KR102656802B1 - Autonomous driving computing platform based on redundant architecture - Google Patents

Abstract

The present disclosure provides an autonomous driving control system based on a redundant structure. This system includes a plurality of sensors configured to sense information about the surrounding environment of the autonomous vehicle, holds main control rights to the autonomous vehicle, and processes signals received from the plurality of sensors to control the autonomous vehicle. a first processor configured to generate a first set of control signals used for a first processor and a second processor configured to sense the surrounding environment of the vehicle by processing signals received from at least some of the plurality of sensors, When an operation error is detected, the first processor transfers main control to the second processor, and the second processor is reconfigured to generate a first set of control signals.

Description

Autonomous driving computing platform based on redundant structure {AUTONOMOUS DRIVING COMPUTING PLATFORM BASED ON REDUNDANT ARCHITECTURE}

The present disclosure relates to an autonomous driving computing platform based on a redundant structure, and more specifically, by providing a redundant structure including a plurality of processors or systems duplicated for autonomous driving control, various defects or operation errors related to autonomous driving control. It is about an autonomous driving computing platform that can effectively respond to and provide safety and reliability of autonomous driving control.

An autonomous driving system may use multiple heterogeneous sensors, multiple power supplies, or multiple computing components to ensure reliable driving and safety. For example, when multiple computing components (or processors) process the same sensing data to generate autonomous driving control signals, the processor in which an operation error occurred is detected by comparing the autonomous driving control signals, and an appropriate response is taken. By executing the procedure, more reliable autonomous driving can be achieved. In addition, various software and hardware enhancements are being made to operate autonomous vehicles effectively and stably.

Additionally, in order to increase the safety reliability of the autonomous driving system, a plurality of processors and backup processors that simultaneously perform redundant functions may be provided. However, while this multiplexed autonomous driving system has the advantages of high performance and high safety, it has the disadvantage of high power consumption as multiple processors perform the same control function. In particular, autonomous driving systems perform image analysis using high-performance processors such as GPUs to recognize the surrounding environment and generate autonomous driving control signals based on this, so a large amount of computation is required, which leads to high power consumption.

In general, autonomous driving systems are applied to electric vehicles, and power consumption due to the large amount of calculations required for autonomous driving control directly affects the fuel efficiency of electric vehicles. In a situation where the battery capacity used in electric vehicles is limited to a certain level, a method to increase power efficiency and improve safety and reliability has not yet been provided.

The present disclosure provides a method of configuring and operating an autonomous driving system using a redundant structure-based autonomous driving computing platform in order to solve the problems of the conventional autonomous driving system described above.

According to an embodiment of the present disclosure, an autonomous driving control system based on a redundant structure includes a plurality of sensors configured to detect information about the surrounding environment of the autonomous vehicle, and holds main control rights of the autonomous vehicle, A first processor configured to process signals received from a plurality of sensors to generate a first set of control signals used for controlling the autonomous vehicle, and to process signals received from at least some of the plurality of sensors to determine the surrounding environment of the vehicle. and a second processor configured to detect, wherein when an operation error by the first processor is detected, the first processor transfers main control to the second processor, such that the second processor generates a first set of control signals. is reconstructed.

According to one embodiment, the autonomous driving control system further includes a memory that stores a plurality of pattern information related to operation errors on the autonomous driving control system, and the operation pattern of the first processor or a peripheral device associated with the first processor is stored in the memory. If it is identical or similar to at least one of the plurality of pattern information stored in , it is determined that an operation error of the first processor has occurred.

According to one embodiment, the plurality of pattern information includes at least one of an EMI or EMC operation error pattern, a temperature error pattern, a processor error pattern, a power error pattern, a memory CRC error pattern, and a memory bit error pattern.

According to one embodiment, the second processor, which has received main control rights in the autonomous driving control system, is reconfigured to generate at least part of the first control signal set according to the sensed surrounding environment.

According to one embodiment, the second processor, which has received main control rights from the autonomous driving control system, applies different sensor-specific weights to signals received from a plurality of sensors when the sensed surrounding environment requires different levels of autonomous driving control. It is reorganized to do so.

