Assisted driving methods, devices, controllers and vehicles

Abstract

This application provides an assisted driving method, device, controller, and vehicle. The method includes: a controller acquiring sensor data uploaded by multiple sensors; the controller generating first obstacle information based on the sensor data; the controller analyzing the first obstacle information to generate initial decision information; the controller further optimizing the initial decision information based on the first obstacle information and the sensor data to generate final decision information for assisted driving of the vehicle; and the controller further optimizing the initial decision information based on the first obstacle information and the sensor data to generate final decision information for assisted driving of the vehicle. This method aims to improve vehicle safety.

Description

Technical Field

[0001] This application relates to the field of driver assistance, specifically to a driver assistance method, device, controller, and vehicle. Background Technology

[0002] With the increasing number of cars on the road, the frequency of traffic accidents is also rising. To reduce collision risk, vehicles can be equipped with Automatic Emergency Braking (AEB) and Automatic Emergency Steering (AES) systems. However, the current combined use of AEB and AES in vehicles needs further improvement to enhance vehicle safety. Summary of the Invention

[0003] This application provides an assisted driving method, device, controller, and vehicle to improve vehicle safety.

[0004] In a first aspect, embodiments of this application provide an assisted driving method applied to a vehicle, wherein the vehicle's controller includes a system chip with safety level B and a microcontroller with safety level D, comprising:

[0005] Based on sensor data collected by each of the multiple sensors in the vehicle, first obstacle information and initial decision information are generated in the system chip; wherein, the initial decision information represents the initial decision of the vehicle's assisted driving, and the first obstacle information is obstacle recognition information of safety level B;

[0006] Based on the initial decision information, the first obstacle information, and the sensor data, the microcontroller generates and executes the final decision information for assisted driving of the vehicle at safety level D.

[0007] Secondly, embodiments of this application provide a driver assistance device applied to a vehicle, wherein the vehicle's controller includes a system chip with safety level B and a microcontroller with safety level D, comprising:

[0008] The first processing module is used to generate first obstacle information and initial decision information in the system chip based on sensor data collected by each of the multiple sensors in the vehicle; wherein, the initial decision information represents the initial decision of the vehicle's assisted driving, and the first obstacle information is obstacle recognition information of safety level B.

[0009] The second processing module is used to generate and execute final decision information for assisted driving of the vehicle at safety level D on the microcontroller based on the initial decision information, the first obstacle information, and the sensor data.

[0010] Thirdly, embodiments of this application provide a controller, including: a system chip and a microprocessor;

[0011] The system chip and the microprocessor respectively include a storage unit and a processing unit;

[0012] The storage unit stores computer-executed instructions;

[0013] The processing unit executes the computer execution instructions stored in the storage unit, causing the processing unit to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0014] Fourthly, embodiments of this application provide a vehicle including multiple sensors and controllers as described in the first aspect and / or various possible controllers described in the first aspect.

[0015] Fifthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processing unit, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0016] In a sixth aspect, embodiments of this application provide a computer program product, including a computer program that, when executed by a processing unit, implements the first aspect and / or various possible implementations of the first aspect.

[0017] The assisted driving method, device, controller, and vehicle provided in this application generate first obstacle information of safety level B using a system chip with safety level B, analyze the first obstacle information to generate initial decision information of safety level B, generate second obstacle information of safety level D using a microcontroller with safety level D, and optimize the initial decision information based on the first and second obstacle information to obtain final decision information of safety level D. The means of executing the final decision information achieve the effect of improving vehicle safety to safety level D by using a system chip with safety level B and a microcontroller with safety level D. Furthermore, the use of the system chip with safety level B and the microcontroller with safety level D avoids the need to increase hardware costs. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 A schematic diagram of a functional architecture provided in this application;

[0020] Figure 2 A flowchart illustrating a driving assistance method provided in this application. Figure 1 ;

[0021] Figure 3 A schematic diagram of a system architecture provided in this application Figure 1 ;

[0022] Figure 4 A schematic diagram of a system architecture provided in this application Figure 2 ;

[0023] Figure 5 A flowchart illustrating a driving assistance method provided in this application. Figure 2 ;

[0024] Figure 6 A flowchart illustrating a driving assistance method provided in this application. Figure 3 ;

[0025] Figure 7 A schematic diagram of the structure of an auxiliary driving device provided in this application;

[0026] Figure 8 This is a schematic diagram of the structure of a controller provided in this application. Detailed Implementation

[0027] The embodiments of this application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of this application from the content disclosed in this specification. This application can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of this application. It should be understood that the preferred embodiments are only for illustrating this application and are not intended to limit the scope of protection of this application.

[0028] With the continuous increase in the number of cars in my country, various traffic accidents and the resulting casualties and property damage are also on the rise. To reduce the risk of forward collisions, Automatic Emergency Braking (AEB) systems have been gradually commercialized and applied to vehicles. However, in sudden scenarios such as pedestrians suddenly crossing the road, vehicles braking suddenly ahead, or vehicles emerging from intersections in blind spots, collisions can still occur due to the vehicle's inability to detect danger in advance and the resulting emergency braking. To further improve vehicle safety, Automatic Emergency Steering (AES) has also been implemented. AES can work in conjunction with AEB to better address forward collision issues.

[0029] A commonly used functional architecture that combines AES and AEB can be described as follows: Figure 1 As shown, the hardware in the controller may include a system-on-chip (SOC) with a safety level of B and a microcontroller unit (MCU) with a safety level of D. Optionally, the aforementioned safety level is the Automotive Safety Integrity Level (ASIL). ASIL is a standard defined by ISO 26262 for assessing the safety of electronic and electrical systems. Figure 1 As shown, the SOC is directly connected to the forward-facing camera module and the surround-view module, and can calculate obstacle information in the forward and lateral directions through visual processing. Simultaneously, the SOC can fuse the obstacle information obtained from visual processing with information input from an external radar module to obtain obstacle information with a safety level of B, and then generate decision information based on this obstacle information. This decision information can be output to the decision planning module of the MCU. The MCU's decision planning module can then perform corresponding vehicle assisted driving control based on this decision information. Since the safety level of this SOC is B, the safety level of the decision information generated by the SOC is also B. That is, the safety level of the decision executed by the MCU at this time is B. This decision information can be used to instruct the vehicle to perform emergency braking or emergency steering.

[0030] To further improve vehicle safety and achieve a safety level of D, the assisted driving method provided in this application can be based on, for example... Figure 1The SOC with a security level of B and the MUC with a security level of D are shown. By adding security mechanisms to the MCU, the security level of the final generated decision information is improved, enabling the decision information to meet the security level requirement of D. This application fully utilizes the computing power, interfaces, and alternative system functions of each on-board ECU, achieving a low-cost security strategy without adding new ECUs.

