Control components and vehicles

Abstract

The present disclosure provides a control component and a vehicle, wherein the control component includes: a main sensor; a backup sensor, wherein the information collection object of the backup sensor is the same as that of the main sensor; a first controller, which receives the collection data of the main sensor and the backup sensor respectively; a second controller, which receives the collection data of the main sensor and the backup sensor respectively; and an actuator, which is used to receive a target control instruction and control the operation of a target component according to the target control instruction, wherein the target control instruction is obtained according to the data collected by the main sensor and is determined based on the output result of at least one of the first controller and the second controller.

Description

Technical Field

[0001] The present disclosure relates to the field of control technology, and in particular to a control component and a vehicle. Background Art

[0002] As a new generation of travel, self-driving cars provide great convenience, but the safety risks caused by software and hardware failures have attracted much attention. To ensure safety, the self-driving system needs to add safety mechanisms to control the failure rate within a certain safety range. However, these safety measures usually increase costs. How to minimize cost increases while ensuring safety is a challenge facing the industry. Summary of the invention

[0003] In view of the above problems, the present disclosure provides a control assembly and a vehicle.

[0004] According to the first aspect of the present disclosure, a control component is provided, including: a main sensor; a backup sensor, the information collection object of the backup sensor is the same as that of the main sensor; a first controller, receiving the collection data of the main sensor and the backup sensor respectively; a second controller, receiving the collection data of the main sensor and the backup sensor respectively; an actuator, used to receive a target control instruction, and control the operation of a target component according to the target control instruction, the target control instruction is obtained according to the data collected by the main sensor, and the target control instruction is determined based on the output result of at least one of the first controller and the second controller.

[0005] According to an embodiment of the present disclosure, when the first controller operates normally, the target control instruction is output through the first controller; when the first controller fails, the target control instruction is output through the second controller.

[0006] According to an embodiment of the present disclosure, a first main computing chip is provided in the first controller, and the first main computing chip can perform calculations based on the collected data of the main sensor; a second main computing chip is provided in the second controller, and the second main computing chip can perform calculations based on the collected data of the main sensor; wherein the same main algorithm is provided in the first main computing chip and the second main computing chip, and the target control instruction is determined based on the calculation result of at least one of the first main computing chip and the second main computing chip.

[0007] According to an embodiment of the present disclosure, when the first controller and the second controller operate normally, the target control instruction is determined by the calculation result of the first main computing chip and the calculation result of the second main computing chip.

[0008] According to an embodiment of the present disclosure, when the first controller and the second controller operate normally, the target control instruction is determined by the calculation result of the first main operation chip, and the second main operation chip does not operate.

[0009] According to an embodiment of the present disclosure, in the event of a failure of the first controller, the target control instruction is determined by the calculation result of the second main operation chip.

[0010] According to an embodiment of the present disclosure, a first backup computing chip is provided in the first controller, and the first backup computing chip can perform calculations based on the collected data of the backup sensor; a second backup computing chip is provided in the second controller, and the second backup computing chip can perform calculations based on the collected data of the backup sensor; in the case of abnormal operation of the main algorithm, the backup control instruction is determined by the calculation result of at least one of the first backup computing chip and the second backup computing chip, and the executor receives the backup control instruction and controls the operation of the target component according to the backup control instruction.

[0011] According to an embodiment of the present disclosure, the first controller includes a first output module, which is used to receive a target control instruction and a backup control instruction, verify the target control instruction through the backup control instruction, and send the target control instruction to the actuator if the verification passes.

[0012] According to an embodiment of the present disclosure, the main sensor is used to detect obstacle information in the direction of travel of the vehicle, and the target control instruction is used to control the movement of the vehicle.

[0013] The second aspect of the present disclosure provides a vehicle, comprising: a vehicle body; a main sensor; a backup sensor, the information collection object of the backup sensor is the same as that of the main sensor; a first controller, receiving the collected data of the main sensor and the backup sensor respectively; a second controller, receiving the collected data of the main sensor and the backup sensor respectively; a traveling component; an actuator, for receiving a target control instruction, and controlling the operation of the traveling component according to the target control instruction, the target control instruction being obtained according to the data collected by the main sensor, and being determined based on the output result of at least one of the first controller and the second controller.

[0014] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0016] Figure 1 A schematic diagram of the structure of an automatic driving system in the related art according to an embodiment of the present disclosure is shown;

[0017] Figure 2 A schematic diagram showing an application scenario of a control component and a vehicle according to an embodiment of the present disclosure;

[0018] Figure 3 The schematic diagram of the structure of the control component according to the embodiment of the present disclosure is shown;

[0019] Figure 4 The schematic diagram shows the structure of a controller including a computing chip according to an embodiment of the present disclosure;

[0020] Figure 5 Another structural diagram of a controller including a computing chip according to an embodiment of the present disclosure is schematically shown; and

[0021] Figure 6 A schematic diagram of the structure of a controller including a first output module according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0022] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the present disclosure. In the following detailed description, for ease of explanation, many specific details are set forth to provide a comprehensive understanding of the embodiments of the present disclosure. However, it is apparent that one or more embodiments may also be implemented without these specific details. In addition, in the following description, descriptions of known structures and technologies are omitted to avoid unnecessary confusion of the concepts of the present disclosure.

