An unmanned vehicle control system based on multi-sensor fusion technology

Abstract

The present invention discloses an unmanned vehicle control system based on multi-sensor fusion technology, which relates to the field of unmanned vehicle driving technology, and comprises a perception module, wherein the perception module is used to collect and transmit vehicle surrounding environment information; a map fusion module, wherein the map fusion module comprises a map unit and a positioning fusion unit, wherein the map unit is used to obtain map information near the vehicle through GPS, wherein the positioning fusion unit judges whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section through the map information on the GPS and historical vehicle driving data, and transmits the judgment result; by integrating multiple sensors and advanced decision algorithms, the adaptability of the unmanned vehicle under different environmental conditions is improved, and in particular, under complex or rugged road conditions, the unmanned vehicle can accurately identify and manage multiple traffic participants including pedestrians, bicycles, tricycles, cars and animals.

Description

Technical Field

[0001] The present invention relates to the field of unmanned vehicle driving technology, and more specifically, to an unmanned vehicle control system based on multi-sensor fusion technology. Background Art

[0002] Unmanned vehicles are intelligent vehicles that sense the road environment through on-board sensor systems, automatically plan driving routes, and control vehicles to reach predetermined destinations. They use on-board sensors to sense the vehicle's surroundings and control the vehicle's steering and speed based on the road, vehicle position, and obstacle information obtained through perception, so that the vehicle can travel safely and reliably on the road. They integrate many technologies such as automatic control, architecture, artificial intelligence, and visual computing, and are the product of the high development of computer science, pattern recognition, and intelligent control technology.

[0003] However, in actual use, driverless cars must be able to accurately identify and manage a variety of traffic participants, including pedestrians, bicycles, tricycles, cars, and animals. Especially on complex or rugged roads, the complexity and unpredictability of traffic conditions pose difficulties for driverless cars.

[0004] Moreover, driverless cars are mainly tested and used on designated roads and in designated environments. They have limited space to roam freely, and there may be safety hazards in emergencies and extreme weather. Summary of the invention

[0005] In order to solve the above problems, the present invention provides an unmanned vehicle control system based on multi-sensor fusion technology.

[0006] The present invention provides an unmanned vehicle control system based on multi-sensor fusion technology, comprising a perception module, wherein the perception module is used to collect and transmit vehicle surrounding environment information;

[0007] A map fusion module, the map fusion module includes a map unit and a positioning fusion unit, the map unit is used to obtain map information near the vehicle through GPS, and the positioning fusion unit determines whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section through the map information on the GPS and historical vehicle driving data, and transmits the judgment result;

[0008] A driving control module, the driving control module includes a decision unit and a control unit, the decision unit is used to receive the vehicle surrounding environment information of the perception module and the judgment result of the positioning fusion unit, output a control decision, and transmit it to the control unit;

[0009] The specific steps of the output control decision are as follows:

[0010] When the positioning fusion unit determines through GPS and historical data that the vehicle is on an urban road or a frequently driven road section, the decision unit outputs a high-speed mode decision signal;

[0011] When the positioning fusion unit determines that the vehicle is in a remote area or a path with less historical driving data, the decision unit outputs a safety mode decision signal;

[0012] The vehicle surrounding environment information of the perception module is monitored, and when an emergency signal is monitored, the decision unit outputs an emergency decision signal;

[0013] The control unit is used to adjust the parameters of the vehicle when it is driving, and is also used to switch the control state according to the control decision of the decision unit;

[0014] The control unit includes a first control state and a second control state;

[0015] When the control unit receives the high-speed mode decision signal from the decision unit, switching to the first control state;

[0016] When the control unit receives the safety mode decision signal from the decision unit, switching to the second control state;

[0017] The control unit also includes an emergency control state, which switches to an emergency mode control state when the decision unit outputs an emergency decision signal;

[0018] A communication coordination module is used to realize communication between vehicles and between vehicles and between vehicles and infrastructure, and the communication coordination module adjusts the coordination state according to the control decision of the decision unit.

[0019] Preferably, the specific working mode of the positioning fusion unit is as follows:

[0020] acquiring the real-time position coordinates of the vehicle through a GPS receiver, and retrieving map information near the vehicle from the map data of the map unit using the real-time position coordinates of the vehicle;

[0021] Taking the real-time position of the vehicle as the center, draw a circle with a preset radius to obtain the area around the vehicle;

[0022] Obtaining the number of roads D in the area around the vehicle through the map information of the map unit;

[0023] The road connectivity C is obtained by dividing the number of connected road segments in the area around the vehicle by the number of roads D;

[0024] Obtain the number of vehicles T that passed through the area around the vehicle within a specific time period before the current time point;

[0025] Obtain the average speed V of the area around the vehicle in a specific time period before the current time point;

[0026] Count the number of historical accidents in the area around the vehicle A;

[0027] Based on historical data, a first threshold corresponding to the number of vehicles T, a second threshold corresponding to the average speed V, and a third threshold corresponding to the number of historical accidents A are set;

[0028] Setting a fourth threshold corresponding to the number of roads D and a fifth threshold corresponding to the road connectivity C;

[0029] Based on the number of roads D, road connectivity C, number of vehicles T, average speed V, number of historical accidents A and corresponding thresholds, it is determined whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section.

