Brake control system for vehicle

Abstract

The invention discloses a brake control system of a vehicle. The system comprises a first decision control link which comprises a first sensing module, a decision planning module and a first control module, a first sensing result of the first sensing module is used for outputting to the decision planning module, and a first decision planning result of the decision planning module is used for outputting to the first control module, the first control module is used for determining whether braking operation of the vehicle needs to be triggered or not according to the first decision planning result; the second decision control link comprises a second sensing module and a second control module, a second sensing result of the second sensing module is used for being output to the second control module, and the second control module is used for determining whether braking operation of the vehicle needs to be triggered or not according to the second sensing result.

Description

Technical Field

[0001] The present application relates to the fields of autonomous driving technology and unmanned vehicle technology, and more specifically, to a vehicle braking control system. Background Art

[0002] In the autonomous driving sector, vehicle safety is paramount, particularly emergency braking capabilities in the face of emergencies. Traditional Automatic Emergency Braking (AEB) systems are primarily designed to assist human drivers, integrating multiple internal and external vehicle information to determine potential collision risks and proactively slowing or stopping the vehicle when necessary to avoid or mitigate collision damage. However, AEB has not been effective in autonomous driving scenarios.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] An embodiment of the present application provides a vehicle braking control system to at least solve the problems in the related art.

[0005] According to one aspect of an embodiment of the present application, a vehicle braking control system is provided, comprising: a first decision control link, including a first perception module, a decision planning module and a first control module, the first perception result of the first perception module is used to be output to the decision planning module, the first decision planning result of the decision planning module is used to be output to the first control module, and the first control module is used to determine whether it is necessary to trigger the vehicle's braking operation according to the first decision planning result; a second decision control link, including a second perception module and a second control module, the second perception result of the second perception module is used to be output to the second control module, and the second control module is used to determine whether it is necessary to trigger the vehicle's braking operation according to the second perception result; wherein the relationship between the first perception module and the second perception module includes one of the following: the first perception module and the second perception module are the same perception module, the first perception module and the second perception module are different perception modules, the first perception module includes the second perception module, and the second perception module includes the first perception module.

[0006] Optionally, the first control module is used to determine a first distance between the vehicle and an obstacle within a first preset range from the vehicle based on the first decision planning result, and determine that a braking operation of the vehicle needs to be triggered when the first distance meets a target distance condition; the second control module is used to determine a second distance between the vehicle and an obstacle within a second preset range from the vehicle based on the second perception result, and determine that a braking operation of the vehicle needs to be triggered when the second distance meets the target distance condition.

[0007] Optionally, the first control module is used to execute a first mode for determining whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result in a first situation; the second control module is used to execute a second mode for determining whether it is necessary to trigger the vehicle's braking operation based on the second perception result in a second situation; wherein the second situation is used to indicate that the first mode fails, or the obstacle detected using the first decision planning result does not meet the target distance condition but the obstacle detected using the second perception result meets the target distance condition.

[0008] Optionally, the first decision control link also includes: a fusion module, the first perception module is connected to the fusion module, the fusion module is connected to the decision planning module, and the decision planning module is connected to the first control module; wherein the fusion module is used to fuse the multi-source perception information obtained by multiple perception sources in the first perception module, the decision planning module is used to perform decision planning based on the fusion processing result to obtain a first decision planning result, the first control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result; the second control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the second perception result.

[0009] Optionally, the first decision control link also includes: a prediction module, a first perception module connected to the fusion module, the fusion module connected to the prediction module, the prediction module connected to the decision planning module, and the decision planning module connected to the first control module; wherein the prediction module is used to perform prediction processing on the movement behavior or running position of the obstacle in the future time period based on the fusion processing result to obtain a prediction result, the decision planning module is used to perform decision planning based on the prediction result to obtain a first decision planning result, and the first control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result; the second control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the second perception result.

[0010] Optionally, the first perception module or the second perception module is used to obtain obstacle information through at least one of the following perception devices: a local perception device, a global perception device; or, the first perception module or the second perception module is used to obtain obstacle information through at least one of the following sensors: a lidar, a camera, and a millimeter-wave radar.

[0011] Optionally, the local perception device includes at least a vehicle-mounted perception device, and the global perception device includes at least a V2X device.

[0012] Optionally, the first perception module is used to obtain obstacle information through local perception devices and global perception devices, and the second perception module is used to obtain obstacle information only through local perception devices; or, the first perception module is used to obtain obstacle information through at least two of a lidar, a camera, and a millimeter-wave radar, and the second perception module is used to obtain obstacle information through a lidar.

[0013] Optionally, the first perception module is a multi-source perception module, and the second perception module is a single-source perception module; or, the first perception module is a single-source perception module, and the second perception module is a multi-source perception module; wherein, the source of the perception information of the multi-source perception module is multiple sources, and the source of the perception information of the single-source perception module is a single source.

[0014] Optionally, the first decision control link is deployed in a first chip of the vehicle, and the second decision control link is deployed in a second chip of the vehicle.

[0015] Optionally, the first control module and the second control module are the same control module.

[0016] In an embodiment of the present application, a vehicle braking control system is provided, including: a first decision control link, including a first perception module, a decision planning module and a first control module, the first perception result of the first perception module is used to output to the decision planning module, the first decision planning result of the decision planning module is used to output to the first control module, and the first control module is used to determine whether it is necessary to trigger the vehicle's braking operation according to the first decision planning result; a second decision control link, including a second perception module and a second control module, the second perception result of the second perception module is used to output to the second control module, and the second control module is used to determine whether it is necessary to trigger the vehicle's braking operation according to the second perception result; wherein the relationship between the first perception module and the second perception module includes one of the following: the first perception module and the second perception module are the same perception module, the first perception module and the second perception module are different perception modules, the first perception module includes the second perception module, and the second perception module includes the first perception module.

