With the continuous progress of society, cars are being used by more and more people, and correspondingly, there are more and more traffic accidents. The number of people and property losses caused by traffic accidents every year is staggering. Therefore, vehicle safety issues have attracted great attention. Analysis of a large number of traffic accidents shows that more than 80% of car accidents are caused by unresponsive drivers. More than 65% of vehicle collisions are rear-end collisions, and the rest are side collisions and frontal collisions. Relevant research shows that if the driver can realize the danger of the accident 1 s early and take corresponding measures, 90% of rear-end collisions and 60% of frontal collision accidents can be avoided.
Modern transportation systems and future automated vehicle systems (AVS) require the establishment of intelligent transportation systems (ITS) in order to facilitate traffic monitoring and tracking of vehicles and multi-sensor information fusion. In the future, AVS heterogeneous sensors include video sensors, laser scanners, and radar sensors. The purpose of fusion is to input targets into the path planning and guidance system. The vehicle active anti-collision control system based on multi-sensor information fusion is based on the target information in front of the vehicle received by the multi-sensor and the status information of the vehicle, using multi-source information fusion technology to identify the distance and speed of the vehicle in front of the vehicle And other status information, and to estimate the risk of collision. For example, if the distance between cars is close to the critical distance, an alarm signal is issued to draw the driver's attention;
If the vehicle spacing is less than the critical safety distance, the braking system is activated to avoid collisions.
Obviously, the vehicle active anti-collision control system based on multi-sensor information fusion is an active anti-collision and anti-lock vehicle safety system. It enables optimal control of the three aspects of reaction time, distance and speed. Reducing the driver's burden and making judgment errors will play an important role in improving traffic safety, and can effectively avoid the occurrence of most automobile accidents. At the same time, it also lays a good foundation for increasing the speed of vehicles, increasing road capacity, and realizing automated driving.
2. Composition and function of vehicle active anti-collision control system based on multi-sensor information fusion
Automobile rear-end collision control system is an active safety system. During normal driving, the system is in a non-working state. When the front of the vehicle is very close to the rear of the vehicle in front, the system will issue a rear-end warning. After issuing a warning, if the driver does not take braking deceleration measures, the system automatically activates the emergency braking device to avoid a rear-end accident.
Automobile rear-end collision control system
It has three functions: environmental monitoring function, anti-collision judgment function and vehicle control function.
1. Driving environment monitoring system
The driving environment monitoring system is composed of an environment detection system and a vehicle condition detection system. The environment detection system consists of millimeter-wave radar, lidar, CCD camera, and road sensors capable of judging the condition of the road surface, which measure the distance between the workshop and the direction of the vehicle in front. The vehicle's peripheral sensing technology is the key technology to realize automobile anti-collision. The performance of the sensor will directly affect the performance of the entire system. Only by increasing the reliability of the sensor can it reduce the false alarm rate of the system. It can be seen from Table 1 that the microwave sensor (radar) has a high cost performance, so the microwave sensor that works on millimeter waves is generally selected as the main sensor, and the image and road surface sensors are used as auxiliary sensors to detect obstacles in front of the vehicle. The millimeter-wave radar is installed at the center of the front of the vehicle, and the laser radar is installed on both sides of the millimeter-wave radar. Their main function is to measure the distance between the vehicle and the vehicle in front and the orientation of the vehicle in front, and transmit the measured data to the Collision judgment system; CCD camera obtains image information of vehicles and obstacles ahead, road sensor obtains status information of road surface, vehicle condition detection system detects speed, acceleration and other status information of own vehicle, all information will be sent to anti-collision Judgment system.
2. Anti-collision judgment system
The anti-collision judgment system consists of a target recognition system and a hazard estimation system. The target recognition system fuses the information of sensors such as millimeter wave radar, lidar, and CCD cameras to estimate the distance and relative speed of the nearest vehicle or obstacle in front of the vehicle, and transmits this signal to the hazard estimate system.
The hazard estimation system calculates the "critical workshop distance" based on the road conditions (wet / dry), the vehicle's condition (such as vehicle speed, steering angle, and lateral sway rate), the distance and relative speed from the vehicle in front, and the driver's reaction status The actual measured workshop distance is compared with the critical workshop distance. At a certain moment when the actual measured workshop distance is very close to the critical workshop distance, the alarm sends a warning signal. When the actual measured workshop distance is equal to or less than the critical workshop distance, the brake control system is automatically activated.