[0031] To meet the above requirements, this application analyzed relevant failure scenarios that need to meet ASIL D functional safety standards. It was found that the main optimization scenario for ASIL D is the unexpected triggering of AES during normal vehicle operation. Unexpected AES triggering typically involves large steering angles and high steering rates, and due to the unexpected nature of the triggering, the driver usually cannot take over the vehicle in time. Analysis of unexpected AES triggering reveals that AES implementation requires accurate identification of lateral hazards, ensuring that the AES function is triggered only when there are no lateral hazards. Furthermore, to ensure that the implementation of this AES function meets ASIL D safety requirements, adding a safety mechanism to the MCU can further optimize the identification of lateral hazards, improving identification accuracy and the accuracy of AES trigger determination.

[0032] This application achieves a solution that meets ASIL D safety requirements by adding a safety mechanism to the MCU, using an ASIL B chip system and an ASIL D microcontroller. This improves vehicle safety, solves the problem of insufficient computing power in the microcontroller unit, and realizes a low-cost safety strategy without adding an ECU.

[0033] The technical solution of this application and how the technical solution of this application solves the above-mentioned technical problems are described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0034] Figure 2 Flowchart of the assisted driving method provided in this application Figure 1 ,like Figure 2 As shown, with the controller in the vehicle as the executing entity, the method includes:

[0035] S101. Based on the sensor data collected by each of the multiple sensors in the vehicle, generate first obstacle information and initial decision information in the system chip. The initial decision information represents the initial decision of the vehicle's assisted driving, and the first obstacle information is obstacle recognition information at safety level B.

[0036] In this embodiment, the system chip in the controller can acquire sensor data collected and uploaded by multiple sensors. Optionally, the sensor can be installed on the vehicle. The sensor installed on the vehicle can upload its data to the system chip in the controller in real time. Optionally, the sensor can also be installed on the roadside. The system chip in the controller can acquire the sensor data uploaded by the roadside sensor when the distance to the roadside sensor is less than or equal to a sensor threshold.

[0037] The system chip in the controller can generate first obstacle information based on the sensor data. This first obstacle information is used to indicate obstacles around the vehicle. Specifically, the first obstacle information can be used to describe in detail the key features of obstacles around the vehicle, such as their position, speed, and type. Since the system chip's safety level is B, the first obstacle information is obstacle recognition information with a safety level of B. Optionally, the first obstacle information can include information on all obstacles around the vehicle. Optionally, the system chip in the controller can identify the sensor data using a preset recognition algorithm. Optionally, the recognition algorithm can be a machine learning algorithm. For example, the machine learning algorithm can be a region-based convolutional neural network (R-CNN), a single-shot multibox detector (SSD), YOLO, etc. Optionally, the system chip in the controller can preprocess the sensor data and then input it into the recognition algorithm to obtain the first obstacle information on the road. Optionally, the system chip in the controller can also input the data from each sensor into the corresponding recognition algorithm to obtain the obstacle corresponding to that sensor. The system chip in the controller can then perform intersection calculations on the obstacles corresponding to each sensor to obtain the final first obstacle information.

[0038] The system chip in the controller can analyze the information of the first obstacle and generate initial decision information. This initial decision information preliminarily plans the vehicle's assisted driving path and strategy.

[0039] Optionally, this step can be performed on the system chip.

[0040] In one example, the specific process by which the system chip in the controller generates first obstacle information and initial decision information based on sensor data may include:

[0041] Step 1: Identify the data from each sensor to obtain the third obstacle information corresponding to each sensor data.

[0042] In this step, the system chip in the controller can be pre-set with a recognition model corresponding to each sensor. The system chip in the controller can use the recognition model corresponding to the sensor to identify the sensor data uploaded by the sensor and obtain the third obstacle information corresponding to the sensor data. This third obstacle information is the information about obstacles around the vehicle obtained after identifying the sensor data. For example, when visual sensors and radar sensors are included, it can include the third obstacle information identified by the visual sensor and the third obstacle information identified by the radar sensor. The third obstacle information identified by the visual sensor and the third obstacle information identified by the radar sensor may contain different obstacles, or there may be different recognition results for the same obstacle in terms of position, speed, and type.

[0043] Step 2: Match the third obstacle information corresponding to each sensor data to obtain the first obstacle information.

[0044] In this step, the system chip in the controller can integrate and refine the third obstacle information corresponding to each sensor data through matching to obtain more accurate and comprehensive first obstacle information. Optionally, the obstacle matching requirements can be determined according to ASIL B safety requirements. Optionally, the method of integrating and refining the third obstacle information corresponding to each sensor data can be to calculate the intersection or union of the third obstacle information corresponding to each sensor data to obtain the final first obstacle information. Optionally, in one implementation, when the fourth obstacle information corresponding to the visual sensor data does not contain obstacle A, but the fourth obstacle information corresponding to the radar sensor data contains obstacle A, the system chip in the controller may not record obstacle A in the first obstacle information. In another implementation, when the fourth obstacle information corresponding to the visual sensor data does not contain obstacle A, but the fourth obstacle information corresponding to the radar sensor data contains obstacle A, the system chip in the controller may record obstacle A in the first obstacle information.

[0045] Step 3: Generate initial decision information based on the information of the first obstacle.

[0046] In this step, the system chip in the controller can be equipped with a decision algorithm. The system chip in the controller can input the first obstacle information into the decision algorithm to obtain the initial decision information. Optionally, the requirements of the decision algorithm can be determined according to the safety requirements of ASIL B. Optionally, the initial decision information can be used to indicate whether there is an obstacle in front of the vehicle and whether the vehicle needs to avoid a collision with the obstacle by means of emergency braking. If emergency braking is required, the system chip in the controller can also calculate the deceleration of the vehicle. Furthermore, the decision information can also be used to indicate whether there is an obstacle to the side of the vehicle. If there is no obstacle to the side of the vehicle, the system chip in the controller can also plan the angle of emergency steering so that the vehicle can avoid a collision with the obstacle in front of the vehicle by means of emergency steering. Optionally, the emergency steering judgment can be performed when it is impossible to avoid a collision with the obstacle in front of the vehicle by deceleration.

[0047] S102. Based on the initial decision information, the first obstacle information, and the data from each sensor, the microcontroller generates and executes the final decision information for assisted driving of the vehicle at safety level D.