[0017] Specifically, in this embodiment of the present application, the vehicle's braking control system is equipped with two decision-making control links: a first decision-making control link and a second decision-making control link. By introducing two independent decision-making control links, even if the first decision-making control link fails in any of its sensing, decision-making, or control stages, the second decision-making control link can immediately intervene and independently trigger the vehicle's braking operation based on its own sensing results and control logic, significantly enhancing the safety of the vehicle's braking control system. Furthermore, the sensing module in the second decision-making control link is directly connected to the control module, reducing data processing and decision-making time. When an emergency occurs, the control module in the second decision-making control link can directly receive sensing information from the sensing module and quickly determine whether to trigger the vehicle's braking operation, without requiring the complex calculations of the decision-making and planning module. This significantly accelerates the response time of emergency braking. Furthermore, the first and second control modules operate independently, reducing the risks associated with interdependence between the modules. Even if the first decision-making control link fails completely, the second decision-making control link can still independently complete the entire emergency braking process, ensuring reliable braking under extreme conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a schematic diagram of a vehicle braking control system according to an embodiment of the present application;

[0020] Figure 2 is a schematic diagram of a first decision control link according to an embodiment of the present application;

[0021] Figure 3 This is a schematic diagram of another first decision control link according to an embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0023] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequential order. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0024] In the field of unmanned driving, the safety of vehicles is of vital importance, especially the emergency braking capability in the face of emergencies. Traditional Automatic Emergency Braking (AEB) systems are designed mainly to assist manual driving. They judge potential collision risks by integrating multiple information sources inside and outside the vehicle, and actively slow down or stop the vehicle when necessary to avoid or reduce collision damage. However, in unmanned driving scenarios, the decision-making control logic of the AEB system is based on the main link of autonomous driving, in which data analysis and decision-making control functions are integrated. If any link in the main driving link fails, the vehicle's emergency braking function will not be able to start normally, thereby affecting the safety of the vehicle. Therefore, in order to solve this problem, this application proposes a vehicle braking control system.

[0025] According to an embodiment of the present application, an embodiment of a vehicle braking control system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0026] Figure 1 is a schematic diagram of a vehicle braking control system according to an embodiment of the present application, such as Figure 1 As shown, the vehicle braking control system 10 includes a first decision control link 11 and a second decision control link 12 .

[0027] The first decision control link 11 includes a first perception module 111, a decision planning module 112, and a first control module 113. The first perception result of the first perception module 111 is output to the decision planning module 112, and the first decision planning result of the decision planning module 112 is output to the first control module 113. The first control module 113 is configured to determine whether to trigger a vehicle braking operation based on the first decision planning result.

[0028] In this embodiment, the first perception module 111 is a front-end device in the first decision-making control link, which is used to collect obstacle information about the vehicle's surrounding environment. The first perception module can perceive obstacle information around the vehicle through a multi-source perception method, where the multi-source perception method is used to indicate that obstacle information is perceived through multiple perception sources. For example, the first perception module can perceive obstacle information around the vehicle through multiple sensor devices. The multiple sensor devices include, but are not limited to, lidar, binocular cameras, fisheye cameras, millimeter-wave radars, etc. Alternatively, the first perception module can also perceive obstacle information around the vehicle through local perception devices and global perception devices, which are not specifically limited here.

[0029] Optionally, the first perception module preprocesses the obstacle information obtained through multi-source perception, such as filtering, noise reduction, coordinate conversion, etc., and then integrates it into a first perception result in a unified format for analysis and processing by the subsequent decision-making and planning module.

[0030] Optionally, the decision-making planning module 112 is a core component of the first decision-making control link. It can receive the first perception result transmitted by the first perception module and perform data analysis on the first perception result to obtain a first decision-making planning result. For example, after receiving the first perception result, the decision-making planning module can analyze the obstacle type, distance, speed, and other information in the first perception result to determine the vehicle's current driving environment. Based on the analyzed information, it can calculate the potential collision risk and, based on the risk assessment results, determine whether to trigger the vehicle to perform a braking operation and the timing of braking.

[0031] Optionally, the first control module 113 is the direct executor of the first decision-making planning link. After receiving the first decision-making planning result from the decision-making planning module, the first control module can convert the decision-making planning result into a braking operation instruction to control the execution of the braking operation. Optionally, to ensure the effectiveness and accuracy of the braking operation, the first control module 113 can also include a feedback loop to monitor the vehicle's braking process and adjust the braking strategy based on actual conditions.

[0032] Optionally, the first decision-making control loop, a complete closed-loop system encompassing environmental perception of the vehicle's surroundings, decision-making and planning, and braking execution, is used to control the braking operations of the autonomous vehicle during normal driving. This first decision-making control loop not only accurately and promptly identifies and assesses potential collision risks but also independently determines whether and how to brake based on the severity of the risk, effectively preventing or mitigating vehicle collisions. This is a key component in ensuring the safe operation of autonomous vehicles.

[0033] The second decision control link 12 includes a second perception module 121 and a second control module 122. The second perception result of the second perception module 121 is output to the second control module 122, and the second control module 122 is used to determine whether to trigger the vehicle braking operation according to the second perception result.

[0034] In this embodiment, the second decision control link 12 exists in parallel with the first decision control link 11 , and together they form a redundant and safe emergency braking system.

[0035] Alternatively, as Figure 1 As shown, in the second decision control link 12, the second perception module 121 is directly connected to the second control module 122, that is, the obstacle information around the vehicle perceived by the second perception module 121 can be directly transmitted to the second control module without the access of other modules in the middle. The information transmission path is greatly shortened, which helps to reduce the time delay from perception to decision-making when an obstacle is detected, and ensure the immediacy of the braking operation, which is especially important for vehicles traveling at high speeds.

[0036] Optionally, the second perception module 121 is a front-end information collection device in the second decision-making control link. This second perception module can be the same as or different from the first perception module. The second perception module 121 is used to monitor the vehicle's surroundings in real time, including but not limited to the distance, speed, and direction of obstacles ahead, as well as the vehicle's own motion state.

[0037] Optionally, the second perception module 121 may include one or more types of sensors, such as radar, lidar, camera, inertial measurement unit, V2X equipment, etc., to obtain comprehensive perception information. These devices can cover different perception ranges and angles, ensuring that the perception results of the second decision link are as comprehensive and accurate as possible.

[0038] Optionally, the second control module 122 is configured to receive the second perception result from the second perception module 121 and independently determine whether emergency braking needs to be triggered based on the second perception result, and to determine the braking force and timing. For example, the second control module 122 may include independent decision-making logic for assessing potential collision risks. This logic may rapidly generate a braking strategy based on factors such as preset safety thresholds, the approaching speed and distance of the obstacle, and so on. If a collision risk is determined, an emergency braking command will be immediately issued to control the vehicle to perform the braking operation.

[0039] Optionally, the second decision-making control link acts as an independent redundancy mechanism. Its direct connection design allows it to immediately initiate and independently complete the entire emergency braking process if the first decision-making control link fails. Even in the extreme case of a failure in the first decision-making control link, the second control module in the second decision-making control link can quickly respond based on the data from the second perception module, ensuring vehicle driving safety.

[0040] As an optional embodiment, the relationship between the first perception module and the second perception module includes one of the following: the first perception module and the second perception module are the same perception module, the first perception module and the second perception module are different perception modules, the first perception module includes the second perception module, and the second perception module includes the first perception module.

[0041] In this embodiment, the first perception module and the second perception module are the same perception module, which means that the first perception module and the second perception module can be the same group of perception devices. That is, the first perception module and the second perception module share the same sensor (such as radar, camera, lidar, etc.). Since the first decision control link and the second decision control link are based on the same perception data input, the two links can provide consistent perception results under normal operation, but redundancy is achieved through different algorithms or logic at the decision level. Doing so can reduce hardware costs while maintaining a high level of information consistency and ensuring that the two decision links make decisions based on similar inputs.