3. Vehicle control with automatic brake operating mechanism
The International Highway Commission surveyed the driver's reaction time and concluded that the average value was 0.5 to 3 seconds. If the driver's reaction time is 1.5s, then when the speed of the car is 40Km / h, the distance traveled by the car during the reaction time is 16.7m; when the speed is 80Km / h, the distance traveled will be 33.4m. The reaction time of the automatic braking system is much shorter than that of the driver, and its reaction distance is only 0.5 m.
During operation, the anti-collision judgment system continuously obtains the safe distance through data processing based on the measured distance between the two vehicles, its own vehicle speed, relative vehicle speed and other related information, and compares it with the actual distance measured by the radar. If the measured distance is less than the safety distance, an alarm message will be issued. If the driver has not yet taken measures and the safety distance is less than the limit safety distance, the system will act on the conventional braking system of the car through the actuator to slow down the car. When the limit distance is exceeded, the braking mechanism returns to normal.
3. Millimeter wave radar
At present, the most popular sensing method is a radar system that uses millimeter waves for measurement. Millimeter wave refers to electromagnetic waves with an operating frequency of 30 to 100 GHz and a wavelength of 1 to 10 mm. Millimeter wave radar (mainly 9 4GHz) was originally mainly used for short-range anti-armor weapon systems, its function is to accurately measure the distance and relative speed of the target. Millimeter-wave radar can work around the clock and is not affected by weather conditions, and the harsh climate environment is one of the main causes of traffic accidents. With the emergence and application of GaAs high-frequency devices and monolithic microwave integrated circuits MMIC, the performance of millimeter wave radar has been greatly improved, the cost has also decreased, and the size of the radar can be made very small, which is convenient for automotive Installation. Therefore, millimeter-wave radar has become the first choice for automotive forward-looking radar. In order to find the traffic jam ahead on the highway in time, the detection distance of the millimeter-wave radar for cars must be more than 100m; in order to cover the left and right lane lines, the detection width must be 3.5m; The flyover is also detected, and a detection range of about 3m corresponding to the elevation of the road is required above and below. The main indicators are as follows:
â‘ Antenna: small size, low cost, high performance, but also easy to install and use.
â‘¡Operating frequency: The operating frequency of millimeter wave radar is related to its performance and price. Generally speaking, the higher the frequency, the better the reflection effect of the target, but the penetration of the signal will be weakened, the ranging range will be reduced, and the device cost will increase. There have been reports of radar prototypes and finished products working at 24GHz, 60GHz, 76-77GHz. Now, 76-77GHz millimeter-wave radar has a good price-performance ratio, and this working frequency is currently used abroad. Due to the influence of factors such as devices and costs, China currently prefers to use a 35 GHz operating frequency.
â‘¢ Viewing angle: The viewing angle is the scanning range of the antenna beam, including the azimuth angle and the high and low angles. In order to reduce the false alarm rate, the azimuth is generally selected from 9oC to 12oC, or even greater. The high-low angle is about 3oC.
â‘£ Action distance: 100m ï½ž 150m. For example, the United States stipulates 1 ï½ž 100m, and Europe â€™s stipulates 1 ï½ž 150m. The range determination is based on the principle that the two vehicles will not collide with each other while braking.
â‘¤Measured dynamic range: The radar must have sufficient dynamic range to ensure that it can recognize large and small targets.
â‘¥ Resolution: The resolution of the radial distance can reach 1m. 4. Multi-sensor fusion strategy
Multi-sensor information fusion (MulTIsensor InformaTIon Fusion) or multi-source information fusion is a new technology developed in recent years
Surgery. Information fusion is an effective method to solve the trajectory prediction and tracking of aircraft, missiles and other aircraft, and it is also an intelligent information service.
One of the most promising research directions in the field of science. From a broad perspective, information fusion generally exists in nature. For example, the human cognitive objective world
, Is to obtain information through the senses of sight, hearing, touch, taste and smell, etc., and to obtain cognitive conclusions through the fusion of the brain. From narrow
From the perspective of justice, different sensors obtain different measurement data of the same object, and use a certain algorithm to obtain a comprehensive information, this is the data
Fusion. Data fusion is the simplest and most practical method in information fusion. This method is based on estimation theory, especially Bayes estimation.