[0048] In this embodiment, the microcontroller in the controller further optimizes the initial decision information based on the first obstacle information and data from various sensors to generate the final decision information for assisted driving of the vehicle. Optionally, the first obstacle information can be optimized based on sensor information according to more refined obstacle recognition rules, so as to use the optimized first obstacle information to optimize the initial decision information and obtain the final decision information. This final decision information can be determined according to the safety requirements of ASIL D. Optionally, this step can be executed on the microcontroller in the controller. The microcontroller in the controller can be pre-set with a recognition algorithm determined according to the safety requirements of ASIL D. The microcontroller in the controller can use this recognition algorithm to optimize and recognize the first obstacle information to obtain more accurate obstacle information. The microcontroller in the controller can then use this more accurate obstacle information to detect and optimize the initial decision information to obtain the final decision information.

[0049] In one example, the process by which the microcontroller in the controller obtains the final decision information may include:

[0050] Step 1: Generate second obstacle information based on the data from each sensor. The second obstacle information is obstacle recognition information at safety level D.

[0051] In this step, the microcontroller in the controller can generate more accurate second obstacle information than the first obstacle information based on data collected in real time from various sensors. The generation method for this second obstacle information differs from that of the first obstacle information, and the generation of the second obstacle information has higher security requirements. The security level of this second obstacle information can be D.

[0052] Step 2: Based on the information of the first obstacle and the information of the second obstacle, optimize the initial decision information to obtain the final decision information.

[0053] In this step, the microcontroller in the controller can comprehensively consider the advantages and complementarity of the first obstacle information and the second obstacle information, and optimize and adjust the initial decision information through intelligent algorithms in order to obtain more accurate and reliable final decision information. The microcontroller in the controller can then transform this final decision information into a series of precise control commands to guide the vehicle to perform corresponding actions such as emergency braking, emergency steering, or issuing warnings.

[0054] The assisted driving method provided in this application embodiment allows the controller to acquire sensor data collected and uploaded by multiple sensors. The controller can generate first obstacle information based on this sensor data. The controller can analyze the first obstacle information to generate initial decision information. The controller can further optimize the initial decision information based on the first obstacle information and the sensor data to generate final decision information for assisted driving of the vehicle. By acquiring the first obstacle information and the initial decision information, and then optimizing the initial decision information based on the sensor information and the first obstacle information, the vehicle's safety is improved.

[0055] Based on the above embodiments, such as Figure 3 and Figure 4 Two system architecture diagrams are shown. Figure 3 An external system hierarchical architecture designed to meet ASIL D security level requirements, such as Figure 4 This refers to the internal hardware and software architecture hierarchy designed to meet ASIL D security level requirements.

[0056] like Figure 3As shown, this safety architecture may include a first group of sensors and a second group of sensors. The first group of sensors may include a forward-looking camera module, a panoramic camera module, a high-precision map, and a LiDAR. The second group of sensors may include a forward-looking radar and corner radar. The number of LiDAR and corner radars can be four. This safety architecture may also include an autonomous driving control unit, a gateway, an emergency braking control module, an emergency steering control module, and a human-machine interaction control module. The first and second group of sensors constitute the vehicle's perception system. These two groups of sensors are configured based on the principle of minimizing risk and are independent of each other. The first group of sensors is connected to the autonomous driving control module 7 via a panoramic deserializer, a forward-looking deserializer, and Ethernet. The second group of sensors is connected to the autonomous driving control module via two CAN buses and directly to the gateway via Ethernet. The autonomous driving control module 7 is connected to the gateway via two CAN buses. The gateway 8 is connected to the emergency braking control module, the emergency steering control module, and the human-machine interaction control module via three CAN buses, respectively.

[0057] like Figure 4 As shown, this safety architecture may include an autonomous driving control module. This module may consist of a system-on-a-chip (SoC) and a microcontroller. The SoC internally houses three modules: vision processing, perception fusion, and decision planning. The microcontroller unit includes four software modules: lateral hazard detection, AEB / AES arbitration, AEB control, and AES control. The vision processing module within the SoC connects to the perception fusion module via internal chip communication, and the perception fusion module connects to the decision planning module via internal chip communication. The vision processing and decision planning modules can also connect to the lateral hazard detection module and the AEB / AES arbitration module within the microcontroller, respectively, via inter-chip communication. The AEB and AES control modules can connect to a gateway via a CAN bus. The AEB / AES arbitration module within the microcontroller connects to the AEB and AES control modules.

[0058] The forward-looking camera module, forward-looking radar, corner radar, panoramic camera module, and lidar all meet ASIL B safety requirements. The gateway, emergency braking control module, and emergency steering control module meet ASIL D safety requirements. The vision processing, perception fusion, and decision planning modules in the system chip meet ASIL B safety requirements. The lateral hazard target detection, AEB / AES arbitration, AEB control, and AES control modules in the microcontroller meet ASIL D safety requirements.

[0059] Under ASIL B safety requirements, the system-on-a-chip (SoC) decision-making and planning mechanism can arbitrate with the Automatic Emergency Braking (AEB) system when an emergency steering maneuver is planned. If emergency braking can avoid a collision, the MCU can directly output an emergency braking request command. If the arbitration determines that emergency braking cannot avoid a collision, an emergency steering control command needs to be output for collision avoidance. However, to meet ASIL D safety requirements and avoid unintended steering, the MCU can also perform safety analysis through a lateral hazard target determination module to prevent unintended steering, oversteering, understeering, and other problems.

[0060] Figure 5 Flowchart of the assisted driving method provided in this application Figure 2 ,like Figure 5 As shown, in this embodiment... Figures 1 to 4 Based on the illustrated embodiment, the process of generating the final decision information is described in detail. The specific process of this method includes:

[0061] S201. Identify the data from each sensor to obtain the third obstacle information corresponding to each sensor data.

[0062] In this embodiment, the microcontroller in the controller can store the recognition model corresponding to each sensor. The microcontroller in the controller can use the recognition model to identify the sensor data of each sensor and obtain the third obstacle information corresponding to each sensor data.

[0063] S202. The information of the third obstacle is fused and filtered to obtain the information of the second obstacle.

[0064] In this embodiment, the microcontroller in the controller fuses and filters the third obstacle information corresponding to each sensor data, eliminating redundant or erroneous obstacle information to obtain more accurate second obstacle information. Optionally, the microcontroller in the controller can obtain the second obstacle information by first filtering, then fusing, and then filtering again. Optionally, the microcontroller in the controller can also obtain the second obstacle information by first fusing and then filtering.

[0065] In one example, the specific process by which the microcontroller in the controller obtains the second obstacle information through a process of first filtering, then fusing, and then filtering again may include:

[0066] Step 1: Filter the third obstacle information according to the probability threshold corresponding to each sensor data to obtain the fourth obstacle information.