According to one embodiment, the second processor, which has received main control rights in the autonomous driving control system, detects objects with different computational processing capacities in signals received from a plurality of sensors when the sensed surrounding environment requires different levels of autonomous driving control. It is reorganized to apply the recognition model.

According to one embodiment, in an autonomous driving system, while the first processor processes signals received from at least some of the plurality of sensors to generate a first control signal set, the second processor processes the signals received from at least some of the plurality of sensors. The signals are processed independently to generate a second set of control signals that have a smaller range than the set of control signals.

According to one embodiment, the plurality of sensors in the autonomous driving control system include at least one of a LiDAR sensor, a laser sensor, an infrared sensor, and a camera.

According to another embodiment of the present disclosure, an autonomous driving control method based on a redundant structure, executed by at least one processor, includes detecting information about the surrounding environment of the autonomous vehicle by a plurality of sensors, Processing signals received from a plurality of sensors to generate, by a first processor holding main control rights of the autonomous vehicle, a first set of control signals used for control of the autonomous vehicle, and providing the second processor to the second processor. detecting the surrounding environment of the vehicle by processing signals received from at least some of the plurality of sensors, and when an operation error by the first processor is detected, the first processor transfers main control to the second processor. Previously comprising reconfiguring the second processor to generate a first set of control signals.

According to another embodiment of the present disclosure, a computer program stored in a computer-readable recording medium is provided to execute an autonomous driving control method on a computer.

According to various embodiments of the present disclosure, when a main processor error is detected based on a fault list, the autonomous driving control system based on a redundant structure is configured to connect a plurality of redundant processors to minimize the risk of the error. By minimizing the time it takes to switch control, reliability regarding the safety of autonomous driving can be secured.

According to various embodiments of the present disclosure, when operating an autonomous driving control system based on a redundant structure, a backup processor is on standby to respond to a defect in the main processor by determining a specific sensor set required for autonomous driving control according to the surrounding situation. The power consumed can be effectively reduced.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the description of the claims.

Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, in which like reference numerals represent like elements, but are not limited thereto.
1 is a diagram illustrating an example in which a redundant structure-based autonomous driving system controls road driving of an autonomous vehicle according to an embodiment of the present disclosure.
Figure 2 is a block diagram showing the configuration of an autonomous driving control system according to an embodiment of the present disclosure.
Figure 3 is a block diagram showing the configuration of an error detection unit according to an embodiment of the present disclosure.
Figure 4 is a block diagram showing the configuration of a first processor and a second processor according to an embodiment of the present disclosure.
Figure 5 is a flowchart showing an autonomous driving control method based on a redundant structure according to an embodiment of the present disclosure.
Figure 6 is a flowchart showing an autonomous driving control method based on a redundant structure according to another embodiment of the present disclosure.

Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the attached drawings. However, in the following description, detailed descriptions of well-known functions or configurations will be omitted if there is a risk of unnecessarily obscuring the gist of the present disclosure.

In the accompanying drawings, identical or corresponding components are given the same reference numerals. Additionally, in the description of the following embodiments, overlapping descriptions of identical or corresponding components may be omitted. However, even if descriptions of components are omitted, it is not intended that such components are not included in any embodiment.

Advantages and features of the disclosed embodiments and methods for achieving them will become clear by referring to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the present disclosure is complete and to those skilled in the art to which the present disclosure pertains. It is only provided to fully inform the user of the scope of the invention.

Terms used in the present disclosure will be briefly described, and the disclosed embodiments will be described in detail.

The terminology used in this disclosure selects general terms that are currently widely used as much as possible while considering the functions in this disclosure, but this may vary depending on the intention or precedent of a technician working in the related field, the emergence of new technology, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the relevant invention. Therefore, the terms used in this disclosure should be defined based on the meaning of the term and the overall content of this disclosure, rather than simply the name of the term.

In this disclosure, singular expressions include plural expressions, unless the context clearly specifies the singular. Additionally, plural expressions include singular expressions, unless the context clearly specifies plural expressions.

When it is said that a part 'includes' a certain element throughout the present disclosure, this means that other elements may be further included rather than excluding other elements, unless specifically stated to the contrary.