[0030] Preferably, the specific method of determining whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section is as follows:

[0031] If the number of vehicles T in the area around the vehicle is greater than the first threshold and the average speed V is greater than the second threshold, the urban road possibility is increased by one point;

[0032] If the number of historical accidents A in the area around the vehicle is less than the third threshold, the urban road possibility is increased by one point;

[0033] If the number of roads D in the area around the vehicle is greater than the fourth threshold and the road connectivity C is greater than the fifth threshold, the urban road possibility is increased by one point;

[0034] If the number of vehicles T in the area around the vehicle is less than the first threshold and the average speed V is less than the second threshold, the remote area possibility is increased by one point;

[0035] If the number of historical accidents A in the area around the vehicle is greater than the third threshold, the remote area possibility is increased by one point;

[0036] If the number of roads D in the area around the vehicle is less than the fourth threshold and the road connectivity C is less than the fifth threshold, the remote area possibility is increased by one point;

[0037] If the urban road probability is greater than or equal to three points, it is judged to be an urban road or a frequently driven road section;

[0038] If the remote area probability is greater than or equal to three points, it is judged to be a remote area or a route with less historical driving data.

[0039] Preferably, the specific method of determining whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section also includes:

[0040] If the number of vehicles T in the area around the vehicle is greater than the first threshold and the average speed V is less than the second threshold, the urban road possibility is increased by one point;

[0041] If the number of vehicles T in the area around the vehicle is less than the first threshold and the average speed V is greater than the second threshold, the remote area possibility is increased by one point;

[0042] If the number of roads D in the area around the vehicle is greater than the fourth threshold and the road connectivity C is greater than the fifth threshold, the urban road possibility is increased by one point;

[0043] If the number of roads D in the area around the vehicle is less than a fourth threshold and the road connectivity C is greater than a fifth threshold, the remote road possibility is increased by one point.

[0044] Preferably, the specific steps of the decision unit outputting the emergency decision signal are as follows:

[0045] Acquiring the vehicle surrounding environment information of the perception module, specifically including image information, weather information, road surface status information and traffic rules information around the vehicle;

[0046] If there is an obstacle in the image information of the vehicle's driving path, an emergency decision signal is generated and transmitted;

[0047] The vehicle surrounding environment information also includes a laser radar. When the image information identifies an obstacle, the laser radar information is used to verify whether there is an obstacle.

[0048] If there is an abnormality in the weather information, that is, the local weather forecast issues an early warning signal, or the road condition information is abnormal, a second-class emergency decision signal is generated and transmitted;

[0049] Furthermore, if the local weather forecast issues a warning signal, or monitors heavy rain or strong winds, the road status information is used to verify whether the weather information is correct;

[0050] Based on traffic rules information, three types of emergency decision signals are issued.

[0051] Preferably, when the control unit receives the high-speed mode decision signal from the decision unit, the specific working mode of switching to the first control state is:

[0052] The initial maximum speed limit H and the speed increase J of the vehicle are obtained, and a new speed limit H1 is obtained according to the initial maximum speed limit H plus the speed increase J, so as to meet the demand of high-speed driving by increasing the speed limit;

[0053] According to the formula N1=N*k, the new vehicle acceleration N1 is calculated, where N is the initial acceleration and k is the acceleration adjustment coefficient determined according to the vehicle performance. The vehicle acceleration N1 is adjusted to change the vehicle throttle response curve.

[0054] Preferably, when the control unit receives the safety mode decision signal of the decision unit, the specific working method of switching to the second control state is:

[0055] Obtain the speed reduction value M of the vehicle, and obtain a new speed limit value H2 according to the initial maximum speed limit value H minus the speed reduction value M, thereby reducing the speed limit value;

[0056] The initial information collection frequency G of the perception module is obtained, and a new material frequency G1 is obtained by multiplying the initial information collection frequency G by the adjustment coefficient J. The environmental perception capability is improved by increasing the sampling rate of the sensor data of the perception module.

[0057] Preferably, the specific working method of switching to the emergency mode control state when the decision unit outputs the emergency decision signal is:

[0058] When the control unit receives an emergency decision signal, the control unit immediately controls the vehicle to brake, stop or turn;

[0059] When the control unit receives the second type of emergency decision signal, it obtains a new speed limit H2 according to the initial maximum speed limit H minus the emergency speed reduction value F, and further reduces the speed; it should be noted that in this embodiment, the emergency speed reduction value F can be set by the user or the manufacturer, and in this embodiment, it can be 60km / hour;

[0060] When the control unit receives the three types of emergency decision signals, it reads the speed limit or traffic restriction rules in the traffic rule information to perform corresponding control on the vehicle.