[0067] In this step, the microcontroller in the controller can be configured with probability thresholds corresponding to each sensor's data. The microcontroller first filters the third obstacle information corresponding to each sensor's data based on its probability threshold, thus obtaining the fourth obstacle information. Optionally, different sensors can have the same probability threshold. For example, the probability threshold for both a vision sensor and a radar sensor can be 80%. Optionally, different sensors can have different probability thresholds. For example, the probability threshold for a vision sensor can be 75%, and the probability threshold for a radar sensor can be 85%. The microcontroller in the controller filters the obstacle information based on the probability value of each obstacle in the third obstacle information corresponding to each sensor, comparing it to the probability threshold for that sensor. If the probability value of an obstacle in the third obstacle information is less than the probability threshold, the microcontroller can delete obstacles with probability values ​​less than the threshold and retain obstacles with probability values ​​greater than or equal to the threshold, thus obtaining the fourth obstacle information corresponding to that sensor data.

[0068] Step 2: Fusion and matching of the fourth obstacle information corresponding to each sensor data to obtain the fifth obstacle information.

[0069] In this step, the microcontroller in the controller can fuse and match the fourth obstacle information corresponding to the data from each sensor. This process aims to integrate data from different sensors to improve the accuracy and reliability of obstacle detection, thereby obtaining the fifth obstacle information. Optionally, the microcontroller in the controller can identify obstacles with the same location in the fourth obstacle information corresponding to each sensor information through matching, and retain the obstacles with the same location to obtain the fifth obstacle information. Optionally, the microcontroller in the controller can also obtain the obstacle information of each obstacle detected by all sensor data through fusion calculation, thereby assembling the fifth obstacle information.

[0070] One way to obtain the fifth obstacle information through fusion matching may include the following steps:

[0071] Step 21: Match the fourth obstacle information corresponding to each sensor data to obtain the sixth obstacle information corresponding to each sensor data.

[0072] In this step, the microcontroller in the controller matches the fourth obstacle information corresponding to each sensor data to determine whether the obstacles in the fourth obstacle information corresponding to each sensor data are the same obstacle. If the obstacles in the fourth obstacle information corresponding to each sensor data are the same obstacle, the microcontroller in the controller completes the matching of the obstacle and stores the obstacle in the sixth obstacle information. Optionally, in one implementation, when the fourth obstacle information corresponding to the visual sensor data does not contain obstacle A, but the fourth obstacle information corresponding to the radar sensor data contains obstacle A, the microcontroller in the controller may not record obstacle A in the sixth obstacle information. In another implementation, when the fourth obstacle information corresponding to the visual sensor data does not contain obstacle A, but the fourth obstacle information corresponding to the radar sensor data contains obstacle A, the microcontroller in the controller may record obstacle A in the sixth obstacle information and pad the information corresponding to the visual sensor data with 0.

[0073] Step 22: Based on the probability weights corresponding to each sensor data, perform weighted fusion on the sixth obstacle information corresponding to each sensor data to obtain the fifth obstacle information.

[0074] In this step, the microcontroller in the controller can acquire the probability weights corresponding to each sensor data point. The microcontroller in the controller can then perform weighted fusion of the probability values ​​of each obstacle in the sixth obstacle information to obtain the final probability value of each obstacle. The microcontroller in the controller can then assemble the fifth obstacle information based on the final probability values ​​of each obstacle. Optionally, in one implementation, the probability weights of the sensor data can be set based on empirical values. In another implementation, the probability weights of the sensor data can be determined based on the detection accuracy of the sensor data.

[0075] Optionally, the microcontroller in the controller can also determine the probability weights corresponding to each sensor data based on the third obstacle information and the sixth obstacle information corresponding to each sensor data. Specifically, the microcontroller in the controller can determine a first number of obstacles that exist in both the third obstacle information and the sixth obstacle information corresponding to each sensor data. The microcontroller in the controller can determine a first parameter based on the ratio of this first number to a second number of obstacles in the third obstacle information corresponding to the sensor data. The microcontroller in the controller can process the first parameter corresponding to each sensor data to obtain the probability weights of each sensor data. Optionally, the sum of the probability weights corresponding to each sensor data can be 1.

[0076] Step 3: Filter the information of the fifth obstacle according to the preset fusion threshold to obtain the information of the second obstacle.

[0077] In this step, the microcontroller in the controller can store a preset fusion threshold. The microcontroller can further filter the fifth obstacle information based on this preset fusion threshold. Specifically, the microcontroller can compare the fusion threshold with the probability values ​​of each obstacle in the fifth obstacle information. If the probability value of an obstacle in the fifth obstacle information is greater than or equal to the fusion threshold, the microcontroller can retain the obstacle in the second obstacle information. If the probability value of an obstacle in the fifth obstacle information is less than the fusion threshold, the microcontroller can delete the obstacle.

[0078] In another example, the specific process by which the microcontroller in the controller obtains the second obstacle information through a process of first fusing and then filtering may include:

[0079] Step 1: Match the probability thresholds corresponding to each sensor data with the information of the third obstacle to obtain the information of the seventh obstacle corresponding to each sensor data.

[0080] In this step, the microcontroller in the controller matches the third obstacle information corresponding to each sensor data to determine whether the obstacles in the third obstacle information corresponding to each sensor data are the same obstacle. If the obstacles in the third obstacle information corresponding to each sensor data are the same obstacle, the microcontroller in the controller completes the matching of the obstacle and stores the obstacle in the seventh obstacle information. Optionally, in one implementation, when the third obstacle information corresponding to the visual sensor data does not contain obstacle A, but the third obstacle information corresponding to the radar sensor data contains obstacle A, the microcontroller in the controller may not record obstacle A in the seventh obstacle information. In another implementation, when the third obstacle information corresponding to the visual sensor data does not contain obstacle A, but the third obstacle information corresponding to the radar sensor data contains obstacle A, the microcontroller in the controller may record obstacle A in the seventh obstacle information and pad the information corresponding to the visual sensor data with 0.

[0081] Step 2: Based on the probability weights corresponding to each sensor data, the seventh obstacle information corresponding to each sensor data is weighted and fused to obtain the eighth obstacle information.

[0082] In this step, the microcontroller in the controller can acquire the probability weights corresponding to each sensor data point. The microcontroller in the controller can then perform weighted fusion of the probability values ​​of each obstacle in the seventh obstacle information to obtain the final probability value for each obstacle. The microcontroller in the controller can then assemble the eighth obstacle information based on the final probability values ​​of each obstacle. Optionally, in one implementation, the probability weights of the sensor data can be set based on empirical values. In another implementation, the probability weights of the sensor data can be determined based on the detection accuracy of the sensor data.

[0083] Step 3: Filter the information of the eighth obstacle according to the preset fusion threshold to obtain the information of the second obstacle.