The term 'unit' or 'module' used in the specification refers to a software or hardware component, and the 'unit' or 'module' performs certain roles. However, 'part' or 'module' is not limited to software or hardware. A 'unit' or 'module' may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, 'part' or 'module' refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, etc. , procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. Components and 'parts' or 'modules' can be combined into smaller numbers of components and 'parts' or 'modules' or into additional components and 'parts' or 'modules'. Could be further separated.

According to an embodiment of the present disclosure, a 'unit' or 'module' may be implemented with a processor and memory. The term “processor” should be interpreted broadly to include general purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some contexts, “processor” may refer to an application-specific integrated circuit (ASIC), programmable logic device (PLD), field programmable gate array (FPGA), etc. The term “processor” refers to a combination of processing devices, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such combination of configurations. It may also refer to

In this disclosure, 'system' may refer to a configuration that includes one or more servers, computing devices, software modules or components that execute recommendation functions and/or functions that predict business growth probability, or a combination thereof. For example, it may refer to one or more computing devices, server devices, or distributed computing devices that provide cloud services, but is not limited thereto. Hereinafter, when describing embodiments of the redundancy-based autonomous driving system, the system includes a software architecture, operating system, library, driver, or one or more of these and hardware modules such as a processor, memory, etc. that implement redundancy-based autonomous driving. It may mean that components are combined.

1 is a diagram illustrating an example in which an autonomous driving system based on a redundant structure according to an embodiment of the present disclosure controls the road driving of an autonomous vehicle.

The autonomous vehicle 110 shown in FIG. 1 may include an autonomous driving module 120 that generates an autonomous driving control signal. The autonomous driving module 120 is a main block (hereinafter referred to as 'first processor') configured to process signals received from a plurality of sensors to generate a set of control signals used to control the autonomous vehicle 110. ) 112, and a shadow block (hereinafter referred to as 'second processor') 124 configured to detect the surrounding environment of the vehicle 110 by processing signals received from at least some of the plurality of sensors. can do. Additionally, the autonomous vehicle 110 may include a plurality of sensors such as a camera 130, lidar 140, radar 150, etc., but its configuration is not limited thereto.

The autonomous driving module 120 may process signals (or sensing data) received from a plurality of sensors 130, 140, and 150 to recognize the surrounding environment or objects. The road driving example 100 shows an example in which the autonomous driving module 120 recognizes the surrounding environment and objects, including other vehicles 160, based on signals received from a plurality of sensors.

In one embodiment, the main block (first processor) 122 of the autonomous driving module 120 holds main control rights to the autonomous vehicle 110 . The main block 122, which holds main control rights, executes all functions of autonomous driving based on signals received from all sensors 130, 140, and 150 mounted on the vehicle 110, or operates the sensors 130, 140, and 150. Only some functions of autonomous driving can be executed depending on the surrounding environment recognized based on signals. For example, the main block 122 performs high-performance object recognition based on signals received from all sensors 130, 140, and 150. By using models to recognize the surrounding environment, precise and accurate autonomous driving control can be performed.

In one embodiment, the shadow block (second processor) 124 of the autonomous driving module 120 may sense the surrounding environment of the vehicle without holding main control rights. When the autonomous driving module 120 requires different levels of autonomous driving control depending on the surrounding environment, the shadow block (second processor) 124 can apply object recognition models with different computational processing capacities or weights for each sensor. there is. For example, the shadow block 124 applies a high weight to the camera 130 for low-level autonomous driving control when the surrounding environment is relatively simple and the risk of an accident is low, while other sensors 140 and 150 ), a low weight can be applied. In another example, the shadow block 124 may apply a high weight to all sensors 130, 140, and 150 for high-level autonomous driving control when the surrounding environment is relatively complex and the risk of an accident is high. Additionally or alternatively, the shadow block (second processor) 124 may execute minimal functions overlapping with the main block (first processor) 122 even without main control rights. For example, the shadow block 124 may execute low-level autonomous driving control based on signals received from some of the sensors 140 and 150 in the absence of main control authority.

In one embodiment, the shadow block (second processor) 124 responds to a defect in the main block (first processor) 122 by allowing the main block (first processor) 122 to send a first set of control signals. During generation, the minimum autonomous driving function overlapping with the main block (first processor) 122 may be executed. At this time, in performing the minimum overlapping autonomous driving function, the shadow block (second processor) 124 is larger than the set of control signals generated by the main block (first processor) 122 to execute all autonomous driving functions. A small set of control signals can be generated.