[0061] Preferably, the specific working mode of the communication cooperation module in the initial situation is as follows:

[0062] Configure communication parameters according to the vehicle's current location and driving status;

[0063] Exchange position, speed, and driving direction information with surrounding vehicles, and exchange traffic rules and road condition information with traffic lights and roadside units;

[0064] receiving a control decision from a decision unit, specifically a high-speed mode, a safety mode, or an emergency mode;

[0065] Based on control decisions, the coordinated state with surrounding vehicles and infrastructure is adjusted.

[0066] Preferably, the specific work of the communication coordination module also includes:

[0067] After the decision unit outputs the emergency decision signal, the emergency information is broadcasted;

[0068] It is also used to receive emergency information from other vehicles or infrastructure and take appropriate emergency measures.

[0069] Beneficial effects: By integrating multiple sensors and advanced decision-making algorithms, the adaptability of driverless cars in different environmental conditions is improved, especially in complex or rugged road conditions. Driverless cars can accurately identify and manage multiple traffic participants including pedestrians, bicycles, tricycles, cars and animals; it enables driverless cars to intelligently switch between high-speed mode and safety mode according to real-time environmental changes and traffic conditions, ensuring driving safety in complex traffic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0070] Figure 1 It is a flow chart of the management system of the present invention. DETAILED DESCRIPTION

[0071] Application scenarios: However, in actual use, driverless cars must be able to accurately identify and manage a variety of traffic participants, including pedestrians, bicycles, tricycles, cars, and animals. Especially on complex or rugged roads, the complexity and unpredictability of traffic conditions pose difficulties for driverless cars.

[0072] Moreover, driverless cars are mainly tested and used on designated roads and in designated environments. They have limited space to roam freely, and there may be safety hazards in emergencies and extreme weather.

[0073] like Figure 1 As shown: A driverless vehicle control system based on multi-sensor fusion technology, including a perception module, the perception module is used to collect and transmit vehicle surrounding environment information;

[0074] It should be noted that in this embodiment, real-time collection of vehicle surrounding environment information is achieved by integrating data from multiple sensors such as lidar, camera, millimeter wave radar, GPS, IMU, etc.

[0075] Specific vehicle surrounding environment information includes image information around the vehicle, weather information during vehicle driving, road condition information in the vehicle driving area, traffic rules information in the vehicle driving area, etc.;

[0076] In this embodiment, image information around the vehicle can be collected by a high-definition camera, including road signs, traffic signals, pedestrians, vehicles, etc.;

[0077] Use meteorological sensors to collect weather information, such as rainfall, snow, temperature, humidity, etc., to adapt to driving in different weather conditions;

[0078] Analyze road conditions, such as slippery, potholes, and ice, through road condition sensors (such as wheel speed sensors and accelerometers) and cameras;

[0079] Identify traffic signs and signals through visual sensors, and obtain real-time traffic rules information through V2X communication (communication between vehicles and infrastructure);

[0080] A map fusion module, the map fusion module includes a map unit and a positioning fusion unit, the map unit is used to obtain map information near the vehicle through GPS, and the positioning fusion unit determines whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section through the map information on the GPS and historical vehicle driving data, and transmits the judgment result;

[0081] A driving control module, the driving control module includes a decision unit and a control unit, the decision unit is used to receive the vehicle surrounding environment information of the perception module and the judgment result of the positioning fusion unit, output a control decision, and transmit it to the control unit;

[0082] The specific steps of the output control decision are as follows:

[0083] When the positioning fusion unit determines through GPS and historical data that the vehicle is on an urban road or a frequently driven road section, the decision unit outputs a high-speed mode decision signal;

[0084] When the positioning fusion unit determines that the vehicle is in a remote area or a path with less historical driving data, the decision unit outputs a safety mode decision signal;

[0085] The vehicle surrounding environment information of the perception module is monitored, and when an emergency signal is monitored, the decision unit outputs an emergency decision signal;

[0086] The control unit is used to adjust the parameters of the vehicle when it is driving, and is also used to switch the control state according to the control decision of the decision unit;

[0087] The control unit includes a first control state and a second control state;

[0088] When the control unit receives the high-speed mode decision signal from the decision unit, it switches to the first control state; it should be noted that in the first control state, the control unit adjusts the driving parameters of the vehicle, such as increasing the speed limit, optimizing the acceleration and steering response, to meet the needs of high-speed driving;

[0089] When the control unit receives the safety mode decision signal from the decision unit, it switches to the second control state; it should be noted that in the second control state, the control unit reduces the speed limit of the vehicle and increases the monitoring frequency and sensitivity of the sensor to improve the perception of the surrounding environment;

[0090] The control unit also includes an emergency control state, which switches to an emergency mode control state when the decision unit outputs an emergency decision signal; it should be noted that in the emergency mode, the control unit takes emergency risk avoidance measures, such as emergency braking and emergency obstacle avoidance operations, and may activate hazard warning lights to alert other vehicles and pedestrians;

[0091] A communication coordination module is used to realize communication between vehicles and between vehicles and between vehicles and infrastructure, and the communication coordination module adjusts the coordination state according to the control decision of the decision unit. It should be noted that according to the control decision of the decision unit, the coordination state with other vehicles and infrastructure is adjusted to optimize traffic flow and improve safety. In an emergency, emergency information is broadcast through the vehicle-infrastructure communication system to alert surrounding vehicles and traffic participants.

