"How do you feel the level of intelligence of a car? Sit inside the cab and feel it." "How do you feel the level of intelligence in the cab? Calculate the type and number of sensors in it." These two sentences reflect the most intuitive feelings of consumers about the process of automotive intelligence, and also reflect the important role played by sensors in automotive intelligence. In recent years, the intelligent process of the car continues to advance, the cockpit is one of the representatives of rapid development. The sensor has become one of the key links in the development of intelligent cockpit and even the whole intelligent car industry.

"How do you feel the level of intelligence of a car? Sit inside the cab and feel it." "How do you feel the level of intelligence in the cab? Calculate the type and number of sensors in it." These two sentences reflect the most intuitive feelings of consumers about the process of automotive intelligence, and also reflect the important role played by sensors in automotive intelligence. In recent years, the intelligent process of the car continues to advance, the cockpit is one of the representatives of rapid development. The sensor has become one of the key links in the development of intelligent cockpit and even the whole intelligent car industry.

New Features Continue to Be Integrated, the Rapid Development of Intelligent Cockpit

"In recent years, with the accelerated development of intelligence, electrification, and networking, the car is changing from a single mode of transportation to a third space that integrates leisure, entertainment, office, and other multi-functional functions." Guo Yansheng, the chief engineer of the Electronic Components Industry Development Research Center of the Ministry of Industry and Information Technology, said in an interview with reporters. In this process, as a space to carry and realize a series of intelligent applications and service changes in the car, the importance of an intelligent cockpit in the development of intelligent cars is becoming increasingly apparent.

According to the report released by Harness Capital, the popularity of intelligent cockpits in new car models has been accelerating in recent years. Features such as large central control screen/connected screen, intelligent voice, and OTA upgrade have become the most added and most common part, and have gradually become an important criterion to judge whether the car is equipped with the intelligent cockpit. In addition, as technology upgrades and car manufacturers seek differentiation, there are more new features are incorporated into the intelligent cabin.

Driver monitoring system (DMS) is currently one of the most popular assisted driving features. According to Jerry Chang, technical marketing manager of ST's Asia Pacific Imaging Products Division, the DMS system can acquire images through the camera and detect the driver's driving behavior and physiological state using image recognition technology and algorithm analysis capabilities, including head tracking, eye tracking, driver identification, fatigue driving detection, line of sight tracking/distraction reminders, etc. Research shows that more than 60% of traffic accidents are caused by driver distraction or fatigue driving, with rear-end accidents accounting for 94% of the total. The image sensor is the core component of the DMS system. The continuous improvement of image sensor technology also brings higher safety and scenario applicability for DMS systems and driving.

Human-computer interaction is also a focus of the current development of intelligent cockpit. With the voice interaction technology towards maturity, the cockpit voice interaction has now achieved dual-tone area interaction, which can screen the voice commands of the driver and the rider. In the future, gesture interaction, line of sight interaction, head movement interaction, and other in-cockpit interaction and object perception solutions are beginning to receive more and more attention. Amax Semiconductor and OSRAM Opto Semiconductors marketing manager Tu Shaobei said that perception, understanding, and expression will be the important development direction of future intelligent cabin human-computer interaction systems. Although the human-computer interaction in the car has been changing, the logic is the same, that is, how to make the driver's operation more convenient and safe.

In addition, steering wheel pressure sensing, passenger identification (such as identifying the use of child seats), temperature, humidity, gas sensing, etc., will increasingly be integrated into the car cabin. "Starting from human-machine interaction, as people's requirements for safety and health become higher and higher, more and more new functions will be integrated in the future, with the general direction of improving the safety and comfort of car driving." Zhu Jiaqi, deputy secretary-general of China Sensor and Internet of Things Alliance, pointed out that "after road recognition, automatic cruise and other rapid development, in-vehicle sensing will become another focus of future development landing." Specifically, the interior environment perception content that has been maturely implemented is mainly focused on voice recognition and control, driver fatigue monitoring, automatic air conditioning, and other aspects, such as occupant health signs monitoring, children's emotion monitoring, in-car biological monitoring, and other functions that give users warm care content will be the future point of force.

Growing Market With Double Improvement in Sensor Types and Numbers

Conceptually speaking, the intelligent cockpit is a system with the cockpit domain controller of the car as the core, with the display, HMI (human-computer interaction), visual tracking, and other components together. Because the car cockpit does not involve the chassis control and other aspects, the technical implementation of relatively low difficulty, coupled with the cockpit is the closest contact with the driver and passenger space, function landing more easily perceived by the user, so the intelligent cockpit has become the fastest pace of the current part of the car intelligence.