[0023] The terms used herein are only for describing specific embodiments and are not intended to limit the present disclosure. The terms "comprise", "include", etc. used herein indicate the existence of features, steps, operations and / or components, but do not exclude the existence or addition of one or more other features, steps, operations or components.

[0024] All terms (including technical and scientific terms) used herein have the meanings commonly understood by those skilled in the art unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0025] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0026] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0027] The embodiment of the present disclosure provides a control component. Before introducing the technical solution provided by the embodiment of the present disclosure, the related technologies involved in the present disclosure are first described.

[0028] In related technologies, for L4 level (the fourth level of autonomous driving technology), in order to achieve the system functional safety level ASIL-D (Automotive Safety Integrity Level D, the highest level of automotive safety integrity level), the following are usually used: Figure 1 The design scheme shown in the figure. This scheme enhances the reliability of the system by introducing a main controller and a redundant controller. However, under this scheme, whether the main controller fails or the redundant controller fails, the execution capability safety level of the autonomous driving system will be downgraded to ASIL-B (medium risk level), resulting in the execution capability of the autonomous driving system being limited and losing some necessary safety behaviors for autonomous driving.

[0029] Figure 2 The application scenario diagram of the control component and the vehicle according to the embodiment of the present disclosure is schematically shown.

[0030] It should be noted that Figure 2 The examples shown are merely scenarios in which the embodiments of the present disclosure can be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure cannot be used in other devices, systems, environments or scenarios.

[0031] like Figure 2 As shown, the application scenario according to this embodiment may include a control component 100 and a vehicle 200 .

[0032] The control component 100 can interact with the vehicle 200 to achieve management and control of the vehicle 200. The control component 100 and the vehicle 200 are connected through a network that provides a communication link medium, and specifically, the communication connection can be achieved through a wired or wireless communication link or an optical fiber cable.

[0033] The control component 100 includes a main sensor 101, a backup sensor 102, a first controller 103, a second controller 104 and an actuator 105. The main sensor 101 and the backup sensor 102 are responsible for receiving various data from the vehicle 200, the first controller 103 and the second controller 104 are responsible for calculating the data and generating control instructions, and the actuator 105 is responsible for executing the control instructions so that the vehicle 200 can drive, stop, accelerate, decelerate and perform other operations according to the instructions of the control component 100.

[0034] The control component 100 can also interact with other autonomous vehicles, such as autonomous electric vehicles, autonomous aircraft, and autonomous ships that can transport passengers. The autonomous vehicle can be integrated with the control component 100 or connected to the control component 100 to achieve autonomous driving of the autonomous vehicle without the need for passenger intervention.

[0035] According to the vehicle 200 of the present disclosure, the control component 100 of the above embodiment is provided. Therefore, when some components in the control component 100 fail or are disconnected, such as when the main sensor 101 fails, the vehicle 200 can continue to collect data through the backup sensor 102, so that the first controller 103, the second controller 104 and the actuator 105 can work normally, thereby improving the safety and reliability of the vehicle 200.

[0036] It should be understood that Figure 2 The number and type of control components and vehicles in the embodiment are only illustrative. Depending on the implementation requirements, there can be any number and type of control components and vehicles.

[0037] The following will be based on Figure 2 The scene described by Figure 3~Figure 6 The control components of the embodiments of the present disclosure are described in detail.

[0038] Figure 3 The structural diagram of the control component according to the embodiment of the present disclosure is schematically shown.

[0039] like Figure 3 As shown, the control component 100 of this embodiment includes: a main sensor 101 , a backup sensor 102 , a first controller 103 , a second controller 104 and an actuator 105 .

[0040] The main sensor 101 and the backup sensor 102 are both part of the control component 100. The main sensor 101 and the backup sensor 102 are used as the main data source to monitor and collect data of a specific environment or equipment in real time. The actual situation can be reflected according to the data collected by the main sensor 101 and the backup sensor 102. The main sensor 101 and the backup sensor 102 can be connected to a specific information collection object, and these physical quantities can be converted into electrical signals or digital signals through a conversion mechanism for subsequent processing.

[0041] Among them, the information collection object of the backup sensor 102 is the same as that of the main sensor 101. That is, the main sensor 101 and the backup sensor 102 can collect data at the same time. By setting the backup sensor 102, an alternative data source can be provided when the main sensor 101 fails or the data is abnormal. The number of backup sensors 102 can also be more than one. In addition, the backup sensor 102 does not participate in data processing under normal circumstances. Only when the main sensor 101 fails, the data collected by the backup sensor 102 will be used. The main sensor 101 and the backup sensor 102 can be sensors of the same type, or sensors of different types, or sensors of partially the same type, such as the main sensor 101 is a camera and the backup sensor 102 is a lidar; or the main sensor 101 is a combination of multiple cameras, and the backup sensor 102 is a combination of a camera and a lidar.

[0042] The first controller 103 receives the collected data from the main sensor 101 and the backup sensor 102 respectively; the second controller 104 receives the collected data from the main sensor 101 and the backup sensor 102 respectively.