In one embodiment, the error pattern of the main block (first processor) 122 is detected based on the fault list, and when it is determined that a fault has occurred according to the detection result, the autonomous vehicle 110 Main control may be transferred from the main block (first processor) 122 to the shadow block (second processor) 124. The shadow block (second processor) 124, which has received control, generates control signals to perform all autonomous driving functions performed by the main block (first processor) 122, or generates some signals depending on the recognized surrounding environment. Control signals can be generated to perform functions.

In one embodiment, error pattern information in the defect list includes, but is not limited to, Electromagnetic Interference (EMI), Electromagnetic Compatibility (EMC), temperature, processor, power, memory CRC, memory bit error pattern, etc. The first processor or the second processor may detect an internal defect by monitoring the operation of the first processor or a peripheral device associated with the first processor based on the defect list.

According to the above-described embodiments, in the autonomous driving control system including a plurality of processors with a duplicated structure, the processor with main control rights (e.g., the first processor) recognizes the surrounding environment and performs autonomous driving based on this. While executing control, another processor (eg, a second processor) may only perform awareness of the surrounding environment. In this configuration, when a defect occurs in the first processor with main control, the second processor is in a state of recognizing the surrounding environment, so when main control is transferred from the first processor to the second processor, the second processor The processor can immediately execute autonomous driving control according to the main control authority based on the results of recognizing the surrounding environment. Accordingly, while the main control right is transferred from the first processor to the second processor, the blank period of normal autonomous driving control can be minimized and system stability can be guaranteed. Additionally, the second processor can minimize overall system power consumption by only recognizing the surrounding environment while not in main control, thereby reducing standby power consumption while not in main control.

Figure 2 is a block diagram showing the configuration of an autonomous driving control system 200 according to an embodiment of the present disclosure.

As shown, the autonomous driving control system 200 is. It may include a sensor unit 210, a control instruction unit 220, an error detection unit 230, an emergency response unit 240, and a weighting unit 250. The control instruction unit 220, error detection unit 230, emergency response unit 240, and weighting unit 250 may correspond to, for example, the autonomous driving module 120 shown in FIG. 1.

In one embodiment, the sensor unit 210 may include a plurality of sensors, that is, a camera 130, LiDAR 140, and radar 150, but is not limited thereto. The sensor unit 210 is connected to the BUS 260 and can transmit sensing data to the control instruction unit 220. The BUS 260 is connected to the sensor bus interfaces 222A and 222B of the control instruction unit 220 and can transmit sensing data. The control instruction unit 220 may generate an autonomous driving control signal using the sensing data received from the sensor unit 210.

In one embodiment, the control instruction unit 220 may include a first processor 221A and a second processor 221B. Here, the first processor 221A may correspond to the main block, and the second processor 221B may correspond to the shadow block. The first processor 221A may include a sensor bus interface 222A and a main operation unit 223A, and the main operation unit 223A may include a driving control unit 224A and a surrounding detection unit 225A. The second processor 221B may include a sensor bus interface 222B and a sub-operation unit 223A, and the sub-operation unit 223A may include a driving control unit 224A and a surrounding detection unit 225B.

In one embodiment, the error detection unit 230 may include a memory 232 and an error pattern detection unit 234. The error detection unit 230 may monitor the operating status of the processors 221A and 221B and detect operating errors in each processor. When detecting an error in the error detection unit 230, the error may be detected by comparing the current operating state of the processors 221A and 221B with the error pattern. The error pattern detection unit 234 may compare error patterns included in the defect list stored in the memory 232 with the current operating states of the processors 221A and 221B.

In one embodiment, the emergency response unit 240 may include an alarm unit 242 and an emergency route creation unit 244. When an error is detected by the error detection unit 230, the emergency response unit 240 may execute an emergency response procedure in response. When the error detection unit 230 detects an error, the alarm unit 242 may generate and transmit a warning message. After sending a warning message, the autonomous driving control system 200 can perform any one of semi-autonomous driving, manual driving, and emergency driving.