As a representative, the development of the cockpit system reflects the entire process of automotive intelligence. In this process, sensors will play a key role. "The car can be treated as a platform for the installation of sensors, a variety of physical, chemical, biological sensors with the development of automotive intelligence will be increasingly applied to the car. The degree of car intelligence will become a key factor in determining the performance and function of the car. One of the foundations of intelligence is perception technology." Guo Yansheng pointed out.

In this context, the market for automotive sensors is growing, with IHS data showing that the global market for intelligent cockpits will be about $42 billion in 2021 and is expected to grow to $68.1 billion in 2030. IHSMarkit statistics show that the average single vehicle sensor (including only cameras, millimeter-wave radar, and body sign monitoring sensors) carrying 3.3 in 2020, is expected to grow to 11.3 by 2030.

Zhu Jiaqi stressed that, from the trend, the future of the automotive sensor market will be a rapid rise in momentum. Automotive sensors can be broadly divided into two markets: stock and incremental. On the one hand, the scale of the stock market mainly for body, chassis, and other applications will not be reduced to carry out certain updates; on the other hand, the incremental market mainly for the intelligent cockpit and autonomous driving is also rising very fast. At present, most models of LiDAR have not been installed, millimeter-wave radar only a small number of cars, fatigue driving monitoring sensors are also installed in only a few models. These are all foreseeable incremental markets. "If we judge by the growth of new sensors, it is expected to grow by more than 10% per year." Zhu Jiaqi predicts.

Ouyang Jian, deputy general manager of Stowe Technology, believes that with the development of the intelligent automotive field, effective driver monitoring is an important part of the realization of autonomous driving, and also brings "core" opportunities for domestic CMOS image sensor manufacturers." Guo Yansheng also pointed out that the development of the intelligent automotive field will provide more development opportunities for China's sensor industry. Chinese image sensor manufacturers will have great potential.

Reliability and Stability Are Highlighted, and the Development of Automotive-grade Sensing Has Become the Focus

As the market for automotive sensors expands, more and more companies are cutting into the automotive sensor track while showing some new technology trends. The first is that there will be more and more MEMS and other semiconductor manufacturing processes of advanced sensors to replace traditional types of sensors. Zhu Jiaqi believes that MEMS and advanced sensors with low cost, good reproducibility, and high yield have a great replacement for traditional types of sensors. Of course, Zhu Jiaqi also pointed out that MEMS and advanced sensors will not fully replace traditional types of sensors, silicon-based products still have certain limitations, such as the measurement of exhaust emissions sensors need to support the high-temperature environment of 800 ℃, which is not the characteristics of silicon-based products.

Second, the fusion of multiple sensors in the car has become a mainstream trend. Research institute Wilson in the "automotive intelligent network forward-looking technology report", said that in view of the vehicle outside the environment perception object is very complex, in order to cope with different scenarios and ensure the safety of vehicle driving, the choice of multi-sensor fusion perception program has been the industry consensus. Multi-sensor fusion has obvious advantages in dealing with different scenarios, improving perception accuracy, increasing the perception dimension while enhancing environmental adaptability, and further improving system decision reliability.

Once again, the combination of sensors and artificial intelligence technology is becoming increasingly close, sensing human emotions and behaviors to provide help for safe driving. Chengyi Zhang said AI can process real-time data from cameras, microphones, biosensors, and even radar, and then help the car make decisions. Computer vision is a branch of the artificial intelligence field that allows computers and systems to extract meaningful information from digital images, video, and other visual input data and act or make recommendations based on that information.

Finally, reliability and stability are the most emphasized properties of automotive-grade sensors. Guo Yansheng pointed out that the geography of China is very complex, and reliability and stability are very important for automotive sensors. Cars need to withstand more vibration and shock during movement, which requires automotive sensors to provide long life, high stability, and meet the high reliability of automotive products and other requirements.

Based on these technical trends, Guo Yansheng stressed that in the development of China's automotive sensor industry, the user should be the leader, a collection of system integrators, module hardware, sensor devices, and chip manufacturers, together to build a technology research and development platform for industry, academia, and research. Only then can we establish a complete R & D system in accordance with the industrial chain structure, open up different links in the industry, promote the development of basic technologies and jointly promote the localization of automotive sensors.