[0043] The first controller 103 is connected to the main sensor 101 and the backup sensor 102, that is, the main sensor 101 and the backup sensor 102 are each connected to the first controller 103 through an independent data transmission path, so that the collected data of the main sensor 101 and the backup sensor 102 can be received respectively. At the same time, the second controller 104 is also configured to receive the collected data from the main sensor 101 and the backup sensor 102 in parallel.

[0044] The first controller 103 is connected in parallel with the second controller 104, that is, the input sources of the first controller 103 and the second controller 104 (i.e., the main sensor 101 and the backup sensor 102) are the same, but they can calculate and analyze the input data based on the preset control logic, mathematical model or artificial intelligence algorithm, and output corresponding target control instructions, so that data comparison and verification can be performed between the two controllers.

[0045] It should be noted that more controllers can be added as needed to handle more complex data processing tasks, or the number and configuration of controllers can be flexibly adjusted in different application scenarios according to different requirements for data processing capabilities and redundancy.

[0046] The actuator 105 is used to receive the target control instruction and control the operation of the target component according to the target control instruction. The target control instruction is obtained according to the data collected by the main sensor and is determined based on the output result of at least one of the first controller 103 and the second controller 104.

[0047] The actuator 105 is used to receive and analyze the target control instruction from the controller, wherein the target control instruction is obtained according to the data collected by the main sensor 101, and in the case of a failure of the main sensor 101, it can also be obtained according to the data collected by the backup sensor 102 when the main sensor 101 encounters a failure or data anomaly. After the first controller 103 and the second controller 104 independently process the data output by the main sensor 101, at least one instruction signal can be generated. The actuator 105 receives the instruction signals from the two parallel links respectively, obtains the target control instruction, and controls the operation of the target component (such as a motor, a steering system, etc.) according to the target control instruction.

[0048] In some exemplary embodiments, a high-precision laser radar is selected as the main sensor 101 to scan the vehicle's surroundings in real time and generate three-dimensional point cloud data. At the same time, the backup sensor 102 uses a laser radar of the same model as the main sensor 101 as a backup to ensure that it can seamlessly take over when the main sensor 101 fails. The first controller 103 and the second controller 104 are configured to receive the collected data of the main sensor 101, process and analyze the data respectively, and output corresponding results. The actuator 105 receives the output result of at least one of the first controller and the second controller to determine the target control instruction, and controls the operation of the target component of the vehicle according to the instruction, so that the vehicle travels according to the predetermined trajectory and speed.

[0049] It is understandable that, through the redundant control component design of the embodiment of the present disclosure, in the case of a single point failure, that is, whether it is a sensor failure or a controller failure, it is possible to quickly switch to the backup device and continue to work, thereby effectively avoiding safety accidents caused by the reduction of the reliability of the operation of the actuator control target component, and improving safety. At the same time, the control component has a simple structure and saves costs without adding new devices.

[0050] In the embodiment of the present disclosure, the main sensor 101 is used to detect obstacle information in the direction of the vehicle, and the target control instruction is used to control the movement of the vehicle.

[0051] For example, the main sensor 101 may be a laser radar, which measures the distance by emitting laser light and receiving reflected signals, thereby constructing an accurate three-dimensional image of the surrounding environment. At the same time, the main sensor 101 may also be a millimeter wave radar, which uses electromagnetic waves in the millimeter wave band for detection and ranging. In addition, the main sensor 101 may also be an ultrasonic sensor, which measures the distance by emitting ultrasonic waves and receiving echoes.

[0052] Exemplarily, the main sensor 101 may be a combination of the above-mentioned various types of sensors, which work together to fully cover the 360-degree environmental perception around the vehicle.

[0053] In the autonomous driving scenario, the main sensor 101 is installed on the autonomous driving vehicle and is used to detect obstacle information in the direction of the vehicle's travel, that is, the information collection object is the obstacles around the vehicle, which can include static obstacles, such as road facilities, buildings and trees, etc., and can also include dynamic obstacles, such as other vehicles, pedestrians and animals. At the same time, the information collection object can also be road markings (such as lane lines, stop lines and turn arrows, etc.) and traffic signs (such as traffic lights, speed limit signs and no-turn signs, etc.). In addition, the main sensor 101 can also collect the vehicle's own status information, such as vehicle speed, acceleration, steering wheel angle, brake and accelerator pedal input, etc., as well as sensor status data, to provide support for the vehicle's autonomous driving technology.

[0054] In some exemplary embodiments, a main sensor 101 is installed on an autonomous driving vehicle. The main sensor 101 is a laser radar, which can identify obstacles, road signs, vehicles and other pedestrians, and perform high-precision vehicle positioning. When the vehicle is driving on an urban road, the main sensor 101 monitors the road conditions ahead in real time. For example, when the laser radar detects that a pedestrian is about to cross the road 50 meters ahead, the collected data will be transmitted to the first controller 103 and the second controller 104. After the first controller 103 and the second controller 104 receive the collected data, they immediately calculate the relative speed and distance between the pedestrian and the vehicle, predict the possible path of the pedestrian, and generate a target control instruction, that is, an instruction to decelerate. Then, the deceleration instruction is transmitted to the actuator 105, and the actuator 105 performs a deceleration operation to ensure that there is enough time and space to safely stop the vehicle and avoid collision with pedestrians. As the pedestrian passes safely, the main sensor 101 will continue to detect obstacle information in the direction of the vehicle, and the first controller 103 and the second controller 104 will issue an acceleration command, and the actuator 105 will execute the acceleration command to restore the vehicle to its previous driving speed. In addition, if the main sensor 101 also detects that an emergency vehicle is approaching from behind and may pose a danger, the first controller 103 and the second controller 104 can also issue an emergency avoidance command to control the vehicle to slightly turn to the adjacent lane (provided that the lane is safe and obstacle-free) to further ensure driving safety.