Accounting theory, and mainly for the same type of data information. The typical application is to predict the track in target tracking
The data of the device is fused to obtain the best estimation result. Data fusion methods are divided into centralized processing methods and distributed processing methods.
In target tracking research, the distribution processing method has its special importance.
The working environment of the automobile anti-collision system is harsh, and there are many interference factors. It is easy to generate false alarms by using only a single radar sensor to make judgments.
To improve the ability to recognize and estimate targets, it is necessary to introduce multi-sensor information fusion technology. Among them, the sensors include radar sensors, laser scanning
Instrument and video sensor, etc. Comprehensively process the multi-source information provided by multiple sensors of the same type or different types distributed in different locations.
The purpose is to reduce the uncertainty of detection and form a relatively consistent perception description of the system environment in order to obtain an accurate and reliable analysis and judgment
To break the results, thereby improving the system's decision-making ability.
1. Target recognition based on multi-sensor information fusion technology
One of the key technologies of automobile anti-collision system is the target recognition system. Because when the radar emits electromagnetic waves to the front, everything in front of the car
Objects such as trees, highway signs, three-dimensional intersections, bridges, overhead wires, etc. will reflect radar waves. The system must eliminate those false ones,
That is, the signals reflected by objects that do not cause a collision risk can be detected and processed by those real, that is, signals that are indeed at risk of collision.
Work accurately without malfunctions.
In order to eliminate or reduce the occurrence of false alarms, in addition to ensuring certain technical indicators when designing and selecting sensors (such as requiring radar
The angle of view is within a certain range), but also use the information of other sensors for comprehensive analysis and judgment.
2. Distance estimation based on multi-sensor information fusion technology
It can be seen from the above introduction that the distance between the vehicle and the preceding vehicle is an important parameter of the automobile anti-collision system. When calculating the critical safety distance,
It is necessary to estimate the speed and acceleration of the vehicle in front of it, so the accuracy of this distance will directly affect the reliability and accuracy of the anti-collision system
Sensors for measuring distance include laser sensors and millimeter wave sensors, each of which has its own characteristics. Their measuring range,
The adaptability of the environment and the ability to reflect the target are also different, but no matter what kind of sensor is used to ensure that the measurement in the entire measurement range
Accuracy and reliability must use fusion technology, so that according to the complementarity and redundancy of sensor information, appropriate mathematical processing
To get a more accurate distance value.
3. Risk assessment based on multi-sensor information fusion technology
The core of the risk assessment system is to make a comprehensive judgment based on road conditions, the running status of the vehicle, the distance and relative speed from the vehicle in front, and the driver's reaction status, calculate the "critical workshop distance" and compare the actual measured workshop distance with the critical Compare workshop distance.
The determination of the â€œcritical distanceâ€ must consider the influence of various aspects. If the driver â€™s response is more sensitive, or the road condition is better, or the vehicle â€™s braking system works well, the â€œcritical distanceâ€ can take a smaller value; otherwise , "Critical workshop distance" needs to take a larger value to prevent collisions.
The main content of the vehicle active anti-collision control system based on multi-sensor information fusion is to discuss the method of real-time fusion of multi-source information, including real-time target recognition algorithm of real-time fusion of multi-source information, real-time parameters of real-time fusion of multi-source information Estimation, real-time risk assessment of real-time fusion of multi-source information, etc., and apply these methods to engineering practice. The technical indicators that can be achieved by the vehicle active anti-collision control system based on multi-sensor information fusion include the ability to collect data online in real time, and complete the fusion of target recognition and multi-sensor information; the accuracy of target recognition reaches industrial application standards; Carry out anti-collision judgment on the current state and the state of obstacles; in particular, it can provide early warning of dangerous situations, and send an alarm signal to remind the driver when approaching the target. The implementation of vehicle active anti-collision control system based on multi-sensor information fusion can greatly improve the safety of vehicle operation and minimize the occurrence of traffic accidents. In particular, if this method is applied to an automatic vehicle system (AVS), it can bring great improvements to vehicle safety.
Use anti-water connector
Compensation adjustment uses High stability Multi-turn potentiometer
Anti-water rubber washer in the cover prevent the amplifier to be damaged
Prevent Load Cell to be damaged by lightning and Surge signal
Fibos Load Cell sensor amplifier
load cell amplifier, sensor amplifier
Fibos Measurement Technology (Changzhou) Co., Ltd. , https://www.fibos-sensor.com