[0084] In this step, the microcontroller in the controller can store a preset filtering threshold. The microcontroller can further filter the eighth obstacle information based on this preset filtering threshold. Specifically, the microcontroller can compare the filtering threshold with the probability values ​​of each obstacle in the eighth obstacle information. If the probability value of an obstacle in the eighth obstacle information is greater than or equal to the filtering threshold, the microcontroller can retain the obstacle in the second obstacle information. If the probability value of an obstacle in the eighth obstacle information is less than the filtering threshold, the microcontroller can delete the obstacle.

[0085] S203. Based on the initial decision information, determine at least one initial driving area.

[0086] In this embodiment, the microcontroller in the controller can acquire the generated initial decision information. The microcontroller can extract at least one initial driving area from this initial decision information. This initial driving area can be a drivable area indicated by the initial decision information. For example, when emergency braking can avoid a collision, the initial driving area may include a forward driving area. Similarly, when multiple emergency steering angles can avoid a collision, the initial driving area may include multiple lateral areas.

[0087] S204. Based on the information of the first obstacle and the second obstacle, generate an activation marker for the initial driving area.

[0088] In this embodiment, the microcontroller in the controller can generate a corresponding activation identifier for each initial driving area based on the first obstacle information and the second obstacle information. This activation identifier indicates whether the initial driving area needs to be activated. Optionally, the microcontroller in the controller can determine whether the initial driving area needs to be activated by judging whether the initial driving area contains obstacles based on the first obstacle information and the second obstacle information.

[0089] In one example, the process of generating the activation identifier may include the following steps:

[0090] Step 1: If the initial driving area does not include information on the first obstacle and the second obstacle, then the activation flag of the initial driving area is set to be activatable.

[0091] In this step, the microcontroller in the controller checks whether the initial driving area contains first obstacle information and / or second obstacle information. That is, whether the obstacles indicated in the first obstacle information and second obstacle information appear in the initial driving area. If the initial driving area does not contain the obstacles indicated in the first obstacle information and second obstacle information, the microcontroller in the controller sets the activation flag of the initial driving area to be active. When the driving area is active, it indicates that the driving area is a safe area.

[0092] Step 2: If the initial driving area includes information about the first obstacle and / or the second obstacle, then the activation flag of the initial driving area is set to non-activatable.

[0093] In this step, if the initial driving area contains obstacles indicated by the first obstacle information and / or the second obstacle information, the microcontroller in the controller will correspondingly set the activation flag of the initial driving area to inactive. When the driving area is inactive, it indicates that a collision may occur while driving in that driving area. That is, the initial driving area determined based on the first obstacle information is inaccurate.

[0094] In another example, the process of generating the activation identifier may include:

[0095] If the initial driving area does not include information on the first obstacle and the second obstacle, then the activation flag for the initial driving area is set to "Active". If the initial driving area includes information on the first obstacle and the second obstacle, then the activation flag for the initial driving area is set to "Inactive". If the initial driving area includes information on the first obstacle but not the second obstacle, then the activation flag for the initial driving area is set to "High Risk". If the initial driving area does not include information on the first obstacle but includes information on the second obstacle, then the activation flag for the initial driving area is set to "High Risk".

[0096] S205. Generate final decision information based on the activation marker of the initial driving area.

[0097] In this embodiment, the microcontroller in the controller can determine the final decision it needs to execute based on the activation flags of each initial driving area, and then generate final decision information. Optionally, the activation flag may indicate that the initial driving area is activated or deactivated. If the activation flag indicates that the initial driving area is activated, the microcontroller in the controller can generate final decision information based on the activated initial driving area. If the activation flag indicates that the initial driving area is deactivated, the microcontroller in the controller can delete the deactivated drivable area from the decision information.

[0098] In one example, the process by which the microcontroller in the controller generates the final decision information may include:

[0099] Step 1: If the activation flag of the lateral initial driving area corresponding to the initial decision information is activatable, then determine the final decision information to instruct the vehicle to control the vehicle to make an emergency turn based on the lateral initial driving area where the activation flag is activatable.

[0100] In this step, after receiving the initial decision information, the microcontroller in the controller first checks the activation flag of the lateral initial driving area corresponding to the initial decision information. If the activation flag of the lateral initial driving area is active, the microcontroller in the controller can determine that the final decision information is to perform an emergency turn based on the active lateral initial driving area. Optionally, when multiple lateral initial driving area activation flags are active, the microcontroller in the controller can determine the final steering angle for the emergency turn based on the steering angle corresponding to each initial driving area. Optionally, the microcontroller in the controller can select the minimum steering angle.

[0101] Step 2: If the activation markers of the lateral initial driving area corresponding to the initial decision information are all inactive, then determine whether the activation markers of the forward initial driving area corresponding to the initial decision information are active.

[0102] In this step, if the activation markers of all lateral initial driving areas corresponding to the initial decision information are inactive, the microcontroller in the controller further determines the activation markers of the forward initial driving area.

[0103] Step 3: If the activation flag of the forward initial driving area corresponding to the initial decision information is activatable, then determine that the final decision information instructs the vehicle to control the vehicle to brake urgently according to the forward initial driving area where the activation flag is activatable.

[0104] In this step, when the activation flag of the forward initial driving area is activated, the microcontroller in the controller then determines the final decision information. This final decision information instructs the vehicle to perform emergency braking measures based on the forward initial driving area.

[0105] Step 4: If all activation markers for the initial lateral driving area corresponding to the initial decision information are inactive, then generate the first warning message. The first warning message is used to alert the user that a collision cannot be avoided when steering.

[0106] In this step, if all activation markers for the initial lateral driving area corresponding to the initial decision information are inactive, it indicates that a collision cannot be avoided by steering. At this time, the microcontroller in the controller will immediately generate a first warning message to alert the user. This first warning message is used to alert the user that a lateral collision cannot be avoided.

[0107] Step 5: If all activation markers for the forward initial driving area corresponding to the initial decision information are inactive, a second warning message is generated. The second warning message is used to alert the user that braking cannot avoid a collision.

[0108] In this step, if the lateral areas are not feasible, the microcontroller in the controller then checks the activation indicators of the forward initial driving area. If all the activation indicators of the forward initial driving area are also inactive, it means that emergency braking will not avoid a collision. At this time, the microcontroller in the controller will generate a second alarm message to warn the user. This second alarm message is used to remind the user that a forward collision cannot be avoided.