[0042] Optionally, the first and second perception modules are distinct, meaning they can be independent hardware devices, each with its own corresponding sensor and data processing unit. This design primarily aims to increase perception diversity and redundancy in the vehicle's braking control system. With independent perception links, even if a problem arises with the perception device or data processing unit in one decision-making control link, the other decision-making control link can still operate normally, thereby ensuring the stability and reliability of the emergency braking system.

[0043] Optionally, the first perception module includes the second perception module, meaning that the second perception module is a subset or portion of the first perception module. In other words, the first perception module is a more comprehensive perception system that can process and analyze information from multiple sensors, while the second perception module focuses on processing a specific set of sensor data within the first perception module. This design ensures that when the first perception module is operating normally, it can utilize all available information to make decisions. However, if a part of the first perception module fails, the second perception module, acting as a backup, can still provide the necessary perception results to support the normal operation of the second decision-making control link.

[0044] Optionally, the second perception module includes the first perception module, which means that the function of the first perception module is part of the second perception module. In this case, the second perception module may be a more integrated perception system with more sensor types and more powerful data processing capabilities. The first perception module, as a sub-module within it, can be regarded as an extraction of a specific function, such as focusing only on obstacle detection in front of the vehicle. This design emphasizes the leading role of the second perception module, while also ensuring that even when a problem occurs in a sub-part of the second perception module (i.e., the first perception module), the second perception module can still ensure that the basic functions of the second decision-making control link are not affected through the collaborative work of the remaining modules.

[0045] In the vehicle braking control system provided in the embodiments of the present application, two decision-making control links are provided: a first decision-making control link and a second decision-making control link. By introducing two independent decision-making control links, even if the first decision-making control link fails in any of the perception, decision-making planning, or control links, the second decision-making control link can immediately intervene and independently trigger the vehicle's braking operation based on its own perception results and control logic, greatly enhancing the safety of the system. Moreover, the perception module in the second decision-making control link is directly connected to the control module, reducing data processing and decision-making time. When an emergency occurs, the control module in the second decision-making control link can directly receive perception information from the perception module and quickly determine whether to trigger the vehicle's braking operation without going through the complex calculations of the decision-making planning module, thereby greatly accelerating the emergency braking response speed. Furthermore, the first and second control modules operate independently, reducing the risks associated with interdependence between the modules. Even if the first decision-making control link completely fails, the second decision-making control link can still independently complete the entire emergency braking process, ensuring the vehicle's braking reliability under extreme conditions. This solves the technical problem in related technologies of being unable to effectively control the vehicle's braking operation after the failure of the main autonomous driving link.

[0046] Next, the braking control system of the vehicle will be further introduced.

[0047] As an optional implementation, the first control module is used to determine a first distance between the vehicle and an obstacle within a first preset range from the vehicle based on a first decision-making planning result, and determine that a braking operation of the vehicle needs to be triggered when the first distance meets a target distance condition; the second control module is used to determine a second distance between the vehicle and an obstacle within a second preset range from the vehicle based on a second perception result, and determine that a braking operation of the vehicle needs to be triggered when the second distance meets the target distance condition.

[0048] In this embodiment, since the first decision control link and the second decision control link are two independent links, the first control module in the first decision control link can determine whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result. The second decision control link serves as a safety redundancy, and the second control module in the second decision control link is directly connected to the second perception module. Based on this, the second control module can directly determine whether it is necessary to trigger the vehicle's braking operation based on the second perception result. When either the first control module or the second control module determines that it is necessary to trigger the vehicle's braking operation, the vehicle is triggered to perform the braking operation. The independent design of the two links ensures that the two links can work in parallel without affecting each other. Even if one link fails, the other link can seamlessly take over, continuously monitor and make corresponding emergency braking decisions.

[0049] Optionally, the first control module is used to evaluate the distance between the vehicle and the obstacle in front after receiving the first decision planning result of the decision planning module, and then determine whether it is necessary to trigger the vehicle to perform a braking operation.

[0050] For example, the first control module calculates a first distance between the vehicle and an obstacle within a first preset range based on the obstacle information provided in the first decision-making planning result. The first preset range is a pre-set range for obtaining obstacle information. After obtaining the first distance, the first distance can be compared with a preset target distance condition to determine whether the first distance meets the target distance condition. If the first distance meets the target distance condition, a determination is made to trigger a braking operation for the vehicle.

[0051] Optionally, the second control module is similar to the first control module and is configured to directly receive the second sensing result from the second sensing module and determine a second distance between the vehicle and an obstacle within a second preset range from the vehicle based on the second sensing result. After determining the second distance, the second distance may be compared with a target distance condition to determine whether the two distances meet the target distance condition. If the first distance meets the target distance condition, a braking operation of the vehicle may be triggered.

[0052] Optionally, the target distance condition indicates that the distance between the vehicle and the nearest obstacle within the first preset range or the second preset range is less than a distance threshold. That is, if the first distance satisfies the target distance condition, then the distance between the vehicle and the nearest obstacle within the first preset range is less than the distance threshold. If the second distance satisfies the target distance condition, then the distance between the vehicle and the nearest obstacle within the second preset range is less than the distance threshold.

[0053] Optionally, the first control module and the second control module work independently. Even if one of the control modules fails, the other control module can still make braking decisions independently, providing system-level redundancy and safety protection.

[0054] Optionally, the direct perception and decision-making process of the second control module can quickly respond to emergency situations and avoid the risk of accidents caused by decision delays. This feature is particularly important in the event of a failure in the first decision-making control link.

[0055] Optionally, the complementary effects of the first control module and the second control module in ensuring vehicle braking safety together constitute a comprehensive, efficient and safe emergency braking control system, significantly improving the ability of unmanned vehicles to respond to emergencies.

[0056] As an optional implementation, the first control module is used to execute a first mode for determining whether it is necessary to trigger a braking operation of the vehicle based on a first decision-making planning result in a first situation; the second control module is used to execute a second mode for determining whether it is necessary to trigger a braking operation of the vehicle based on a second perception result in a second situation; wherein the second situation is used to indicate that the first mode fails, or the obstacle detected using the first decision-making planning result does not meet the target distance condition but the obstacle detected using the second perception result meets the target distance condition.

[0057] In this embodiment, when constructing the vehicle's braking control system, in order to ensure the stability and emergency response capability of the vehicle's braking control system, two independent decision control links are adopted: a first decision control link and a second decision control link, to achieve multiple safety redundancy.