[0055] It should be noted that the backup sensor 102 can also be used to detect obstacle information in the direction of vehicle travel. When the main sensor 101 fails or the data is abnormal, the collected data of the backup sensor 102 is used to generate target control instructions to control the movement of the vehicle.

[0056] It can be understood that by applying control components to vehicles, the vehicle can quickly switch to the backup system when facing sensor failure or controller abnormality, thereby achieving autonomous driving more stably and safely in complex and changing traffic environments.

[0057] On the basis of the above embodiment, in this embodiment, when the first controller 103 operates normally, the target control instruction is output through the first controller 103 ; when the first controller 103 fails, the target control instruction is output through the second controller 104 .

[0058] The first controller 103, as the main controller, is responsible for receiving the collected data from the main sensor 101, and generates the target control instructions after complex algorithm processing and decision logic. However, when the first controller fails to work properly due to various reasons (such as hardware failure, software error and network interruption, etc.), the second controller 104 will immediately take over the control, also receive the collected data from the main sensor 101, and generate the target control instructions based on its built-in control algorithm.

[0059] It should be noted that when a fault is detected in the first controller 103, the switching logic will be triggered immediately, and the control right will be transferred from the first controller 103 to the second controller 104 within milliseconds, and the second controller 104 will output the target control instruction to ensure the continuity and stability of the vehicle's driving.

[0060] In actual operation, the logic of command arbitration can be integrated on the actuator 105 end. If the command deviations output by the first controller 103 and the second controller 104 are small and are basically the same, the actuator 105 can control the operation of the target component according to the highly consistent target control command, thereby ensuring the stability and reliability of the system operation. When there are significant differences in the command signals output by the first controller 103 and the second controller 104, the priority of the command can be set, for example, the control command output by the first controller 103 is used as the target control command and executed. If the first controller 103 fails or the command is unreasonable, the command of the second controller 104 is used as the target control command. In addition, the health of the first controller 103 and the second controller 104 can be monitored, and then it is decided which command to use to control the operation of the target component. In other cases, the actuator can also combine the output results of the two controllers and obtain a more comprehensive and optimized control command through a weighted or fusion algorithm.

[0061] Exemplarily, when the first controller 103 operates normally, the first controller 103 acts as a main controller, receives real-time collected data from the main sensor 101 (such as radar, camera, etc.), and quickly processes the received information, including but not limited to data cleaning, feature extraction, and obstacle identification. Based on the processed information, the first controller 103 uses control algorithms and decision logic to generate target control instructions, such as acceleration, deceleration, lane keeping, or slight steering, and immediately outputs them to the actuator 105 for execution.

[0062] For example, when the first controller 103 fails (such as processor overheating, communication interruption, etc.), the switching logic is immediately started to transfer the control right from the first controller 103 to the second controller 104. After the second controller 104 takes over the control right, it generates a target control instruction based on the received information to control the operation of the target component, such as controlling the vehicle to continue to drive safely or find a safe parking position. At the same time, in the automatic driving scenario, the fault information of the first controller 103 can also be recorded, and after the vehicle stops, the fault report is sent to the owner or service center through the vehicle communication system for timely repair and maintenance.

[0063] It should be noted that for details not included in this embodiment, please refer to the implementation details of the aforementioned embodiment.

[0064] It can be understood that through the dual controller architecture (i.e., the first controller 103 and the second controller 104), when the first controller 103 fails, the target control instructions can be generated due to the processing of the second controller 104, thereby avoiding potential safety risks and significantly improving the reliability and safety of the system.

[0065] In an embodiment of the present disclosure, a first main computing chip is provided in the first controller 103, and the first main computing chip can perform calculations based on the collected data of the main sensor 101; a second main computing chip is provided in the second controller 104, and the second main computing chip can perform calculations based on the collected data of the main sensor 101; wherein the same main algorithm is provided in the first main computing chip and the second main computing chip, and the target control instruction is determined based on the calculation result of at least one of the first main computing chip and the second main computing chip.

[0066] Figure 4 The schematic diagram shows the structure of a controller including a computing chip according to an embodiment of the present disclosure.

[0067] like Figure 4 As shown, a first main computing chip is provided in the first controller 103, and a second main computing chip is provided in the second controller 104. Both the first main computing chip and the second main computing chip are connected to the main sensor 101 and are integrated with the same main algorithm, and can respectively calculate the collected data of the main sensor 101 to generate at least one calculation result. The target control instruction is determined according to the calculation result of at least one of the first main computing chip and the second main computing chip.