[0109] The assisted driving method provided in this application embodiment allows the microcontroller in the controller to store recognition models corresponding to each sensor. The microcontroller in the controller can use these recognition models to identify sensor data from each sensor, obtaining third obstacle information corresponding to each sensor data. The microcontroller in the controller fuses and filters the third obstacle information corresponding to each sensor data, eliminating redundant or erroneous obstacle information to obtain more accurate second obstacle information. The microcontroller in the controller can extract at least one initial driving area from this initial decision information. The microcontroller in the controller can generate corresponding activation markers for each initial driving area based on the first and second obstacle information. Based on the activation markers of each initial driving area, the microcontroller in the controller determines the final decision to be executed, thereby generating final decision information. By using the recognition models stored in the microcontroller to identify, fuse, and filter sensor data to obtain accurate second obstacle information, and combining this with the first obstacle information to generate activation markers for the initial driving areas, and then generating and executing final decision information based on the activation markers, the method aims to improve vehicle safety.

[0110] Based on the above embodiments, the microcontroller in the controller can further add the following judgment during the generation of final decision information to improve the effectiveness of the final decision information, enhance vehicle safety, and enable it to meet ASIL D safety requirements. The specific process may include:

[0111] S301. If the final decision information instructs the vehicle to perform emergency steering or emergency braking, then determine whether the control module used to perform emergency braking or emergency steering is abnormal.

[0112] In this embodiment, when the microcontroller in the controller determines that the final decision information instructs the vehicle to perform emergency steering or emergency braking, it can access the control module used for performing emergency braking or emergency steering to determine whether the control module used for performing emergency braking or emergency steering is malfunctioning. Optionally, in S205, the microcontroller in the controller can also access the control module used for performing emergency steering when it determines that emergency steering needs to be performed, to determine whether the control module used for performing emergency steering is malfunctioning. Optionally, the microcontroller in the controller can also access the control module used for performing emergency braking when it determines that emergency braking needs to be performed, to determine whether the control module used for performing emergency braking is malfunctioning. Optionally, malfunctions may include response delays, signal instability, functional failures, etc.

[0113] S302. If the control module used to perform emergency braking or emergency steering malfunctions, a third prompt message is generated. The third prompt message is used to notify the user that the control module used to perform emergency braking or emergency steering malfunctions.

[0114] In this embodiment, the microcontroller in the controller can also generate a third prompt message when the control module used to perform emergency braking or emergency steering is malfunctioning, so as to inform the user that the control module used to perform emergency braking or emergency steering is currently malfunctioning, so as to ensure that the user can understand in time and take possible countermeasures to ensure driving safety.

[0115] Optionally, the microcontroller in the controller can also generate a third warning message in S205 if it determines that an emergency steering operation is required and the emergency steering control module is malfunctioning. Subsequently, the microcontroller in the controller can generate a third warning message in S205 if it determines that an emergency braking operation is required and the emergency braking control module is malfunctioning.

[0116] Based on the above embodiments, such as Figure 6As shown, based on the above architecture, the AES (Autonomous Assist System) is powered on synchronously after the vehicle starts up. The perception system transmits environmental perception information to the autonomous driving control module through relevant channels. After processing and recognizing the information, the autonomous driving control module sends forward and lateral control commands to the gateway via the CAN bus. The gateway then forwards the forward control commands to the emergency braking control module and the emergency steering control module via two CAN buses, and forwards the Human Machine Interface (HMI) control signals to the human-machine interaction control module via another CAN bus, thereby realizing the vehicle's driver assistance control. The specific process may include:

[0117] S401, The vehicle controller can control the vehicle to start.

[0118] S402, The vision processing module processes obstacles perceived by the vision module.

[0119] In this embodiment, the vision processing module acquires video information from the front of the vehicle captured by the front-view camera module and video information from the sides of the vehicle captured by the panoramic camera module through a deserializer. The vision processing module then processes this video information to obtain obstacle information. This obstacle information may specifically include vehicles, pedestrians, stationary objects, etc. The vision processing module can also calculate the relative position information between the vehicle and the obstacles, as well as the motion attributes of the obstacles. The motion attributes of the obstacles may include velocity, lateral acceleration, longitudinal acceleration, and heading angle. The vision processing module can then transmit this obstacle information to the perception fusion module. This vision processing module is developed according to ASIL B level.

[0120] S403, the perception fusion module fuses the forward-looking radar target and the visually processed target.

[0121] In this embodiment, the perception fusion module can match and fuse the first obstacle information transmitted from the vision processing module with the obstacles identified by external sensors such as corner radar, lidar, and forward radar. The perception fusion module can also reconstruct the coordinates of the obstacles based on the vehicle's own coordinate system to obtain the first obstacle information. The perception fusion module can then transmit this first obstacle information to the decision-making and planning module. This perception fusion module is developed according to ASIL B level.

[0122] S404, the decision planning module determines whether the conditions for triggering AEB have been met.

[0123] In this embodiment, the decision planning module determines whether there is an obstacle ahead that poses a collision risk to the vehicle based on the first obstacle information. If so, the conditions for triggering AEB are met.

[0124] S405, the decision planning module plans the AEB deceleration / AES steering angle.

[0125] In this embodiment, when the decision planning module determines that AEB needs to be triggered, it can perform AEB deceleration planning. Simultaneously, the decision planning module can also perform AES steering angle planning by determining the lateral drivable area. The decision planning module ultimately calculates the AEB deceleration and AES steering angle, forming initial decision information. The controller's system chip can output this initial decision information to the AEB / AES arbitration module. This decision planning module is developed according to ASIL B level.

[0126] S406, The lateral hazard target judgment module determines whether there is an obstacle.

[0127] In this embodiment, the lateral hazard target determination module can receive first obstacle information identified by the vision module. This first obstacle information may include obstacles such as vehicles, people, and guardrails. Simultaneously, the lateral hazard target determination module can also receive obstacle information input from the corner radar. Within the designated initial driving area of ​​the AES function, the lateral hazard target module performs obstacle target screening. If an obstacle exists in the initial driving area, a hazard target marker is recorded as present. If no obstacle exists, the hazard target marker is recorded as absent. The microcontroller in the controller can transmit the lateral hazard target markers to the AEB / AES arbitration module. This lateral hazard target determination module is developed according to ASIL D level.

[0128] S407. Is the emergency braking control module faulty?

[0129] In this embodiment, the AES / AEB arbitration module determines whether AES and AEB need to be activated based on the initial decision information input by the decision planning module. When it is determined that there is an obstacle ahead, and a collision cannot be avoided by triggering AEB, and there is a dangerous target to the side, it is necessary to determine whether the emergency braking control module is malfunctioning.

[0130] S408, AEB / AES arbitration module arbitration triggers AEB function.

[0131] In this embodiment, when the AES / AEB arbitration module determines that there is no fault in the braking system, it outputs an AES control request to the AEB control module. The AES / AEB arbitration module is developed according to ASIL D level.

[0132] S409 and AEB control modules output control commands.

[0133] In this embodiment, the AEB controller outputs a deceleration control command to the braking system.