[0058] Optionally, the core of the first decision control link lies in the first control module, which is used to execute a first mode in a first situation to determine whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result. That is, the first control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result under normal working conditions. The first decision planning result integrates data from multiple dimensions, such as the vehicle's current driving state, road environment information, obstacle location, and prediction model. When the first control module calculates that the first distance meets the preset target distance condition based on this information, it will activate the first mode, triggering an emergency braking operation to prevent a potential collision.

[0059] Optionally, a second decision-making control link serves as a backup and supplement to the first, primarily driven by a second control module. This second control module is directly connected to the second perception module, enabling direct access to obstacle information around the vehicle without the complex data processing required during the decision-making and planning phase. This design ensures the second control module can respond to emergencies immediately, making swift decisions based on the second perception results. The second perception results primarily focus on obstacle identification and immediate distance calculation from the vehicle.

[0060] Optionally, the failure of the first mode refers to the failure of the first control module in the first decision control link to work properly due to software or hardware failures. For example, a failure in any module in the first decision link, such as a failure in the first perception module, a failure in the decision planning module, or a failure in the first control module, will cause the first mode to fail. In addition, the cumulative error introduced in the calculation process of the decision result based on the first perception result by the first decision control link may also cause the first mode to fail. In the event of failure of the first mode, the second mode is immediately activated to take over the decision-making task of emergency braking. The second control module will independently make a judgment on whether to trigger braking based on the second perception result, without being affected by the first decision control link, to ensure that the vehicle's braking control system can still respond in an emergency.

[0061] Optionally, even if the first control module determines that emergency braking is not necessary based on the first decision-making plan, if the second perception module obtains a second perception result indicating that the obstacle's distance from the vehicle meets the target distance condition, the second mode will be activated. This means that the second control module will directly trigger the vehicle's braking operation based on the second perception result, providing additional protection for safe driving.

[0062] Optionally, the configuration of a first and second decision-control link ensures that autonomous vehicles can assess the necessity of emergency braking through multiple pathways when encountering potential obstacles. The first decision-control link is responsible for making braking decisions based on deep decision planning, while the second decision-control link provides a more direct and faster perception feedback mechanism. This design not only enhances the stability of the vehicle's braking control system but also improves the response speed to emergency situations, making it an indispensable component of achieving safe driving in autonomous driving technology. Through this complementary mechanism, the vehicle's braking control system can effectively respond to various unexpected situations.

[0063] As an optional implementation, the first decision control link also includes: a fusion module, the first perception module is connected to the fusion module, the fusion module is connected to the decision planning module, and the decision planning module is connected to the first control module; wherein, the fusion module is used to fuse the multi-source perception information obtained by multiple perception sources in the first perception module, the decision planning module is used to perform decision planning based on the fusion processing result to obtain a first decision planning result, the first control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result; the second control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the second perception result.

[0064] In this embodiment, Figure 2 is a schematic diagram of a first decision control link according to an embodiment of the present application, such as Figure 2 As shown, the first decision control link 11 further includes a fusion module 114 , wherein the first perception module 111 is connected to the fusion module 114 , the fusion module 114 is connected to the decision planning module 112 , and the decision planning module 112 is connected to the first control module 113 .

[0065] Optionally, the fusion module is used to integrate the multi-source perception information from the first perception module into the first perception module, and use advanced information fusion technology, such as Kalman filtering, particle filtering, etc., to fuse these scattered data to obtain a fusion processing result, and then transmit the fusion processing result to the decision planning module. The decision planning module can perform decision planning based on the fusion processing result to obtain a first decision planning result, and transmit the first decision planning result to the first control module, so that the first control module determines whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result.

[0066] Optionally, the second decision control link where the second control module is located is intended to provide a rapid response mechanism in an emergency situation. The second control module is directly connected to the second perception module to obtain the second perception result transmitted by the second perception module, and determine whether it is necessary to trigger the vehicle's braking operation based on the second perception result.

[0067] Optionally, the design of the first decision-making control link and the second control module fully embodies the concept of combining redundancy and immediate response in autonomous driving technology. The first decision-making control link achieves high accuracy in complex decision-making and planning through the collaboration of multiple modules, while the second decision-making control link, through a direct connection between the perception module and the control module, provides a rapid response mechanism in emergency situations, providing a critical safety barrier for the vehicle's braking control system, ensuring that braking decisions can be made regardless of the situation, thereby maximizing driving safety.

[0068] As an optional implementation, the first decision control link also includes: a prediction module, a first perception module connected to a fusion module, a fusion module connected to a prediction module, a prediction module connected to a decision planning module, and a decision planning module connected to a first control module; wherein the prediction module is used to perform prediction processing on the movement behavior or running position of the obstacle in a future time period based on the fusion processing result to obtain a prediction result, the decision planning module is used to perform decision planning based on the prediction result to obtain a first decision planning result, the first control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the first decision planning result; the second control module is used to determine whether it is necessary to trigger the vehicle's braking operation based on the second perception result.

[0069] In this embodiment, Figure 3 is a schematic diagram of another first decision control link according to an embodiment of the present application, such as Figure 3 As shown, the first decision control link 11 also includes a prediction module 115, wherein the first perception module 111 is connected to the fusion module 114, the fusion module 114 is connected to the prediction module 115, the prediction module 115 is connected to the decision planning module 112, and the decision planning module 112 is connected to the first control module 113.

[0070] Optionally, the prediction module is used to receive the fusion processing results of the fusion module, and predict the movement behavior or running position of the obstacle in the future time period based on the fusion processing results to obtain a prediction result, and then transmit the prediction result to the decision planning module. After receiving the prediction result, the decision planning module performs decision planning based on the prediction result to obtain a first decision planning result, and transmits the first decision planning result to the first control module. The first control module is used to determine whether the obstacle within the first preset range of the vehicle meets the target distance condition based on the first decision planning result, and when the target distance condition is met, determine whether the vehicle's braking operation needs to be triggered.

[0071] Optionally, because the second control module is directly connected to the second perception module in the second decision-making control link, the second control module can directly obtain the second perception result of the second perception module and, if the obstacle within the second preset range from the vehicle meets the target distance condition, determine whether to trigger the vehicle's braking operation. This instant decision-making capability, which eliminates the need for prediction and decision-making planning, is crucial in emergency situations, ensuring that even if the first decision-making link fails, the vehicle can still take timely action to avoid or mitigate potential risks.

[0072] Optionally, the first and second decision-making control links each have distinct emphases: the first prioritizes deep perception information comprehension and decision-making planning, while the second focuses on immediate perception and rapid response. This complementary dual system creates an intelligent and reliable vehicle braking control system, significantly improving the adaptability and safety of autonomous vehicles in complex traffic environments.

[0073] As an optional implementation, the first perception module or the second perception module is used to obtain obstacle information through at least one of the following perception devices: a local perception device, a global perception device; or, the first perception module or the second perception module is used to obtain obstacle information through at least one of the following sensors: a lidar, a camera, and a millimeter-wave radar.