[0092] As an optional embodiment: the specific working mode of the positioning fusion unit is as follows:

[0093] acquiring the real-time position coordinates of the vehicle through a GPS receiver, and retrieving map information near the vehicle from the map data of the map unit using the real-time position coordinates of the vehicle;

[0094] Taking the real-time position of the vehicle as the center, draw a circle with a preset radius to obtain the area around the vehicle;

[0095] Obtaining the number of roads D in the area around the vehicle through the map information of the map unit;

[0096] The road connectivity C is obtained by dividing the number of connected road segments in the area around the vehicle by the number of roads D;

[0097] The number of vehicles T passing through the area around the vehicle in a characteristic time period before the current time point is obtained; it should be noted that, in this embodiment, the characteristic time period may be a week, a day, or a month, etc.;

[0098] It should also be noted that by using video surveillance data, vehicle monitoring and counting is performed through computer vision technology (such as OpenCV). The specific steps include:

[0099] Extract frames from the video stream and convert each frame image into a grayscale image;

[0100] Apply background subtraction (such as MOG2 algorithm) to separate the foreground, i.e. the moving vehicle;

[0101] Perform morphological processing on the separated foreground, such as erosion, dilation, and closing operations, to remove noise and fill holes within the vehicle contour;

[0102] Monitor the contours in the processed image, calculate the area of ​​the contours, and filter out contours with too small an area to exclude non-vehicle targets;

[0103] By counting the number of vehicles passing through a specific area within a specific time period, we can get T;

[0104] The average speed V of the area around the vehicle in a specific time period before the current time point is obtained; it should be noted that the speed is calculated by analyzing the time difference of the vehicle passing through a specific monitoring area. The specific steps include:

[0105] Installing speed monitoring devices, such as radar guns or laser speed guns, at specific locations on the road, or using video analytics to track the time it takes vehicles to pass specific points;

[0106] Record the timestamp of each vehicle passing through the monitoring area;

[0107] Calculate the time difference for each vehicle to pass through the area and calculate the average speed based on the distance;

[0108] Average the speeds of all vehicles to get V;

[0109] Count the number of historical accidents in the area around the vehicle A; it should be noted that the historical accident data in a specific area is queried from the accident record database of the traffic management department, and the steps include:

[0110] Access to accident record databases provided by traffic management departments;

[0111] Query all accidents recorded in the area based on the vehicle's location and time range;

[0112] The total number of accidents in the statistical query results is A;

[0113] A first threshold corresponding to the number of vehicles T, a second threshold corresponding to the average speed V, and a third threshold corresponding to the number of historical accidents A are set based on historical data; in this embodiment, the average value of historical data of the road section in the city before the current time period can be used as the threshold of the area around the vehicle;

[0114] A fourth threshold corresponding to the number of roads D and a fifth threshold corresponding to the road connectivity C are set; it should be noted that the threshold of the number of roads D can be obtained by multiplying the average number of roads per square kilometer in the city where the vehicle is located by the size of the area around the vehicle, and the threshold of the road connectivity C can be set to a minimum ratio to ensure navigation connectivity, which can be set to 0.8 or 0.9 to ensure that most roads are connected;

[0115] Based on the number of roads D, road connectivity C, number of vehicles T, average speed V, number of historical accidents A and corresponding thresholds, it is determined whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section.

[0116] As an optional embodiment: the specific method of determining whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section is as follows:

[0117] If the number of vehicles T in the area around the vehicle is greater than the first threshold, and the average speed V is greater than the second threshold, the possibility of an urban road is increased by one point; it should be noted that high traffic volume and high speed are typical characteristics of urban roads, indicating that the road section has heavy traffic and vehicles are traveling at high speeds, which meets the characteristics of urban roads;

[0118] If the number of historical accidents A in the area around the vehicle is less than the third threshold, the possibility of urban roads is increased by one point; it should be noted that on the basis of unmanned driving, the accident rate of urban roads is much lower than that of remote areas and unknown paths; a low accident rate may mean that the traffic management of the road section is good and the driver abides by the traffic rules, which is usually a sign of urban roads because urban roads usually have more complete traffic management and monitoring systems;

[0119] If the number of roads D in the area around the vehicle is greater than the fourth threshold and the road connectivity C is greater than the fifth threshold, the possibility of an urban road is increased by one point; it should be noted that urban areas usually have dense road networks and high connectivity between roads, which helps traffic flow and dispersion and is an important feature of urban roads;

[0120] If the number of vehicles T in the area around the vehicle is less than the first threshold and the average speed V is less than the second threshold, the remote area possibility is increased by one point; it should be noted that low traffic and low speed indicate that the traffic on this road section is not busy and the vehicle speed is slow, which is usually a feature of remote areas or areas with underdeveloped transportation;