[0068] The first controller 103 can adopt a highly integrated strategy, that is, only one powerful first main computing chip is configured. The first main computing chip integrates a main algorithm system composed of multiple algorithms, including but not limited to environmental perception algorithms, path planning algorithms, motion control algorithms, and fault diagnosis and fault tolerance algorithms. Each algorithm is optimized for a specific data processing task to ensure that when processing complex collected data from the main sensor 101, the results can be obtained quickly and accurately.

[0069] Exemplarily, when the main sensor 101 captures obstacle information, road information, and the vehicle's own motion status in the surrounding environment, this information will be transmitted to the first main computing chip in real time. Subsequently, the various algorithms inside the chip will work together to parse and process the collected data. For example, the environmental perception algorithm is responsible for identifying and tracking obstacles, the path planning algorithm generates the optimal driving path based on the current environment and target location, and the motion control algorithm is responsible for converting the planned path into specific control instructions to drive the vehicle to perform corresponding actions. At the same time, the fault diagnosis and fault tolerance algorithm will continuously monitor the operating status of the system. Once an abnormality or fault is found, the corresponding emergency response mechanism will be immediately triggered to ensure the stability and safety of the system.

[0070] Figure 5 Another structural diagram of a controller including a computing chip according to an embodiment of the present disclosure is schematically shown.

[0071] In some exemplary embodiments, since the main algorithms integrated in the first main computing chip and the second main computing chip are the same, in some scenarios, the first main computing chip may need to process a large amount of environmental data, while the second main computing chip may be relatively idle. At this time, part of the computing tasks can be transferred from the first main computing chip to the second main computing chip to balance the workload of the two chips. In addition, the algorithm configuration can be flexibly adjusted according to different application scenarios and requirements, and different algorithms can be configured for the two main computing chips to achieve a higher level of fault tolerance and capture more diversified information, so as to make more comprehensive and accurate decisions. For example, when one of the main computing chips fails, the other main computing chip can take over part or all of its functions to ensure the continuity and stability of the system.

[0072] It can be understood that the first main computing chip and the second main computing chip are not only closely connected to the main sensor to realize the real-time transmission and processing of data, but also have the same core main algorithm built in, ensuring that when processing the collected data from the main sensor, there are redundant calculation paths, thereby improving the accuracy and reliability of data processing.

[0073] In an embodiment of the present disclosure, a first backup computing chip is provided in the first controller 103, and the first backup computing chip can perform calculations based on the collected data of the backup sensor 102; a second backup computing chip is provided in the second controller 104, and the second backup computing chip can perform calculations based on the collected data of the backup sensor 102; in the case of abnormal operation of the main algorithm, the backup control instruction is determined by the calculation result of at least one of the first backup computing chip and the second backup computing chip, and the executor 105 receives the backup control instruction and controls the operation of the target component according to the backup control instruction.

[0074] Continue to refer to Figure 4 The first controller 103 is provided with a first backup computing chip, and the second controller 104 is provided with a second backup computing chip. The first backup computing chip and the second backup computing chip are both connected to the backup sensor 102. The first backup computing chip and the second backup computing chip can integrate a backup algorithm. The main algorithm and the backup algorithm in the same controller (the first controller 103 or the second controller 104) are different. When the main algorithm runs abnormally, the backup algorithm in the first backup computing chip and the second backup computing chip can calculate the collected data of the backup sensor 102 and generate at least one calculation result to determine the backup control instruction. Based on the backup control instruction, the operation of the target component is controlled.

[0075] In some exemplary embodiments, the main algorithm may have an abnormality in the agenda, such as calculation errors, response delays or crashes. At this time, the backup mechanism will be triggered immediately, and at least one of the first backup computing chip and the second backup computing chip will use the backup algorithm to calculate the collected data of the backup sensor, and generate a backup control instruction based on the calculation results to replace the original control output of the main algorithm, ensuring that the actuator 105 can control the target components (such as motors, valves, heaters and other key equipment) to operate in a predetermined safety or emergency mode according to the backup control instruction.

[0076] It should be noted that, in the embodiment of the present disclosure, the working state of the first backup computing chip and the second backup computing chip can be flexibly adjusted according to the specific configuration of the system and the real-time fault situation. That is to say, in the first case, the first backup computing chip and the second backup computing chip may be in an activated state at the same time and work together to generate backup control instructions at the same time to improve the safety factor of the operation of the control target component. For example, in some extreme cases, the main algorithm may not be able to continue to run due to a serious fault, and it is necessary to switch to the backup control mode immediately. In order to ensure the reliability and stability of the backup control, the first backup computing chip and the second backup computing chip can be activated at the same time, so that they can calculate based on the collected data of the backup sensor 102 and generate their own control instructions. Then, the two backup control instructions can be evaluated and selected according to the preset arbitration mechanism or comparison algorithm. Finally, an optimal backup control instruction is selected and passed to the target component through the actuator 105 to achieve effective control of the target component. In addition, activating the first backup computing chip and the second backup computing chip at the same time can also bring additional redundancy and fault tolerance. If one of the backup computing chips fails or is abnormal during operation, the other backup computing chip can still continue to work to ensure that the system will not be completely paralyzed due to the failure of a single component. In the second case, when the system failure is relatively minor, or the system configuration has optimized the work of the backup computing chip, only one of the backup computing chips can be activated. For example, in some application scenarios, the system may only need one backup computing chip to cope with possible abnormal situations. At this time, in order to reduce system power consumption and cost, you can choose to activate only one backup computing chip and let it independently undertake the tasks of data processing and control instruction generation.