[0074] In this embodiment, the perception module plays a crucial role in the autonomous vehicle's emergency braking system, acquiring information about obstacles around the vehicle. This information serves as the basis for subsequent decision-making and emergency braking. The perception module typically uses various types of perception devices or sensors to acquire information about obstacles around the vehicle.

[0075] Optionally, the first perception module or the second perception module is used to obtain obstacle information through a local perception device or a global perception device. Among them, the local perception device mainly focuses on a small area near the vehicle, can quickly capture the dynamics of obstacles close to the vehicle, and is suitable for emergency braking scenarios. For example, local perception devices usually include ultrasonic sensors, short-range lidars, etc., which can identify obstacles in front of or around the vehicle in a very short time, even when driving at low speed or parking. For example, when a vehicle is driving slowly in a parking lot, the local perception device can quickly detect pedestrians or objects that suddenly appear, providing a data basis for the vehicle's emergency braking.

[0076] Optionally, global perception devices typically have a wider range than local perception devices to acquire information over a longer distance along the vehicle's path. These devices, including long-range lidar, wide-angle cameras, and high-resolution millimeter-wave radar, can detect obstacles at long distances and identify key infrastructure such as road signs and traffic lights, providing a basis for intelligent decision-making.

[0077] Optionally, the first or second perception module is configured to acquire obstacle information using at least one of the following sensors: lidar, camera, or millimeter-wave radar. Lidar precisely measures the distance between an obstacle and the vehicle by emitting laser pulses and receiving reflected signals. It can generate high-resolution three-dimensional point cloud images, providing reliable perception information even in low light or rainy or snowy conditions. Lidar is particularly well-suited for detecting and identifying long-range obstacles, providing the vehicle with sufficient warning time to make appropriate obstacle avoidance or braking decisions.

[0078] Optionally, the camera uses optical imaging principles to capture visual information around the vehicle. Image processing algorithms can identify road signs, vehicles, pedestrians, and animals. Its advantages lie in its color recognition and texture analysis capabilities, which are crucial for understanding complex environments and traffic regulations. The camera can be a binocular camera, a fisheye camera, or the like, without specific limitations. However, the performance of the camera is significantly affected by lighting conditions. Its perception capabilities may decrease at night or in bad weather, and it is usually necessary to use it in conjunction with other sensors.

[0079] Millimeter-wave radar, which utilizes electromagnetic waves with millimeter-wave wavelengths to detect obstacles, operates at a higher frequency than conventional automotive radar, enabling greater accuracy and a wider field of view. Millimeter-wave radar performs exceptionally well in adverse weather conditions such as fog, rain, and snow, boasting strong penetration and resistance to interference. It is particularly well-suited for obstacle detection during fast-moving conditions, providing continuous and stable distance and speed information, ensuring that the decision-making control chain can respond appropriately in any environment.

[0080] Optionally, both the first and second perception modules in the autonomous vehicle's emergency braking system integrate the capabilities of local and global perception devices, as well as the functions of multiple sensors such as lidar, cameras, and millimeter-wave radar. This design ensures that the vehicle's braking control system can fully and accurately perceive its surroundings. Especially in emergency situations, it can quickly and accurately obtain obstacle information, providing solid support for safe driving.

[0081] As an optional implementation, the local perception device includes at least a vehicle-mounted perception device, and the global perception device includes at least a V2X device.

[0082] In this embodiment, the local perception device includes at least onboard perception devices, such as various sensors deployed on the vehicle, primarily used to capture real-time information about the vehicle's immediate surroundings. These devices include, but are not limited to, lidar, cameras, millimeter-wave radar, and ultrasonic sensors.

[0083] Optionally, the global perception device includes at least a V2X device, which refers to a V2X communication device that can include V2V, V2I, and V2P communication methods, and is used to collect information about obstacles within a second preset range from the vehicle. Among them, V2V communication is used to indicate that vehicles can communicate directly with each other, sharing their respective positions, speeds, directions, and dynamic information, helping vehicles to predict distant traffic conditions or potential dangers in advance and achieve collaborative driving. V2I communication is used to instruct vehicles to communicate with infrastructure (such as traffic lights, road signs, etc.) to obtain information such as road conditions and traffic light status, and optimize path planning and traffic management. V2P communication is used to instruct vehicles to communicate with pedestrians, allowing vehicles to perceive the movement intentions of surrounding pedestrians through smartphones or other personal devices, thereby enhancing driving safety. Through V2X technology, vehicles are integrated into a wider transportation network and information exchange, expanding the vehicle's perception field of view, enabling vehicles to obtain long-distance warning information, road environment changes, etc., which is of great significance for improving the driving safety of unmanned vehicles, alleviating traffic congestion, and preventing accidents.

[0084] Optionally, local and global perception devices can be combined to form a three-dimensional perception network. Local perception focuses on direct and rapid acquisition of sensory information, suitable for responding to immediate road conditions; while global perception emphasizes broader information exchange, enhancing the vehicle's foresight of potential threats. Together, these two ensure the safe and efficient operation of autonomous vehicles in complex traffic environments.

[0085] As an optional implementation, the first perception module is used to obtain obstacle information through local perception devices and global perception devices, and the second perception module is used to obtain obstacle information only through local perception devices; or, the first perception module is used to obtain obstacle information through at least two of a lidar, a camera, and a millimeter-wave radar, and the second perception module is used to obtain obstacle information through a lidar.

[0086] In this embodiment, the perception module of an unmanned vehicle is used to capture obstacle information in the vehicle's surrounding environment, providing data for decision-making and control. The first perception module, a perception module in the first decision-making and control chain, can acquire obstacle information through local and global perception devices. The second perception module, a perception module in the second decision-making and control chain, can acquire obstacle information through local perception devices. Alternatively, the first perception module can acquire obstacle information through at least two of a laser radar, a camera, and a millimeter-wave radar, while the second perception module can acquire obstacle information through the laser radar.

[0087] Optionally, the first perception module obtains obstacle information through a perception method that combines local perception and global perception. It not only uses local perception equipment to obtain obstacle information close to the vehicle (such as nearby pedestrians, obstacles, etc.), but also uses global perception equipment to obtain obstacle information far away from the vehicle. This multi-perspective and multi-distance information collection enables the system to more accurately assess the surrounding environment and lay a solid foundation for subsequent decision-making and planning.

[0088] Optionally, the first perception module can also simultaneously use at least two of the following devices: a lidar, a camera, and a millimeter-wave radar to obtain information about obstacles within a preset range from the vehicle. The lidar is used to provide accurate three-dimensional spatial information, the camera is used to identify color, shape, and texture features, and the millimeter-wave radar maintains stable detection capabilities even in adverse weather conditions. After the first perception module obtains multi-source perception information through this multi-source perception method, it can fuse this multi-source perception information in the fusion module of the first decision-making control link to remove noise, improve data reliability, and generate a first perception result.