[0121] If the number of historical accidents A in the area around the vehicle is greater than the third threshold, the remote area possibility is increased by one point; it should be noted that a high accident rate may mean that the traffic management in the area is not perfect and the driver may not obey the traffic rules, which is more common in remote areas or routes with less historical driving data;

[0122] If the number of roads D in the area around the vehicle is less than the fourth threshold and the road connectivity C is less than the fifth threshold, the remote area possibility is increased by one point; it should be noted that the road network in remote areas is usually sparse and the connectivity between roads is low, which restricts traffic flow and is an important feature of remote areas;

[0123] It should also be noted that the case of being equal is not considered because the number of samples is small. If the number of roads D, road connectivity C, number of vehicles T, average speed V, and number of historical accidents A are equal to the corresponding thresholds, then it is judged as being greater than;

[0124] If the urban road probability is greater than or equal to three points, it is judged to be an urban road or a frequently driven road section;

[0125] If the remote area probability is greater than or equal to three points, it is judged to be a remote area or a route with less historical driving data.

[0126] As an optional embodiment: the specific method of determining whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven road section also includes:

[0127] If the number of vehicles T in the area around the vehicle is greater than the first threshold, and the average speed V is less than the second threshold, the possibility of urban roads is increased by one point; it should be noted that this situation may indicate that the road section is busy, but the vehicle speed is slow, which may be due to traffic congestion or road conditions. This may mean that the road section is an urban road, but there may be traffic problems;

[0128] If the number of vehicles T in the area around the vehicle is less than the first threshold and the average speed V is greater than the second threshold, the remote area possibility is increased by one point; it should be noted that this situation may indicate that the traffic on the road section is not busy, but the vehicle can travel at high speed, perhaps because the road is empty or the road conditions are good. This may mean that the road section is a remote road, but the traffic volume is not heavy;

[0129] If the number of roads D in the area around the vehicle is greater than the fourth threshold and the road connectivity C is the fifth threshold, the possibility of an urban road is increased by one point; it should be noted that this situation may indicate that there are a large number of roads, but the connectivity is average, which is a characteristic of urban roads. Connectivity is not sufficient to fully determine the type of road segment;

[0130] If the number of roads D in the area around the vehicle is less than the fourth threshold and the road connectivity C is greater than the fifth threshold, the remote road possibility is increased by one point. This situation may indicate that although the number of roads is small, the connectivity is good, which may be a feature of roads in remote areas, but good connectivity may mean that there is a certain amount of traffic flow in the area;

[0131] It should also be noted that the above scores are used to judge special circumstances.

[0132] As an optional embodiment: the specific steps of the decision unit outputting the emergency decision signal are as follows:

[0133] Acquiring the vehicle surrounding environment information of the perception module, specifically including image information, weather information, road surface status information and traffic rules information around the vehicle;

[0134] If there is an obstacle in the image information of the vehicle's driving path, an emergency decision signal is generated and transmitted; it should be noted that such a situation requires the vehicle to stop and brake or turn immediately;

[0135] The vehicle surrounding environment information also includes a laser radar. When the image information identifies an obstacle, the laser radar information is used to verify whether there is an obstacle.

[0136] For example, LiDAR confirms the three-dimensional position of an obstacle through point cloud data, while millimeter-wave radar verifies the speed of the obstacle through the Doppler effect;

[0137] If there is an abnormality in the weather information, that is, the local weather forecast issues a warning signal, or the road condition information is abnormal, a second-class emergency decision signal is generated and transmitted; it should be noted that such a situation will affect the driving of the vehicle, and the second-class emergency decision signal is used to adjust the vehicle's driving speed and other parameters;

[0138] Furthermore, if the local weather forecast issues a warning signal, or monitors heavy rain or strong winds, the road status information is used to verify whether the weather information is correct;

[0139] It should be noted that for weather information and road condition information, the data of meteorological sensors and road condition sensors (such as wheel speed sensors and accelerometers) will be fused to determine whether there is an abnormality. For example, if the meteorological sensor detects heavy rain and the road sensor detects that the road surface is slippery, this information will be fused to generate a second type of emergency decision signal and transmitted;

[0140] According to the traffic rules information, three types of emergency decision signals are issued. It should be noted that according to the local traffic rules, the speed limit and other data of the vehicle are changed to avoid speeding.

[0141] As an optional embodiment: when the control unit receives the high-speed mode decision signal of the decision unit, the specific working method of switching to the first control state is:

[0142] The initial maximum speed limit H and the speed increase J of the vehicle are obtained, and a new speed limit H1 is obtained by adding the initial maximum speed limit H to the speed increase J, and the speed limit is increased to meet the needs of high-speed driving; it should be noted that the unmanned driving of the vehicle needs to set a maximum speed limit so that the speed of the vehicle does not exceed this limit. In the first control state, the maximum speed limit of the vehicle can be appropriately increased. In this embodiment, the initial maximum speed limit H is obtained by the vehicle manufacturer's setting, which can be 100 km / hour, and the speed increase J can be set according to the vehicle user, and the maximum value does not exceed 40 km / hour;