In one embodiment, in a semi-autonomous driving mode, the control instruction unit 220 may generate an autonomous driving control signal using all or part of the sensing data received from the sensor unit 210. In the manual driving mode, the control instruction unit 220 may transfer full control of the vehicle to the driver or provide driving assistance services such as lane keeping assistance so that the driver can directly operate the vehicle. Meanwhile, in the emergency driving mode, the control instructing unit 220 may generate a control signal to move the vehicle to a safe place along the emergency path generated by the emergency path generating unit 244.

In one embodiment, the weighting unit 250 may include a memory 252 and a sensor weight determination unit 254. The sensor weight determination unit 254 may apply different weights for each sensor when the surrounding environment detected by the surrounding detection units 225A and 225B requires different levels of autonomous driving control. Additionally, when the surrounding environment detected by the surrounding detection units 225A and 225B requires different levels of autonomous driving control, the driving control units 224A and 224B can apply object recognition models with different computational processing capacities.

Figure 3 is a block diagram showing the configuration of the error detection unit 230 according to an embodiment of the present disclosure.

As shown, the error detection unit 230 may include a memory 232 and an error pattern detection unit 234. A defect list 300 including defects or error patterns related to the processor or its peripheral devices may be stored in the memory 232 of the error detection unit 230. Based on the error pattern of the defect list 300, the error pattern detection unit 234 can detect errors in the processors 221A and 221B. Error pattern items in the defect list 300 include, for example, Electro-Magnetic Interference (EMI) operation error pattern 310, Electro-Magnetic Compatibility (EMC) operation error pattern 320, temperature error pattern 330, It may include, but is not limited to, a processor error pattern 340, a power error pattern 350, a memory CRC (Cyclic Redundancy Check) error pattern 360, etc.

Among the error pattern items in the defect list 300, EMI (Electro-Magnetic Interference) may mean electromagnetic interference, where electromagnetic waves radiated or conducted from various electronic components installed in an autonomous vehicle affect the functions of other devices. It may mean causing an obstacle to . Additionally, EMC (Electro-Magnetic Compatibility) can mean electromagnetic compatibility or compatibility, and can mean the ability of a device to secure performance by applying to both the transmitting and receiving sides of electromagnetic waves. The temperature error pattern 330 may be a temperature error in a portion of the system circuit and may mean a temperature level that affects the circuit. The processor error pattern 340 may refer to an error pattern that can be checked by BIST (Built-in Self-Test) or the like. The power error pattern 350 may mean supplying power above or below the power range in which the system can operate normally. Memory CRC error pattern 360 can be divided into hardware problems and software problems. It can be caused by direct damage to data due to storage method or work method, storage error, virus, etc., and can be caused by bad sectors or physical damage to the storage medium. It can be caused by crash damage.

Figure 4 is a block diagram showing the configuration of a first processor and a second processor according to an embodiment of the present disclosure.

FIG. 4 shows the configuration of the first processor 221A and the second processor 221B in the control instruction unit 220 in detail. The first processor 221A may include a main operation unit 223A and a memory 440, and the main operation unit 223A may include a driving control unit 224A and a peripheral monitoring unit 225A. The second processor 221B may include a sub-operation unit 223B and a memory 470, and the sub-operation unit 223B may include a driving control unit 224B and a peripheral monitoring unit 225B. In FIG. 4, the memories 440 and 470 are shown as being configured outside the main operation unit 223A and the sub operation unit 223B, but may also be configured inside the main operation unit 223A and the sub operation unit 223B.

In one embodiment, the driving control unit 224A of the main operation unit 223A may be comprised of a sensor set determination unit 410, and the peripheral monitoring unit 225A may be comprised of an object recognition model application unit 430. . The driving control unit 224B of the sub-computation unit 223B may be comprised of a sensor set determination unit 450, and the surrounding monitoring unit 225B may be comprised of an object recognition model application unit 460.

In one embodiment, when different levels of autonomous driving control are required depending on the surrounding situation detected by the surrounding detection unit 225A, the driving control unit 224A of the main operation unit 223A uses the sensor set determination unit 410. Decide on different sensor sets. The surrounding detection unit 225A of the driving control unit 224A detects the surrounding situation, and when different levels of autonomous driving control are required depending on the surrounding situation, the object recognition model application unit 430 applies a different object recognition model. . Information about different sensor sets and different object recognition models may be stored in memory 440.