[0089] Optionally, compared to the first perception module, the second perception module in the second decision-making and control chain is designed with a greater emphasis on efficiency and immediacy. This second perception module relies solely on local sensing devices, such as lidar, to gather obstacle information. Lidar, with its high-precision ranging capabilities and rapid scanning frequency, is the preferred device for the second perception module. This design enables the second decision-making and control chain to quickly determine the distribution of obstacles in close proximity in front of the vehicle, providing the data needed for immediate braking decisions in emergency situations.

[0090] Optionally, the second perception module in the second decision-control link eliminates the global perception equipment and complex data fusion process of the first perception module, focusing on immediate, local data collection and processing. This streamlined link design minimizes latency from perception to decision-making, enabling rapid response, especially when the vehicle faces sudden obstacles or emergency braking needs.

[0091] Optionally, the first and second perception modules play complementary yet distinct roles in autonomous vehicles. The first perception module, through comprehensive, multi-source information collection, provides deep environmental awareness for decision-making, suitable for comprehensive analysis and planning under normal driving conditions. The second perception module, on the other hand, focuses on rapid, localized perception, enabling independent and immediate response in emergency situations, filling safety gaps in extreme conditions. Together, these two modules create a sophisticated and flexible perception model, providing a solid foundation for the safe operation of autonomous vehicles.

[0092] As an optional implementation, the first perception module is a multi-source perception module, and the second perception module is a single-source perception module; or, the first perception module is a single-source perception module, and the second perception module is a multi-source perception module; wherein, the source of the perception information of the multi-source perception module is multiple sources, and the source of the perception information of the single-source perception module is a single source.

[0093] In this embodiment, based on the difference in the number of sources of information collection, the perception module can be divided into two types: multi-source perception module and single-source perception module. These two types of perception modules are suitable for different application scenarios, and together ensure that the vehicle's braking control system can respond quickly and accurately under various conditions.

[0094] Optionally, the multi-source perception module integrates multiple sensor types, such as lidar, cameras, millimeter-wave radar, and ultrasonic sensors, to collect environmental information from different angles around the vehicle. Each sensor has its inherent strengths and limitations. For example, lidar excels at measuring distances and building 3D maps, while cameras excel at color recognition and shape analysis. Fusion of these sensor information can significantly improve perception accuracy and robustness.

[0095] Optionally, in a multi-source perception module, even if one sensor temporarily fails, other sensors can continue to provide critical data, ensuring continuity and reliability of perception. The complementary effect between data from different sensors helps overcome the recognition challenges that a single sensor might encounter in specific environments.

[0096] Alternatively, compared to a multi-source perception module, a single-source perception module relies on only one type of sensor, such as a high-performance lidar or precise millimeter-wave radar, to acquire environmental information. While this may lack the comprehensiveness and diversity of information, it offers a more efficient response time and lower computational load.

[0097] Alternatively, a single-source perception module can more quickly detect obstacles and generate perception results by avoiding the processing time associated with multi-source data fusion, making it suitable for emergency scenarios requiring immediate decision-making. The relatively simple processing of single-source information reduces data processing complexity, facilitating low-latency, high-efficiency braking decisions.

[0098] Optionally, the first perception module in the first decision control link is a multi-source perception module, and the second perception module in the second decision control link is a single-source perception module, or the first perception module is a single-source perception module and the second perception module is a multi-source perception module.

[0099] For example, when the first perception module in the first decision-making control link is a multi-source perception module, it can obtain multi-source perception information through a multi-source perception method. Subsequently, through the collaborative work of the fusion module, prediction module, decision-making planning module, and the first control module, the behavior and position of obstacles in front of the vehicle are predicted, thereby formulating a more reasonable action strategy to ensure vehicle driving safety. When the second perception module in the second decision-making control link is a single-source perception module, the second perception module can obtain single-source perception information through a single-source perception method and then directly transmit the obtained single-source perception information to the second control module. The second control module can directly make decisions and control the vehicle based on the single-source perception information, thereby triggering the vehicle's braking operation in an emergency.

[0100] Optionally, when the first perception module in the first decision-making control link is a single-source perception module, the first perception module can promptly obtain obstacle information around the vehicle through a single-source perception method, and through the collaborative work of the fusion module, the prediction module, the decision-making planning module, and the first control module, predict the behavior and position of the obstacle in front of the vehicle, thereby determining whether to trigger the vehicle's planned operation. When the second perception module in the second decision-making control link is a multi-source perception module, the second perception module can obtain multi-source perception information through a multi-source perception method, and then transmit the obtained multi-source perception information to the second control module, which will judge and predict the multi-source perception information to determine whether to trigger the vehicle's braking operation.

[0101] Preferably, in the vehicle braking control system provided in the present application, the first decision control link may include a first perception module, a decision planning module, and a first control module. The purpose of this design is to provide comprehensive, intelligent, and safe driving assistance during the normal driving of the unmanned vehicle. Preferably, the first perception module is designed as a multi-source perception module, so that the first perception module will obtain multi-source perception information through multiple perception methods, and then obtain complete environmental information around the vehicle through the multi-source perception information. Then, the decision planning module can perform comprehensive decision planning based on the multi-source perception information, and then the first control module can determine whether to trigger the vehicle's braking operation based on the decision planning results. In this way, by obtaining environmental information around the vehicle in a multi-source manner, potential risks around the vehicle can be predicted in advance, and corresponding avoidance measures can be taken to avoid the impact caused by emergency braking. The second decision control link only includes the second perception module and the second control module. The purpose of this design is to improve the response speed and decision efficiency of the vehicle's braking control system in emergency situations and ensure the driving safety of the vehicle. Preferably, the second perception module is designed as a single-source perception module, so that the second control module can obtain single-source perception information through single-source perception, and then transmit the single-source perception information to the second control module. The second control module can directly determine whether it is necessary to trigger the vehicle's braking operation based on the single-source perception information without the need to perform multi-source perception data fusion and coordinate conversion and other processing operations, which will further improve the vehicle's response rate in emergency braking scenarios or when the first decision control link fails.

[0102] Optionally, in the autonomous vehicle's braking control system, the first and second perception modules form a complementary mechanism. The multi-source perception module, through its comprehensive and in-depth information fusion capabilities, provides navigation and decision-making support for the vehicle in complex environments. The single-source perception module, with its rapid response speed and streamlined information processing, ensures that even when the first decision-making control link fails or environmental information processing is limited, the vehicle can still take timely braking measures to avoid or mitigate collisions. This design enables the emergency braking system to not only cope with changing road conditions during daily driving but also activate quickly in extreme situations, maximizing vehicle safety.

[0103] As an optional implementation, the first decision control link is deployed in a first chip of the vehicle, and the second decision control link is deployed in a second chip of the vehicle.