[0077] It is understandable that the first backup computing chip and the second backup computing chip are respectively set in different controllers, forming a double backup at the physical and algorithm levels. At the same time, when the main algorithm fails, at least one backup computing chip can work normally without interrupting the control process, thereby ensuring the continuity of system control.

[0078] On the basis of the above embodiment, in this embodiment, when the first controller and the second controller operate normally, the target control instruction is determined by the calculation result of the first main computing chip and the calculation result of the second main computing chip.

[0079] When the first controller 103 and the second controller 104 are both in normal operation, the determination of the target control instruction may not rely on the calculation result of a certain main computing chip, but may adopt a more robust dual-chip collaborative decision-making mechanism. Specifically, the first main computing chip and the second main computing chip may receive data from the main sensor 101 respectively, and perform calculations based on their respective integrated main algorithms. Subsequently, the two calculation results will be sent to the actuator 105, which may perform a comprehensive analysis and evaluation of the two calculation results according to preset weights, priorities or complex decision algorithms, and finally determine an optimal target control instruction.

[0080] For example, in a highly automated autonomous driving system, especially in a scenario that meets ASIL-D requirements, the main sensor 101 sends the collected environmental data to the first controller 103 and the second controller 104 at the same time. The first main computing chip and the second main computing chip in the first controller 103 and the second controller 104 process the sensor data based on their respective integrated main algorithms and generate two control instructions. Then, the two controllers send the control instructions generated by each to the actuator 105. The actuator 105 can first verify the integrity and consistency of the two control instructions to ensure that they come from a legitimate and trusted controller. Furthermore, the two control instructions can be comprehensively analyzed and evaluated according to preset weights, priorities or complex decision algorithms. For example, multiple dimensions such as timeliness, accuracy and safety of the instructions can be considered. Finally, the actuator 105 selects an optimal target control instruction and executes it immediately, thereby meeting the safety requirements of the ASIL-D level.

[0081] It can be understood that by adopting a dual-chip collaborative decision-making mechanism, the executor can simultaneously receive different instructions from parallel heterogeneous devices, and select the optimal instruction to execute according to the preset decision-making mechanism, thereby making full use of the computing power and data resources of the two main computing chips and improving the accuracy and robustness of the decision.

[0082] On the basis of the above embodiments, in this embodiment, when the first controller 103 and the second controller 104 operate normally, the target control instruction is determined by the calculation result of the first main operation chip, and the second main operation chip does not operate.

[0083] When both the first controller 103 and the second controller 104 are in normal operation and the system performance requirements do not exceed the preset threshold, the determination process of the target control instruction can be prioritized and completely dependent on the calculation results of the first main computing chip. In other words, the first main computing chip is powerful enough to complete the required computing tasks alone without the additional support of the second main computing chip. At this time, data processing is performed by the first main computing chip to generate the required target control instructions. The second main computing chip will be configured to be in standby mode or low power consumption mode. In this mode, the second main computing chip hardly participates in the actual computing process, and its internal circuits and processors are in a low-power dormant state, retaining only the necessary monitoring and wake-up functions so that it can quickly respond and take over computing tasks when needed.

[0084] In order to ensure the reliability and stability of the system, a redundant backup mechanism can be established between the first controller 103 and the second controller 104. That is, although the second main computing chip does not participate in the calculation under normal circumstances, it can monitor the working status of the first main computing chip in real time. Once the first main computing chip is detected to have a fault or performance degradation, the second main computing chip can quickly switch from the standby state to the normal working mode, take over the computing task, and ensure the continuity and accuracy of the target control instruction.

[0085] For example, in an automatic driving system, the main sensor 101 collects data of the surrounding environment and transmits it to the first controller 103 in real time. After receiving the collected data, the first main computing chip in the first controller 103 immediately starts the preset main algorithm for processing, analyzes the collected data, identifies obstacles, road signs and other vehicles, and performs calculations. At the same time, based on the calculation results, the first main computing chip generates target control instructions, such as steering, acceleration and braking. In this process, the second controller 104 and the second main computing chip inside it remain in an inoperative state, that is, they do not receive any data or perform any calculations, and their power can be completely cut off or reduced to the lowest power consumption mode to save energy. The target control instruction determined based on the calculation result of the first main computing chip is sent to the actuator 105, and the actuator 105 adjusts the operation of the vehicle according to the received instruction to achieve automatic driving.

[0086] It is understandable that by determining the target control instruction through the calculation result of the first main computing chip and putting the second main computing chip in standby mode, the overall power consumption of the system can be reduced, the energy utilization efficiency can be improved, and a balance can be achieved between performance and power consumption. At the same time, it also helps to simplify the structure and control logic of the system and reduce the complexity and maintenance cost of the system.