[0143] According to the formula N1=N*k, the new vehicle acceleration N1 is calculated, where N is the initial acceleration and k is the acceleration adjustment coefficient determined according to the vehicle performance. The vehicle acceleration N1 is adjusted to change the vehicle throttle response curve. It should be noted that in this embodiment, the initial acceleration and the acceleration adjustment coefficient can be obtained according to the vehicle manufacturer's settings;

[0144] It should be noted that by adjusting the speed limit and acceleration, the vehicle can better adapt to different road conditions, such as highways and urban roads; Optimize throttle response: Adjusting the acceleration can change the throttle response curve, making the vehicle acceleration smoother and improving driving comfort; Setting a maximum speed limit can prevent the vehicle from speeding and reduce traffic accidents caused by speeding;

[0145] In situations where rapid acceleration or deceleration is required, adjusting the acceleration can improve the vehicle's response time, thereby improving safety.

[0146] As an optional embodiment: when the control unit receives the safety mode decision signal of the decision unit, the specific working method of switching to the second control state is:

[0147] Obtain the speed reduction value M of the vehicle, and obtain a new speed limit value H2 according to the initial maximum speed limit value H minus the speed reduction value M, thereby reducing the speed limit value;

[0148] The initial information acquisition frequency G of the perception module is obtained, and a new material frequency G1 is obtained by multiplying the initial information acquisition frequency G by the adjustment coefficient J. The environmental perception capability is improved by increasing the sampling rate of the sensor data of the perception module. It should be noted that, in this embodiment, the speed reduction value M of the vehicle can be set by the manufacturer or adjusted by the user. The adjustment coefficient J can be 1.203 in this embodiment. The specific value is set according to the manufacturer of the vehicle, but the value range is between 1 and 2. The purpose is to increase the monitoring frequency of the sensor in the perception module.

[0149] As an optional embodiment: the specific working method of switching to the emergency mode control state when the decision unit outputs the emergency decision signal is:

[0150] When the control unit receives an emergency decision signal, the control unit immediately controls the vehicle to brake, stop or turn;

[0151] When the control unit receives the second type of emergency decision signal, it obtains a new speed limit H2 according to the initial maximum speed limit H minus the emergency speed reduction value F, and further reduces the speed; it should be noted that in this embodiment, the emergency speed reduction value F can be set by the user or the manufacturer, and in this embodiment, it can be 60km / hour;

[0152] When the control unit receives the three types of emergency decision signals, it reads the speed limit or traffic restriction rules in the traffic rule information to perform corresponding control on the vehicle.

[0153] It should be noted that through this hierarchical response mechanism of emergency decision signals, driverless vehicles can respond to various emergency situations more accurately and quickly, thereby significantly improving driving safety and efficiency. Specifically, when an obstacle that directly threatens driving safety is detected, the first type of emergency decision signal ensures that the vehicle can immediately take measures such as braking to stop or turning to avoid obstacles to effectively avoid collisions. In the face of severe weather or road conditions, the second type of emergency decision signal enhances the stability and controllability of the vehicle by reducing the speed and reducing the risk of accidents. The third type of emergency decision signal ensures that the vehicle strictly abides by traffic rules, avoids penalties for speeding or violating traffic restrictions, and ensures driving safety.

[0154] As an optional embodiment: the specific working mode of the communication cooperation module in the initial situation is as follows:

[0155] Configure communication parameters based on the vehicle's current location and driving status; before the driverless vehicle starts driving, the communication coordination module will configure communication parameters based on the vehicle's current location (such as city center, highway, etc.) and driving status (such as speed, direction), including setting the communication range to ensure that the vehicle can effectively communicate with surrounding vehicles and infrastructure; setting the communication frequency to adapt to different communication environments and reduce interference. The configuration of these parameters is dynamic and can be adjusted according to the vehicle's driving environment;

[0156] Exchange position, speed, and driving direction information with surrounding vehicles, and exchange traffic rules and road condition information with traffic lights and roadside units; It should be noted that the communication coordination module enables vehicles to exchange data with surrounding vehicles (V2V) and infrastructure (V2I), including information such as the vehicle's position, speed, and driving direction, which are essential for avoiding collisions and optimizing traffic flow. At the same time, exchange traffic rules and road condition information with traffic lights and roadside units to help vehicles comply with traffic rules, avoid congested areas, and choose the best route;

[0157] Receive control decisions from the decision-making unit, specifically, high-speed mode, safety mode, or emergency mode; It should be noted that the communication coordination module receives control decisions from the decision-making unit, which are based on the environmental information collected by the vehicle's perception module and the judgment results of the positioning fusion unit. The control decision can be a high-speed mode, a safety mode, or an emergency mode. Each mode corresponds to different driving strategies and behaviors, such as speed limit, acceleration, and steering response adjustment;

[0158] According to the control decision, the coordination state with surrounding vehicles and infrastructure is adjusted. It should be noted that according to the control decision received from the decision unit, the communication coordination module adjusts the coordination state with surrounding vehicles and infrastructure;

[0159] For example, in high-speed mode, the vehicle may need to maintain a greater safety distance from the vehicle in front; in safety mode, the vehicle may need to reduce speed and increase the monitoring frequency of sensors.

