Modeling and Quantitative Assessment of Environment Complexity for Autonomous Vehicles
Yulei Wang, Kai Li, Yunfeng Hu, Hong Chen
Abstract
The paper investigates a novel modeling and quantitative assessment approach for environment complexity of autonomous vehicles (AVs), whose purpose is to establish a systematic, logical and quantitative framework for evaluating the intelligence of AVs in complex scenarios. By reducing features of AVs' driving environment, analyzing the properties and relations of environment factors, a topology structure and scheme of fundamental and additional factors is established. Based on an integrated evaluation way of expert evaluation and the analytic hierarchy process (AHP), fundamental and additional environment complexity models are established to realize the subjective and objective evaluation of AVs. The effectiveness of the proposed approach is testified by experimental data and tests.