[0087] On the basis of the above embodiment, in this embodiment, when the first controller 103 fails, the target control instruction is determined by the calculation result of the second main operation chip.

[0088] When the first controller fails to work properly due to hardware failure, software error or communication interruption, the corresponding fault handling mechanism can be triggered to switch to the standby control mode. That is, the collected data from the main sensor 101 can be received and calculated by the second main computing chip, and the target control instruction can be determined according to the calculation result.

[0089] It should be noted that since the second main computing chip has pre-integrated the main algorithm that is the same as or compatible with the first main computing chip, it can generate effective target control instructions based on the collected data of the main sensor 101, and pass the target control instructions to the actuator 105 to achieve precise control of the target component.

[0090] Exemplarily, before the first controller 103 fails, the second main computing chip of the second controller can work normally or be in standby state. In normal operation, after the first controller 103 fails, since the second main computing chip is already in an active state, it can quickly switch roles and take over the tasks of the first controller 103, that is, immediately start receiving and processing data from the main sensor 101, generate target control instructions based on its built-in main algorithm, and send the target control instructions to the actuator 105. In the standby state, after the first controller 103 fails, the system can immediately detect this change and trigger the fault handling mechanism to send a wake-up signal to the second main computing chip to switch it from standby state to normal working state. Once awakened, the second main computing chip will immediately start to perform the same tasks as in the normal working state, that is, receive data from the main sensor 101, generate target control instructions, and send instructions to the actuator 105.

[0091] It should be noted that for details not included in this embodiment, please refer to the implementation details of the aforementioned embodiment.

[0092] It is understandable that the target control instruction can be determined by the calculation result of the second main computing chip, ensuring that a certain control capability and stability can be maintained when the first controller fails. At the same time, since the second main computing chip can work independently, it can also provide a valuable time window for fault recovery and maintenance of the first controller.

[0093] In an embodiment of the present disclosure, the first controller 103 includes a first output module, which is used to receive a target control instruction and a backup control instruction, verify the target control instruction through the backup control instruction, and send the target control instruction to the actuator 105 if the verification passes. When the main algorithm runs normally, the control component will still calculate and generate the backup control instruction.

[0094] Figure 6 A schematic diagram of the structure of a controller including a first output module according to an embodiment of the present disclosure is schematically shown.

[0095] like Figure 6 As shown, the first controller 103 may include a first output module, the first output module is connected to the first main computing chip and the first backup computing chip of the first controller 103, and the second main computing chip and the second backup computing chip of the second controller 104. At the same time, the second controller 104 may include a second output module, the second output module is connected to the first main computing chip and the first backup computing chip of the first controller 103, and the second main computing chip and the second backup computing chip of the second controller 104.

[0096] In some exemplary embodiments, the first output module can receive the target control instruction and the backup control instruction at the same time. The target control instruction is determined based on the output result of at least one of the first main computing chip of the first controller 103 and the second main computing chip of the second controller 104, and includes information such as the action type, parameter settings, and expected execution effect that the actuator 105 needs to perform. The backup control instruction is determined by the calculation result of at least one of the first backup computing chip of the first controller 103 and the second backup computing chip of the second controller 104. The backup control instruction, as a redundant verification means of the target control instruction, can include the same or similar operation requirements as the target control instruction, but can also be presented in different encoding formats, check codes, or encryption methods. After receiving these two types of instructions, the first output module can first perform strict verification on them. In this verification process, it includes but is not limited to: format verification, that is, checking whether the encoding format of the instruction meets the predefined specifications. Content verification, that is, comparing the key information in the target control instruction and the backup control instruction to ensure their consistency or complementarity. Verification code verification, that is, using the built-in verification algorithm to verify the instruction to detect whether there is a transmission error or tampering. Authority verification, that is, confirming whether the sender of the instruction has the corresponding control authority. If the verification is passed, the first output module will confirm the legality and validity of the target control instruction and send it to the actuator 105. The actuator 105 performs corresponding operations according to the received instructions, thereby controlling the operation of the target component.

[0097] If a problem is found in the target control instruction during the verification process (such as format error, inconsistent content, etc.), the first output module can automatically switch to using the backup control instruction to drive the actuator 105 to ensure that the system can continue to operate stably.

[0098] It can be understood that the first controller and its first output module achieve mutual verification by introducing backup control instructions and a strict verification mechanism, thereby effectively improving the accuracy and reliability of system control.

[0099] According to an embodiment of the present disclosure, the present disclosure also provides a vehicle, including: a vehicle body; a main sensor 101; a backup sensor 102, the information collection object of the backup sensor 102 is the same as that of the main sensor 101; a first controller 103, receiving the collection data of the main sensor 101 and the backup sensor 102 respectively; a second controller 104, receiving the collection data of the main sensor 101 and the backup sensor 102 respectively; a traveling component; an actuator 105, used to receive a target control instruction, and control the operation of the traveling component according to the target control instruction, the target control instruction is obtained according to the data collected by the main sensor 101, and the target control instruction is determined based on the output result of at least one of the first controller 103 and the second controller 104.

[0100] The vehicle body has an interior space that can carry passengers or other objects, such as luggage, etc. At the same time, the vehicle body can also carry all hardware and software devices to ensure that they can work together to realize the vehicle's autonomous or assisted driving functions.