[0160] As an optional embodiment: the specific work of the communication coordination module also includes:

[0161] After the decision unit outputs the emergency decision signal, the emergency information is broadcasted;

[0162] When the decision unit outputs an emergency decision signal, the communication coordination module is responsible for broadcasting emergency information to surrounding vehicles and infrastructure, such as vehicle failure, accidents or environmental abnormalities. The broadcast of this information can help surrounding traffic participants respond in time to avoid further accidents.

[0163] It is also used to receive emergency information from other vehicles or infrastructure and take appropriate emergency measures.

[0164] It should be noted that the communication coordination module not only broadcasts emergency information, but also receives emergency information from other vehicles or infrastructure and takes emergency measures based on this information;

[0165] For example, if urgent information is received about road construction ahead, the vehicle may need to slow down or change routes;

[0166] The communication and coordination module ensures that unmanned vehicles can maintain effective communication and coordination with the surrounding environment and other traffic participants in various situations, thereby improving driving safety and traffic efficiency.

[0167] How it works

[0168] By integrating multiple sensors and advanced decision-making algorithms, the adaptability of driverless cars in different environmental conditions is improved, especially in complex or rugged road conditions. Driverless cars can accurately identify and manage various traffic participants including pedestrians, bicycles, tricycles, cars and animals; it enables driverless cars to intelligently switch between high-speed mode and safety mode according to real-time environmental changes and traffic conditions, ensuring driving safety in complex traffic environments.

[0169] The above are only preferred implementations of the present invention. The protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical staff in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of this template.

Claims

1. An unmanned vehicle control system based on multi-sensor fusion technology, characterized in that: It includes a perception module, which is used to collect and transmit information about the vehicle's surrounding environment; A map fusion module, the map fusion module includes a map unit and a positioning fusion unit, the map unit is used to obtain map information near the vehicle through GPS, and the positioning fusion unit determines whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section through the map information on the GPS and historical vehicle driving data, and transmits the judgment result; A driving control module, the driving control module includes a decision unit and a control unit, the decision unit is used to receive the vehicle surrounding environment information of the perception module and the judgment result of the positioning fusion unit, output a control decision, and transmit it to the control unit; The specific steps of the output control decision are as follows: When the positioning fusion unit determines through GPS and historical data that the vehicle is on an urban road or a frequently driven road section, the decision unit outputs a high-speed mode decision signal; When the positioning fusion unit determines that the vehicle is in a remote area or a path with less historical driving data, the decision unit outputs a safety mode decision signal; The vehicle surrounding environment information of the perception module is monitored, and when an emergency signal is monitored, the decision unit outputs an emergency decision signal; The control unit is used to adjust the parameters of the vehicle when it is driving, and is also used to switch the control state according to the control decision of the decision unit; The control unit includes a first control state and a second control state; When the control unit receives the high-speed mode decision signal from the decision unit, switching to the first control state; When the control unit receives the safety mode decision signal from the decision unit, switching to the second control state; The control unit also includes an emergency control state, which switches to an emergency mode control state when the decision unit outputs an emergency decision signal; a communication coordination module, the communication coordination module being used to realize communication between vehicles and between vehicles and between vehicles and infrastructure, and the communication coordination module adjusting a coordination state according to a control decision of the decision unit; When the control unit receives the high-speed mode decision signal from the decision unit, the specific working method of switching to the first control state is: The initial maximum speed limit H and the speed increase J of the vehicle are obtained, and a new speed limit H1 is obtained according to the initial maximum speed limit H plus the speed increase J, so as to meet the demand of high-speed driving by increasing the speed limit; According to the formula N1=N*k, a new vehicle acceleration N1 is calculated, where N is the initial acceleration and k is the acceleration adjustment coefficient determined according to the vehicle performance. The vehicle acceleration N1 is adjusted to change the vehicle throttle response curve; When the control unit receives the safety mode decision signal of the decision unit, the specific working method of switching to the second control state is: Obtain the speed reduction value M of the vehicle, and obtain a new speed limit value H2 according to the initial maximum speed limit value H minus the speed reduction value M, thereby reducing the speed limit value; The initial information collection frequency G of the perception module is obtained, and a new material frequency G1 is obtained by multiplying the initial information collection frequency G by the adjustment coefficient J. The environmental perception capability is improved by increasing the sampling rate of the sensor data of the perception module.