[0104] In this embodiment, the choice of hardware architecture is crucial for ensuring system stability and safety in the design of an autonomous vehicle's emergency braking system. The first and second decision-making control links are deployed on two separate chips within the vehicle, achieving independent redundancy at the hardware level. Even if one decision-making control link fails, the operation of the other will not be affected.

[0105] Optionally, the first decision-control link, the primary decision-making process during normal vehicle operation, comprises a complex series of modules, such as perception, fusion, prediction, and decision planning. These modules require high computing resources and data processing capabilities. Therefore, deploying this link on the first chip is intended to fully utilize high-performance computing units to ensure that every decision is based on comprehensive and accurate information analysis. The first chip is often equipped with a powerful processor or dedicated AI accelerator capable of processing large amounts of data and executing complex algorithms.

[0106] Optionally, the second decision-control link is more compact than the first, providing a fast-response backup solution. The second control module receives information directly from the second perception module, eliminating intermediate steps like data fusion and prediction. This enables the second link to make decisions extremely quickly, especially if the first link fails. It can immediately take over emergency braking control, reducing decision latency and improving safety. The second decision-control link is deployed in a second chip, further strengthening system-level redundancy.

[0107] Alternatively, the two chips can operate independently, each carrying distinct decision-making logic and control flows. This allows the other chip to remain operational even if one fails, ensuring the vehicle retains braking capability in an emergency. Furthermore, the second chip is typically designed to be more robust and streamlined to handle the high-pressure environment of emergencies.

[0108] Optionally, by deploying the first and second decision-making control links on separate chips, the autonomous vehicle's emergency braking system achieves multi-layered safety. The first chip is responsible for deep decision-making during normal operation, while the second chip acts as a rapid response unit in emergencies, providing immediate backup control for the vehicle's braking control system and significantly improving driving safety.

[0109] As an optional implementation, the first control module and the second control module are the same control module.

[0110] In this embodiment, the first control module and the second control module can be the same control module, that is, the first control module and the second control module share the same hardware resources, such as a microprocessor, a memory, and a communication interface, but use different strategies and algorithms at the software level to distinguish their behaviors in different scenarios.

[0111] Alternatively, by integrating the first and second control modules into a single control module, the increased costs and resource waste associated with physically separating the two control modules are avoided, the number of system components is reduced, the overall architecture is simplified, and the complexity of maintenance and management is reduced. Furthermore, since inter-module communication is reduced, decision-making response speed is indirectly improved.

[0112] Optionally, in the same control module, the first control mode and the second control mode are distinguished and switched by software algorithms to adapt to different driving scenarios. For example, under normal driving conditions, the first mode is enabled, and whether emergency braking needs to be triggered is determined based on the deep decision planning results (i.e., the fusion of environmental perception information and the output of the prediction module). In this mode, the control logic is complex and can process prediction information of various driving environments and obstacles to ensure that the vehicle makes the best decision under complex road conditions. When an emergency occurs, or the first decision link fails due to a fault, the control module automatically switches to the second mode. In this mode, the control algorithm is directly driven by the second perception result, bypassing the complex decision-making planning link, and directly evaluating whether immediate braking operation is needed using the shortest path. Compared with the first mode, the second mode is more direct and faster, and is suitable for emergency scenarios that require immediate response.

[0113] Optionally, while the first and second control modules share the same hardware module physically, they are independent in software design. This means the control logic of the two links is strictly isolated to prevent mutual interference. This design allows the control modules to seamlessly switch between different modes without affecting their execution efficiency or decision accuracy.

[0114] The vehicle's braking control system will be further described below in conjunction with preferred implementations.

[0115] The present application provides a vehicle braking control system, comprising: a first decision control link and a second decision control link, wherein the first decision control link comprises at least: a first perception module, a decision planning module, and a first control module, wherein a first perception result of the first perception module is output to the decision planning module, the first decision planning result of the decision planning module is output to the first control module, and the first control module is used to determine whether a braking operation of the vehicle needs to be triggered based on the first decision planning result; and a second decision control link comprises a second perception module and a second control module, wherein a second perception result of the second perception module is output to the second control module, and the second control module is used to determine whether a braking operation of the vehicle needs to be triggered based on the second perception result. That is, in the present application embodiment, by introducing two independent decision control links (the first decision control link and the second decision control link), even if the first decision control link fails in any of the perception, decision planning, or control links, the second decision control link can immediately intervene and independently trigger the braking operation of the vehicle based on its own perception results and control logic, thereby greatly enhancing the safety of the system. Moreover, the perception module in the second decision control link is directly connected to the control module, which reduces the time for data processing and decision making. When an emergency occurs, the control module in the second decision-making control link can directly receive sensory information from the perception module and quickly determine whether the vehicle's braking operation needs to be triggered, without going through the complex calculations of the decision-making planning module. This greatly accelerates the response speed of emergency braking. Furthermore, the first and second control modules operate independently, reducing the risks associated with interdependence between the modules. Even if the first decision-making control link completely fails, the second decision-making control link can still independently complete the entire emergency braking process, ensuring the vehicle's braking reliability under extreme conditions. This solves the technical problem in related technologies that cannot effectively control the vehicle's braking operation after the failure of the main autonomous driving link.

[0116] Optionally, as can be seen from the above introduction, the first perception module in the first decision control link is a multi-source perception module, and the second perception module in the second decision control link is a single-source perception module, or the first perception module is a single-source perception module and the second perception module is a multi-source perception module, and the two perception modules perceive information in two ways respectively, which will not be repeated here. That is to say, the perception methods of the first perception module and the second perception module are not limited in the embodiment of the present application. However, preferably, in the embodiment of the present application, the first perception module in the first decision control link can be set as a multi-source perception module, and the second perception module in the second decision control link can be set as a single-source perception module. The advantage of such a design is to give full play to the unique advantages of the first decision control link and the second decision control link under different driving conditions, and jointly improve the overall performance and safety of the unmanned vehicle.

[0117] For example, since the first decision-making control chain includes at least a decision-making planning module and a first control module in addition to the first perception module, the purpose of designing the first decision-making control chain is to provide a comprehensive, intelligent, and smooth driving assistance system through a multi-level modular design. This system can effectively predict and avoid risks under normal driving conditions, reduce the occurrence of emergency braking, and thus improve ride comfort and driving safety. Based on this, if the first perception module is configured as a multi-source perception module, it can obtain comprehensive environmental information around the vehicle through multi-source perception. This multi-angle and multi-dimensional data acquisition method ensures comprehensive and accurate environmental perception. The multi-source perception information perceived by the first perception module is then input into the decision-making planning control module, which then performs comprehensive decision-making planning based on this multi-source perception information. The first control module then determines whether to trigger the vehicle's braking operation based on the decision-making planning results. This process not only helps avoid obstacles but, more importantly, ensures smooth driving, reduces potential impact on passengers, improves the riding experience, and maintains vehicle stability.