[0101] The main sensor 101, the backup sensor 102, the first controller 103, the second controller 104, the driving components and the actuator 105 are arranged on the vehicle body. Among them, the main sensor 101 collects the road information, obstacle distance, traffic signs, pedestrians and other vehicle dynamics around the vehicle in real time, thereby providing a data basis for the vehicle's decision-making. In order to enhance the redundancy and fault tolerance of the system, the backup sensor 102 and the main sensor 101 have exactly the same information collection object, that is, monitor the same external environment. If the main sensor 101 cannot work normally due to failure, pollution or occlusion, the backup sensor 102 can take over immediately and continue to provide the necessary perception data, thereby ensuring the safety and continuity of the vehicle's driving. The first controller 103 and the second controller 104 receive the collected data from the main sensor 101 and the backup sensor 102 respectively, and can independently use advanced algorithms and models to perform calculations such as environmental understanding, path planning, decision making, and generate target control instructions at the same time. The actuator 105 is responsible for receiving the target control instructions generated by at least one of the first controller 103 and the second controller 104. Based on the target control instructions, the actuator 105 can accurately control the operation of the driving components (the driving components may include the vehicle's engine, motor, steering system and braking system, etc.), for example, controlling the steering system to steer according to the steering instruction, or controlling the braking system to brake according to the braking instruction, thereby realizing the vehicle's acceleration, deceleration, steering and parking operations, and ultimately enabling the vehicle to navigate autonomously and drive safely.

[0102] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0103] It will be appreciated by those skilled in the art that the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways, even if such combinations or combinations are not explicitly described in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features described in the various embodiments of the present disclosure may be combined and / or combined in a variety of ways. All of these combinations and / or combinations fall within the scope of the present disclosure.

[0104] The embodiments of the present disclosure are described above. However, these embodiments are only for illustrative purposes and are not intended to limit the scope of the present disclosure. Although the embodiments are described above, this does not mean that the measures in the various embodiments cannot be used in combination to advantage. Without departing from the scope of the present disclosure, those skilled in the art may make a variety of substitutions and modifications, which should all fall within the scope of the present disclosure.

Claims

1. A control component, comprising: Main sensor; A backup sensor, the information collection object of the backup sensor is the same as that of the main sensor; A first controller receives the collected data of the main sensor and the backup sensor respectively; A second controller receives the collected data of the main sensor and the backup sensor respectively; An actuator is used to receive a target control instruction and control the operation of a target component according to the target control instruction, wherein the target control instruction is obtained according to data collected by the main sensor and is determined based on an output result of at least one of the first controller and the second controller.

2. The control assembly according to claim 1, wherein: When the first controller operates normally, the target control instruction is output through the first controller; In the event of a failure of the first controller, the target control instruction is output through the second controller.

3. The control assembly according to claim 1, wherein: The first controller is provided with a first main computing chip, and the first main computing chip can perform calculations according to the collected data of the main sensor; The second controller is provided with a second main computing chip, and the second main computing chip can perform calculations according to the collected data of the main sensor; The first main computing chip and the second main computing chip are provided with the same main algorithm, and the target control instruction is determined according to a calculation result of at least one of the first main computing chip and the second main computing chip.

4. The control assembly according to claim 3, wherein: When the first controller and the second controller operate normally, the target control instruction is determined by the calculation result of the first main computing chip and the calculation result of the second main computing chip.

5. The control assembly according to claim 3, wherein: When the first controller and the second controller operate normally, the target control instruction is determined by the calculation result of the first main operation chip, and the second main operation chip does not operate.

6. The control assembly according to any one of claims 4 to 5, wherein: In the event of a failure of the first controller, the target control instruction is determined by the calculation result of the second main computing chip.

7. The control assembly according to claim 3, wherein: The first controller is provided with a first backup computing chip, and the first backup computing chip can perform calculations according to the collected data of the backup sensor; The second controller is provided with a second backup computing chip, and the second backup computing chip can perform calculations according to the collected data of the backup sensor; When the main algorithm runs abnormally, a backup control instruction is determined by the calculation result of at least one of the first backup computing chip and the second backup computing chip, and the executor receives the backup control instruction and controls the operation of the target component according to the backup control instruction.

8. The control assembly according to claim 7, wherein: The first controller includes a first output module, which is used to receive the target control instruction and the backup control instruction, verify the target control instruction through the backup control instruction, and send the target control instruction to the actuator if the verification passes.

9. The control assembly according to claim 1, wherein: The main sensor is used to detect obstacle information in the direction of vehicle travel, and the target control instruction is used to control the movement of the vehicle.

10. A vehicle comprising: Vehicle body; Main sensor; A backup sensor, the information collection object of the backup sensor is the same as that of the main sensor; A first controller receives the collected data of the main sensor and the backup sensor respectively; A second controller receives the collected data of the main sensor and the backup sensor respectively; Traveling parts; An actuator is used to receive a target control instruction and control the operation of the travel component according to the target control instruction, wherein the target control instruction is obtained according to the data collected by the main sensor and is determined based on the output result of at least one of the first controller and the second controller.

Images