[0134] The S410 and AEB / AES arbitration modules suppress the triggering of the AEB function and issue a fault message indicating that AEB cannot be activated.

[0135] In this embodiment, if the AES / AEB arbitration module determines that the emergency braking control module is faulty, it will suppress the activation of the AEB function and send a fault message to the HMI indicating that the AEB function cannot be activated.

[0136] The S411 AEB / AES arbitration module suppresses the triggering of the AES function and issues a fault message indicating that AES cannot be activated.

[0137] In this embodiment, when the AES / AEB arbitration module determines that there is a fault in the steering control module, it inhibits the activation of the AES function and sends a fault message to the HMI indicating that the AES function cannot be activated.

[0138] S412. Is the emergency steering control module faulty?

[0139] In this embodiment, the AES / AEB arbitration module determines whether AES and AEB need to be activated based on the information input from the decision planning module. If an obstacle is detected ahead, and triggering AEB cannot avoid a collision, and there are no obstacles to the side, then it is necessary to determine if the steering control module is malfunctioning. Specifically, if an obstacle is detected ahead, and triggering AEB cannot avoid a collision, and there are no obstacles to the side, the AES / AEB arbitration module can determine that an emergency steering maneuver is required.

[0140] S413, AEB / AES arbitration module triggers AES function during arbitration.

[0141] In this embodiment, if the AES / AEB arbitration module determines that the steering control module is fault-free, it will output an AES control request to the AES control module.

[0142] S414, AES control module outputs control commands.

[0143] In this embodiment, the AES module outputs steering control commands to the steering system.

[0144] Figure 7 A schematic diagram of the assisted driving device provided in this application is shown below. Figure 7 As shown, the driver assistance device 500 provided in this embodiment is applied to a vehicle. The vehicle's controller includes a system chip with safety level B and a microcontroller with safety level D, comprising:

[0145] The first processing module 501 is used to generate first obstacle information and initial decision information in the system chip based on the sensor data collected by each sensor among multiple sensors in the vehicle; wherein, the initial decision information represents the initial decision of the vehicle's assisted driving, and the first obstacle information is obstacle recognition information of safety level B.

[0146] The second processing module 502 is used to generate and execute the final decision information for assisted driving of the vehicle with safety level D based on the initial decision information, the first obstacle information and the data from each sensor.

[0147] Optionally, the second processing module 501 is used for:

[0148] Based on the data from each sensor, a second obstacle information is generated; the second obstacle information is obstacle recognition information at safety level D.

[0149] Based on the information about the first obstacle and the second obstacle, the initial decision information is optimized to obtain the final decision information.

[0150] Optionally, the second processing module 501 is used for:

[0151] The data from each sensor is identified to obtain the third obstacle information corresponding to each sensor data.

[0152] The information on the third obstacle is fused and filtered to obtain the information on the second obstacle.

[0153] Optionally, the second processing module 501 is used for:

[0154] The third obstacle information is filtered based on the probability thresholds corresponding to the data from each sensor to obtain the fourth obstacle information;

[0155] The fourth obstacle information corresponding to the data from each sensor is fused and matched to obtain the fifth obstacle information;

[0156] The information of the fifth obstacle is filtered according to the preset fusion threshold to obtain the information of the second obstacle.

[0157] Optionally, the second processing module 501 is used for:

[0158] Match the fourth obstacle information corresponding to each sensor data to obtain the sixth obstacle information corresponding to each sensor data;

[0159] Based on the probability weights corresponding to each sensor data, the sixth obstacle information corresponding to each sensor data is weighted and fused to obtain the fifth obstacle information.

[0160] Optionally, the second processing module 501 is used for:

[0161] Based on the initial decision information, at least one initial driving area is determined;

[0162] Based on the information of the first obstacle and the second obstacle, generate an activation marker for the initial driving area;

[0163] The final decision information is generated based on the activation marker of the initial driving area.

[0164] Optionally, the second processing module 501 is used for:

[0165] If the initial driving area does not include information on the first obstacle and the second obstacle, then the activation flag of the initial driving area is activated.

[0166] If the initial driving area includes information about a first obstacle and / or a second obstacle, then the activation flag of the initial driving area is set to non-activatable.

[0167] Optionally, the second processing module 501 is used for:

[0168] If the activation flag of the lateral initial driving area corresponding to the initial decision information is activatable, then the final decision information is determined to instruct the vehicle to make an emergency turn based on the lateral initial driving area where the activation flag is activatable.

[0169] If the activation markers of the lateral initial driving area corresponding to the initial decision information are all inactive, then determine whether the activation markers of the forward initial driving area corresponding to the initial decision information are active.

[0170] If the activation flag of the forward initial driving area corresponding to the initial decision information is activatable, then the final decision information instructs the vehicle to control emergency braking based on the forward initial driving area where the activation flag is activatable.

[0171] Optionally, the second processing module 501 is used for:

[0172] If all activation markers for the initial driving area in the lateral direction corresponding to the initial decision information are inactive, a first warning message is generated; the first warning message is used to prompt the user that a collision cannot be avoided when steering.

[0173] If the activation markers of the forward initial driving area corresponding to the initial decision information are all inactive, a second alarm message is generated; the second alarm message is used to prompt the user that braking cannot avoid a collision.

[0174] Optionally, the first processing module 501 is used for:

[0175] The data from each sensor is identified to obtain the third obstacle information corresponding to each sensor data.

[0176] By matching the third obstacle information corresponding to the data from each sensor, the first obstacle information is obtained;

[0177] Initial decision information is generated based on the information about the first obstacle.

[0178] Optionally, the second processing module 501 is used for:

[0179] If the final decision information instructs the vehicle to perform emergency steering or emergency braking, then determine whether the control module used to perform emergency braking or emergency steering is abnormal;

[0180] If the control module used to perform emergency braking or emergency steering malfunctions, a third prompt message is generated; the third prompt message is used to notify the user that the control module used to perform emergency braking or emergency steering malfunctions.

[0181] The assisted driving device provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0182] Figure 8 This is a schematic diagram of the controller provided in this application. Figure 8 As shown, the controller 600 provided in this embodiment includes a system chip and a microprocessor. The system chip and the microprocessor may each include at least one processing unit 601 and a storage unit 602. Optionally, the controller 600 further includes a communication component 603. The processing unit 601, the storage unit 602, and the communication component 603 are connected via a bus 604.

[0183] In a specific implementation, at least one processing unit 601 executes computer execution instructions stored in the storage unit 602, causing at least one processing unit 601 to perform the above-described method.

