplementary classification clarifies operational boundaries and system expectations, thereby guiding technological development, regulatory frameworks, and public understanding of autonomous driving. By incorporating critical environmental dimensions into the SAE taxonomy, TEGF enhances the precision of the SAE taxonomy and provides a solid foundation for developing, testing, and deploying safe and reliable autonomous vehicles.