[0118] For another example, since the second decision control link only includes the second perception module and the second control module, and the first perception module is directly connected to the second control module, the purpose of designing the second decision control link in this way is to simplify the information processing process through a very simple link architecture, ensure that the vehicle can respond immediately in an emergency, quickly trigger the braking operation, and improve the immediacy and reliability of accident avoidance. Based on this, if the second perception module is set as a single-source perception module, the second perception module can obtain single-source perception information through a single-source perception method, that is, the second perception module only focuses on one type of sensor data, and can capture key information directly in front of the vehicle with higher sensitivity and faster speed, reducing the complexity and delay of data processing. After obtaining the single-source perception information, the single-source perception information can be directly transmitted to the second control module. Since the perception information is in a single-source form, the second control module can quickly determine whether it is necessary to trigger the vehicle's braking operation after receiving the single-source perception information without additional processing or analysis. Compared to multi-source perception information, this eliminates the intermediate step of comprehensive information processing, significantly shortening the reaction time from perception to braking. This will further improve the vehicle's response rate in emergency braking scenarios or when the first decision-control link fails, making it a key technical means of enhancing the safety of autonomous vehicles. Simultaneously, setting the second perception module as a single-source perception module reduces hardware costs and system complexity, enabling the second decision-control link to serve as an efficient and economical redundant system, promptly intervening in the event of a failure in the first decision-control link to ensure driving safety.

[0119] That is to say, in the embodiment of the present application, preferably, the first perception module in the first decision control link is set to a multi-source perception mode, so that the first decision control link can perform in-depth perception and intelligent decision-making of the vehicle's surrounding environment based on the multi-source perception information perceived by the first perception module, providing a more comprehensive and safe driving strategy for the unmanned vehicle. This design ensures that in non-emergency conditions, the vehicle can improve driving efficiency and riding experience through intelligent planning and control. The second perception module in the second decision control link is set to a single-source perception mode, so that the second decision control link can quickly and directly make vehicle braking decisions based on the single-source perception information perceived by the second perception module. This design ensures that in an emergency or when the first decision control link fails, the second decision control link can quickly and directly make vehicle braking decisions, thereby ensuring the vehicle's driving safety. The two decision control links complement each other and jointly build a comprehensive, reliable and efficient unmanned emergency braking system, which not only meets the intelligent needs of daily driving, but also ensures immediate and safe response when facing emergencies.

[0120] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A vehicle braking control system, characterized in that: include: a first decision control link, comprising a first perception module, a decision planning module, and a first control module, wherein a first perception result of the first perception module is output to the decision planning module, and a first decision planning result of the decision planning module is output to the first control module, and the first control module is configured to determine whether a braking operation of the vehicle needs to be triggered based on the first decision planning result; a second decision control link, comprising a second perception module and a second control module, wherein a second perception result of the second perception module is output to the second control module, and the second control module is configured to determine whether a braking operation of the vehicle needs to be triggered according to the second perception result; Among them, the relationship between the first perception module and the second perception module includes one of the following: the first perception module and the second perception module are the same perception module, the first perception module and the second perception module are different perception modules, the first perception module includes the second perception module, and the second perception module includes the first perception module.

2. The system according to claim 1, wherein: The first control module is used to determine a first distance between the vehicle and an obstacle within a first preset range from the vehicle based on the first decision planning result, and determine that a braking operation of the vehicle needs to be triggered when the first distance meets a target distance condition; the second control module is used to determine a second distance between the vehicle and an obstacle within a second preset range from the vehicle based on the second perception result, and determine that a braking operation of the vehicle needs to be triggered when the second distance meets the target distance condition.

3. The system according to claim 1, wherein: The first control module is used to execute a first mode for determining whether it is necessary to trigger the braking operation of the vehicle based on the first decision-making planning result in a first situation; the second control module is used to execute a second mode for determining whether it is necessary to trigger the braking operation of the vehicle based on the second perception result in a second situation; wherein, the second situation is used to indicate that the first mode fails, or the obstacle detected using the first decision-making planning result does not meet the target distance condition but the obstacle detected using the second perception result meets the target distance condition.

4. The system according to claim 1, wherein: The first decision control link also includes: a fusion module, the first perception module is connected to the fusion module, the fusion module is connected to the decision planning module, and the decision planning module is connected to the first control module; wherein, the fusion module is used to fuse the multi-source perception information obtained by multiple perception sources in the first perception module, the decision planning module is used to perform decision planning based on the fusion processing result to obtain the first decision planning result, the first control module is used to determine whether it is necessary to trigger the braking operation of the vehicle based on the first decision planning result; the second control module is used to determine whether it is necessary to trigger the braking operation of the vehicle based on the second perception result.

5. The system according to claim 4, characterized in that The first decision control link also includes: a prediction module, the first perception module is connected to the fusion module, the fusion module is connected to the prediction module, the prediction module is connected to the decision planning module, and the decision planning module is connected to the first control module; wherein, the prediction module is used to predict the movement behavior or running position of the obstacle in the future time period according to the fusion processing result to obtain a prediction result, the decision planning module is used to perform decision planning according to the prediction result to obtain the first decision planning result, the first control module is used to determine whether it is necessary to trigger the braking operation of the vehicle according to the first decision planning result; the second control module is used to determine whether it is necessary to trigger the braking operation of the vehicle according to the second perception result.

6. The system according to claim 1, wherein: The first perception module or the second perception module is configured to obtain obstacle information through at least one of the following perception devices: a local perception device, a global perception device; or The first perception module or the second perception module is used to obtain obstacle information through at least one of the following sensors: lidar, camera, and millimeter wave radar.

7. The system according to claim 6, characterized in that The local perception device includes at least a vehicle-mounted perception device, and the global perception device includes at least a V2X device.

8. The system according to claim 6, characterized in that The first perception module is used to obtain the obstacle information through the local perception device and the global perception device, and the second perception module is used to obtain the obstacle information only through the local perception device; or, The first perception module is used to obtain the obstacle information through at least two of the laser radar, the camera, and the millimeter wave radar, and the second perception module is used to obtain the obstacle information through the laser radar.

9. The system according to claim 1, wherein: The first perception module is a multi-source perception module, and the second perception module is a single-source perception module; or The first perception module is a single-source perception module, and the second perception module is a multi-source perception module; wherein the perception information of the multi-source perception module comes from multiple sources, and the perception information of the single-source perception module comes from a single source.

10. The system according to claim 1, wherein: The first decision control link is deployed in a first chip of the vehicle, and the second decision control link is deployed in a second chip of the vehicle.

11. The system according to claim 1, wherein: The first control module and the second control module are the same control module.

Images