文献类型：期刊文献

英文题名：Interactive Cognition of Self-Driving: A Multi-Dimensional Analysis Model and Implementation

作者：Nan, Ma[1,2]; Li, Kai[3]; Wu, Zhixuan[4]; Genbao, Xu[1,2]; Cheng, Xu[4]; Guo, Cong[5]

第一作者：Nan, Ma

机构：[1] Faculty of Information and Technology, Beijing University of Technology, Beijing, 100124, China; [2] Engineering Research Center of Intelligence Perception and Autonomous Control, Ministry of Education, Beijing University of Technology, Beijing, 100124, China; [3] DONGFENG USHARING TECHNOLOGY CO., LTD., Wuhan, 430056, China; [4] Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing, 100101, China; [5] Beijing University of Technology, Beijing, 100124, China

第一机构：Faculty of Information and Technology, Beijing University of Technology, Beijing, 100124, China

年份：2023

外文期刊名：SSRN

收录：EI(收录号：20230361873)

语种：英文

外文关键词：Autonomous vehicles

摘要：Self-driving vehicles rely closely on interactions with humans, vehicles, and the surrounding environment. However, the interactive analysis of self-driving is impacted by multiple perception sources, heterogeneous data, and complex environments in actual scenes. Due to the above issues, we are often unclear about the behavior of self-driving vehicles, do not understand their decisions, and it is also difficult to achieve synergy with our human intentions. The primary objective of this paper is to underscore the criticality of interactive cognition in complex environments and to conduct a scientific evaluation of machine interactive cognition analysis. We introduce the research significance, composition, and infrastructure of self-driving interactive cognition as well as self-driving interactive cognition inspired by the Wiener model, which realizes embodied intelligence. Then, a multi-dimensional analysis model of self-driving interactive cognition is established based on perceptual information acquisition, multi-channel and cross-modal data registration, attention mechanism, vision understanding, as well as embodied intelligence. Most importantly, we innovatively propose a Nonlinear-CRITIC-TOPSIS-based method to analyze the interactive cognition analyses of different action recognition algorithms efficiently and conduct experimental verification. The analysize of interactive cognition of self-driving can better capture the characteristics of human-like driving. Future self-driving vehicles are bound to demonstrate multi-channel and cross-modal intelligence perception and human-vehicle-friendly interaction, and we are committed to how to better realize the humanoid driving analysis and the embodied intelligence of self-driving vehicles. ? 2023, The Authors. All rights reserved.