Road surfaces in Taiwan, as well as other developed countries, often experience structural failures, such as patches, bumps, longitudinal and lateral cracking, and potholes, which cause discomfort and pose direct safety risks to motorists. The roads with potholes and road deterioration affect ride comfort and pose a direct safety risk, where an impact could initiate suspension structural damage, leading to a tire blowout later, and even departure from one's lane can endanger one's own and passers-by's life. With the rise of self-driving car systems, a new report from Gartner suggests that worldwide net additions of autonomous-ready vehicles could reach 745,705 units in 2023, of which nearly 60% are mainly used by public transport services. In addition to safety requirements, ride comfort is also a crucial issue for the autonomous car.

  • The World's First Taiwan Pavement Defect Image Dataset (TPDID)

The first dataset for Taiwan pavement defects and puddles (Taiwan Pavement Defect Image Dataset, TPDID) has been established, which includes five categories of pavement defects, such as a puddle, pothole, sudden slope, manhole cover, and expansion joint, and the total number of TPDID samples is 89,723.

  • Domestic Intelligent Electronic Suspension System (IES)

Under Professor's Yu-Chen Lin leadership, the self-driving car team consists of six professors from Feng Chia University, the National Taipei University of Technology, and Chung Yuan University as well as working with five automotive industries (Chimei Motor Electronics Co., Ltd., Trillion Green Energy Co., Ltd., Pin Hsiu Technology Co., Ltd., Cybernet Systems Taiwan Co., Ltd., KAIFA Industry Co., Ltd.) to jointly develop a domestic intelligent electronic suspension system. In this research, the pavement defect detection system based on deep learning technology is proposed to sense the road surface conditions. Next, the reinforcement learning scheme using the deep deterministic policy gradient (DDPG) control strategy is utilized to determine optimal control parameters for the active suspension system in real time so as to ensure good ride quality; further, it can reduce the risk of damage to your car, and increase vehicle stability when the vehicle is going through a large puddle. Hence, automatic prediction and adjustment can be effectively implemented by the pre-learning strategy.

The intelligent electronic suspension system has completed the integration of automotive embedded systems and is installed on a commercial vehicle, and the functional testing has also been completed at the NSTC Taiwan CAR Lab, Tainan. The components and controllers of the intelligent electronic suspension system are entirely independently developed in Taiwan. The developed smart electronic suspension system can be demonstrated to not only effectively improve ride comfort and robustness of autonomous car, but also successfully upgrade their technological capabilities of the domestic automotive industry.

台灣首發 自控系林昱成老師「超進化之智能電子避震系統」引領自主尖端感知與控制黑科技

Department of Automatic Control Engineering, Feng Chia University Professor Yu-Chen Lin - Intelligent Electronic Suspension System

台灣首發 自控系林昱成老師「超進化之智能電子避震系統」引領自主尖端感知與控制黑科技

Intelligent Electronic Suspension System


Next There are no next article.

Related News