[0184] The specific implementation process of the processing unit 601 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0185] In the above embodiments, it should be understood that the processing unit can be a Central Processing Unit (CPU), or other general-purpose processing units, digital signal processing units (DSPs), application-specific integrated circuits (ASICs), etc. A general-purpose processing unit can be a microprocessor unit or any conventional processing unit. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processing unit, or execution by a combination of hardware and software modules within the processing unit.

[0186] The storage unit may include high-speed storage units (Random Access Memory, RAM) and may also include non-volatile storage units (NVM), such as at least one disk storage unit.

[0187] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0188] This application also provides a vehicle including multiple sensors and such as Figure 7 The controller shown is used to execute and implement the methods described above.

[0189] This application also provides a computer program product, including a computer program that, when executed by a processing unit, implements the above-described method.

[0190] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processing unit, implement the above-described method.

[0191] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0192] An exemplary readable storage medium is coupled to a processing unit, enabling the processing unit to read information from and write information to the readable storage medium. Alternatively, the readable storage medium can be an integral part of the processing unit. Both the processing unit and the readable storage medium can reside in an application-specific integrated circuit (ASIC). Alternatively, the processing unit and the readable storage medium can exist as discrete components within the device.

[0193] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0194] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0195] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0196] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0197] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0198] The above embodiments are merely preferred embodiments provided to fully illustrate this application, and the scope of protection of this application is not limited thereto. Equivalent substitutions or modifications made by those skilled in the art based on this application are all within the scope of protection of this application.

Claims

1. A driving assistance method, characterized in that, Applied to vehicles, wherein the vehicle's controller includes a system chip with safety level B and a microcontroller with safety level D, the method includes: Based on sensor data collected by each of the multiple sensors in the vehicle, first obstacle information and initial decision information are generated in the system chip; wherein, the initial decision information represents the initial decision of the vehicle's assisted driving, and the first obstacle information is obstacle recognition information of safety level B; Based on the data from each sensor, a second obstacle information is generated; the second obstacle information is obstacle recognition information at safety level D. Based on the initial decision information, at least one initial driving area is determined; Based on the first obstacle information and the second obstacle information, an activation identifier for the initial driving area is generated; Based on the activation identifier of the initial driving area, final decision information is generated.

2. The method according to claim 1, characterized in that, Based on data from each sensor, second obstacle information is generated, including: The data from each sensor is identified to obtain the third obstacle information corresponding to each sensor data. The third obstacle information is fused and filtered to obtain the second obstacle information.

3. The method according to claim 2, characterized in that, The third obstacle information is fused and filtered to obtain the second obstacle information, including: The third obstacle information is filtered based on the probability thresholds corresponding to the data from each sensor to obtain the fourth obstacle information; The fourth obstacle information corresponding to the data from each sensor is fused and matched to obtain the fifth obstacle information; The fifth obstacle information is filtered according to a preset fusion threshold to obtain the second obstacle information.

4. The method according to claim 3, characterized in that, The fourth obstacle information corresponding to the data from each sensor is fused and matched to obtain the fifth obstacle information, including: The fourth obstacle information corresponding to each sensor data is matched to obtain the sixth obstacle information corresponding to each sensor data; Based on the probability weights corresponding to each sensor data, the sixth obstacle information corresponding to each sensor data is weighted and fused to obtain the fifth obstacle information.

5. The method according to claim 1, characterized in that, Based on the first obstacle information and the second obstacle information, an activation identifier for the initial driving area is generated, including: If the initial driving area does not include the first obstacle information and the second obstacle information, then the activation flag of the initial driving area is activated; If the initial driving area includes the first obstacle information and / or the second obstacle information, then the activation flag of the initial driving area is inactive.

6. The method according to claim 1, characterized in that, Based on the activation identifier of the initial driving area, the final decision information is generated, including: If the activation flag of the initial driving area corresponding to the initial decision information is activatable, then the final decision information is determined to instruct the vehicle to make an emergency turn based on the initial driving area where the activation flag is activatable. If all the activation markers of the initial driving area in the lateral direction corresponding to the initial decision information are inactive, then determine whether the activation markers of the initial driving area in the forward direction corresponding to the initial decision information are active. If the activation flag of the forward initial driving area corresponding to the initial decision information is activatable, then the final decision information instructs the vehicle to control emergency braking based on the forward initial driving area where the activation flag is activatable.

7. The method according to claim 6, characterized in that, The method further includes: If all activation markers of the initial driving area corresponding to the initial decision information are inactive, a first alarm message is generated; the first alarm message is used to prompt the user that a collision cannot be avoided when turning. If all activation markers of the forward initial driving area corresponding to the initial decision information are inactive, a second alarm message is generated; the second alarm message is used to prompt the user that braking cannot avoid a collision.

8. The method according to claim 1, characterized in that, Based on sensor data collected by each of the multiple sensors in the vehicle, first obstacle information and initial decision information are generated in the system chip, including: The data from each sensor is identified to obtain the third obstacle information corresponding to each sensor data. The first obstacle information is obtained by matching the third obstacle information corresponding to the data from each sensor; The initial decision information is generated based on the first obstacle information.

9. The method according to any one of claims 1-8, characterized in that, The method further includes: If the final decision information instructs the vehicle to perform emergency steering or emergency braking, then it is determined whether the control module used to perform the emergency braking or emergency steering is malfunctioning. If the control module used to perform the emergency braking or the emergency steering malfunctions, a third prompt message is generated; the third prompt message is used to notify the user that the control module used to perform the emergency braking or the emergency steering malfunctions.

10. A driver assistance device, characterized in that, Applied to vehicles, the vehicle including a system chip with safety level B and a microcontroller with safety level D, the device includes: The first processing module is used to generate first obstacle information and initial decision information in the system chip based on sensor data collected by each of the multiple sensors in the vehicle; wherein, the initial decision information represents the initial decision of the vehicle's assisted driving, and the first obstacle information is obstacle recognition information of safety level B. The second processing module is used to generate second obstacle information based on data from various sensors; the second obstacle information is obstacle identification information of safety level D; determine at least one initial driving area based on the initial decision information; generate an activation identifier for the initial driving area based on the first obstacle information and the second obstacle information; and generate final decision information based on the activation identifier of the initial driving area.

11. A controller, characterized in that, The controller includes: a system chip and a microprocessor; The system chip and the microprocessor respectively include a storage unit and a processing unit; The storage unit stores computer execution instructions; the processing unit executes the computer execution instructions stored in the storage unit, causing the processing unit to perform the method as described in any one of claims 1-9.

12. A vehicle, characterized in that, The vehicle includes: a plurality of sensors and a controller as described in claim 11.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by the processing unit, are used to implement the method as described in any one of claims 1-9.

14. A computer program product comprising a computer program that, when executed by a processing unit, implements the method of any one of claims 1-9.

Images