2. The unmanned vehicle control system based on multi-sensor fusion technology according to claim 1 is characterized in that: The specific working mode of the positioning fusion unit is as follows: acquiring the real-time position coordinates of the vehicle through a GPS receiver, and retrieving map information near the vehicle from the map data of the map unit using the real-time position coordinates of the vehicle; Taking the real-time position of the vehicle as the center, draw a circle with a preset radius to obtain the area around the vehicle; Obtaining the number of roads D in the area around the vehicle through the map information of the map unit; The road connectivity C is obtained by dividing the number of connected road segments in the area around the vehicle by the number of roads D; Obtain the number of vehicles T that passed through the area around the vehicle within a specific time period before the current time point; Obtain the average speed V of the area around the vehicle in a specific time period before the current time point; Count the number of historical accidents in the area around the vehicle A; Based on historical data, a first threshold corresponding to the number of vehicles T, a second threshold corresponding to the average speed V, and a third threshold corresponding to the number of historical accidents A are set; Setting a fourth threshold corresponding to the number of roads D and a fifth threshold corresponding to the road connectivity C; Based on the number of roads D, road connectivity C, number of vehicles T, average speed V, number of historical accidents A and corresponding thresholds, it is determined whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section.

3. The unmanned vehicle control system based on multi-sensor fusion technology according to claim 2 is characterized in that: The specific method of determining whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section is as follows: If the number of vehicles T in the area around the vehicle is greater than the first threshold and the average speed V is greater than the second threshold, the urban road possibility is increased by one point; If the number of historical accidents A in the area around the vehicle is less than the third threshold, the urban road possibility is increased by one point; If the number of roads D in the area around the vehicle is greater than the fourth threshold and the road connectivity C is greater than the fifth threshold, the urban road possibility is increased by one point; If the number of vehicles T in the area around the vehicle is less than the first threshold and the average speed V is less than the second threshold, the remote area possibility is increased by one point; If the number of historical accidents A in the area around the vehicle is greater than the third threshold, the remote area possibility is increased by one point; If the number of roads D in the area around the vehicle is less than the fourth threshold and the road connectivity C is less than the fifth threshold, the remote area possibility is increased by one point; If the urban road probability is greater than or equal to three points, it is judged to be an urban road or a frequently driven road section; If the remote area probability is greater than or equal to three points, it is judged to be a remote area or a route with less historical driving data.

4. The unmanned vehicle control system based on multi-sensor fusion technology according to claim 3 is characterized in that: The specific method of determining whether the vehicle belongs to a remote area and an unknown path or an urban road or a frequently driven section also includes: If the number of vehicles T in the area around the vehicle is greater than the first threshold and the average speed V is less than the second threshold, the urban road possibility is increased by one point; If the number of vehicles T in the area around the vehicle is less than the first threshold and the average speed V is greater than the second threshold, the remote area possibility is increased by one point; If the number of roads D in the area around the vehicle is greater than the fourth threshold and the road connectivity C is greater than the fifth threshold, the urban road possibility is increased by one point; If the number of roads D in the area around the vehicle is less than a fourth threshold and the road connectivity C is greater than a fifth threshold, the remote road possibility is increased by one point.

5. The unmanned vehicle control system based on multi-sensor fusion technology according to claim 1 is characterized in that: The specific steps of the decision unit outputting the emergency decision signal are as follows: Acquiring the vehicle surrounding environment information of the perception module, specifically including image information, weather information, road surface status information and traffic rules information around the vehicle; If there is an obstacle in the image information of the vehicle's driving path, an emergency decision signal is generated and transmitted; The vehicle surrounding environment information also includes a laser radar. When the image information identifies an obstacle, the laser radar information is used to verify whether there is an obstacle. If there is an abnormality in the weather information, that is, the local weather forecast issues an early warning signal, or the road condition information is abnormal, a second-class emergency decision signal is generated and transmitted; Furthermore, if the local weather forecast issues a warning signal, or monitors heavy rain or strong winds, the road status information is used to verify whether the weather information is correct; Based on traffic rules information, three types of emergency decision signals are issued.

6. The unmanned vehicle control system based on multi-sensor fusion technology according to claim 5 is characterized in that: The specific working method of switching to the emergency mode control state when the decision unit outputs the emergency decision signal is as follows: When the control unit receives an emergency decision signal, the control unit immediately controls the vehicle to brake, stop or turn; When the control unit receives the second type of emergency decision signal, it obtains a new speed limit H2 according to the initial maximum speed limit H minus the emergency speed reduction value F, and further reduces the speed; When the control unit receives the three types of emergency decision signals, it reads the speed limit or traffic restriction rules in the traffic rule information to perform corresponding control on the vehicle.

7. The unmanned vehicle control system based on multi-sensor fusion technology according to claim 1 is characterized in that: The specific working mode of the communication cooperation module in the initial situation is as follows: Configure communication parameters according to the vehicle's current location and driving status; Exchange position, speed, and driving direction information with surrounding vehicles, and exchange traffic rules and road condition information with traffic lights and roadside units; receiving a control decision from a decision unit, specifically a high-speed mode, a safety mode, or an emergency mode; Based on control decisions, the coordinated state with surrounding vehicles and infrastructure is adjusted.

8. The unmanned vehicle control system based on multi-sensor fusion technology according to claim 7 is characterized in that: The specific work of the communication coordination module also includes: After the decision unit outputs the emergency decision signal, the emergency information is broadcasted; It is also used to receive emergency information from other vehicles or infrastructure and take appropriate emergency measures.

Images