Real-Time Non-Driving Behavior Recognition Using Deep Learning-Assisted Triboelectric Sensors in Conditionally Automated Driving

Haodong Zhang; Haiqiu Tan; Wuhong WangZhihao LiFacheng ChenXiaobei JiangXiao LuYanqiang HuLizhou LiJie ZhangYihao SiXiaoli WangKlaus Bengler

首页> 外文期刊>Advanced functional materials >Real-Time Non-Driving Behavior Recognition Using Deep Learning-Assisted Triboelectric Sensors in Conditionally Automated Driving

【24h】

Real-Time Non-Driving Behavior Recognition Using Deep Learning-Assisted Triboelectric Sensors in Conditionally Automated Driving

机译：Real-Time Non-Driving Behavior Recognition Using Deep Learning-Assisted Triboelectric Sensors in Conditionally Automated Driving

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Real-time recognition of non-driving behaviors is of great importance inconditionally automated driving, as it determines the takeover time budget,which in turn has a huge impact on the performance of the takeover. Here, anovel real-time non-driving behavior recognition system (RNBRS) integratingself-powered, low-cost, easy-to-manufacture triboelectric sensors, and a deeplearning model is proposed. The structure, working mechanism, and electricalcharacteristics of triboelectric sensors are investigated and analyzed. Throughthe ingenious structural design of single-electrode triboelectric sensors anddriving simulation experiments under conditional automated driving, nondrivingbehaviors are captured in the form of electrical signals. A well-trainedlong short-term memory network model is adopted to recognize the five mosttypical non-driving behaviors, including phone, console touchpad, driving,monitoring driving, and no operation, and test accuracy of 93.5 is achieved.Demonstration of a set of controlled experiments shows that RNBRS enablesvehicles with conditional automation to dynamically adjust takeover timebudget based on driver behavior, therefore significantly improving both safetyand stability of takeover. This study opens new frontiers for the developmentof self-powered electronics and inspires new thoughts on human-machineinteraction and the safety of autonomous vehicles.

著录项

来源
《Advanced functional materials》 |2023年第6期|2210580.1-2210580.12|共12页
作者
Haodong Zhang; Haiqiu Tan; Wuhong WangZhihao LiFacheng ChenXiaobei JiangXiao LuYanqiang HuLizhou LiJie ZhangYihao SiXiaoli WangKlaus Bengler;
展开▼
作者单位

School of Mechanical Engineering Beijing Institute of Technology Beijing 100081, China;

Department of Traffic Management School People's Public Security University of China Beijing 100038, China;

Shanghai Key Laboratory of Intelligent Manufacturing and Robotics School of Mechatronic Engineering and Automation Shanghai University Shanghai 200444, ChinaDepartment of Mechanical Engineering Technical University of Munich 85747, Garching, Germany;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词
conditionally automated driving; deep learning; non-driving behavior recognition; takeover; triboelectric sensors;

Real-Time Non-Driving Behavior Recognition Using Deep Learning-Assisted Triboelectric Sensors in Conditionally Automated Driving

摘要

著录项

相关主题

期刊订阅