In one embodiment, the driving control unit 224B of the sub-computing unit 223B sets a sensor set when different levels of autonomous driving control are required from the first processor 221A depending on the surrounding situation detected by the surrounding detection unit 225B. The decision unit 450 determines a different sensor set. The surrounding detection unit 225B of the driving control unit 224B detects the surrounding situation, and when a different level of autonomous driving control is required from the first processor 221A depending on the surrounding situation, the object recognition model application unit 460 Apply different object recognition models. Information about different sensor sets and different object recognition models may be stored in memory 470.

In one embodiment, the driving control unit 224B of the sub-operation unit 223B independently processes signals received from some of the plurality of sensors while generating the first control signal set in the main operation unit 223A, and A second control signal set that has a smaller range than the first control signal set generated by the calculation unit 223A may be generated. The sub-operation unit 223B may not retain main control of the autonomous vehicle 110 until the error detection unit 230 detects an error in the first processor 221A. The second control signal set generated by the sub-computing unit 223B may be an autonomous driving control signal to respond to an error in the first processor 221A.

Figure 5 is a flowchart showing a method of operating an autonomous driving system based on a redundant structure according to an embodiment of the present disclosure.

The operating method 500 of the autonomous driving system shown in FIG. 5 may begin with step 510 of receiving sensor data. In one embodiment, the sensing data received in step 510 may be sensing data received from the camera 130, LIDAR 140, and radar 150, but is not limited thereto.

Step 520 of detecting surrounding environment information may be performed. In one embodiment, the surrounding environment information may be information sensed by the surrounding detection units 225A and 225B of the main calculation unit 223A and the sub calculation unit 223B using a plurality of sensing data.

Step 530 of generating a first set of control signals may be performed in the first processor. In one embodiment, the first control signal set may be generated by applying data from different sensor sets and an object recognition model with different computational processing capacity when different levels of autonomous driving control are required depending on the surrounding environment.

Step 540 may be performed in which the second processor recognizes surrounding environment information by processing a signal received from a portion of the sensor. In one embodiment, the surrounding environment information may be information sensed by the surrounding detection unit 225B of the sub-computing unit 223B using a plurality of sensing data.

Step 550 of determining whether the first processor is operating abnormally may be performed. In one embodiment, determination of whether the first processor is operating abnormally may be performed by the error detection unit 230 and may be based on the defect list 300 stored in the memory 232.

In step 550, in response to the determination that the first processor is operating abnormally, main control may be transferred to the second processor. In one embodiment, the second processor 221B may receive main control rights from the processor 221A and generate an autonomous driving control signal by applying data from different sensor sets and/or object recognition models with different computational processing capacities. there is.

The method 500 of operating an autonomous driving system may further include generating a first control signal set in a second processor (570). In one embodiment, the first control signal set may be a control signal set with a larger range than the second control signal set generated by the second processor 221B before error detection by the first processor 221A.

Figure 6 is a flowchart showing a method of operating an autonomous driving system based on a redundant structure according to another embodiment of the present disclosure.

As shown, the operating method 600 of the autonomous driving system may begin with the step 610 of receiving sensor data. In one embodiment, the sensing data received in step 610 may be the camera 130, the lidar 140, or the radar 150, but is not limited thereto.

Step 620 of detecting surrounding environment information may be performed. In one embodiment, the surrounding environment information may be information sensed by the surrounding detection units 225A and 225B of the main calculation unit 223A and the sub calculation unit 223B using a plurality of sensing data.

Additionally, step 630 of generating a first set of control signals may be performed in the first processor. In one embodiment, the first control signal set can be generated by applying data from different sensor sets and/or object recognition models with different computational processing capacities when different levels of autonomous driving control are required depending on the surrounding environment. .

Step 640 may be performed in which the second processor recognizes surrounding environment information by processing a signal received from a portion of the sensor. In one embodiment, the surrounding environment information may be information sensed by the surrounding detection unit 225B of the sub-computing unit 223B using a plurality of sensing data.

Step 650 of determining whether the first processor is operating abnormally may be performed. In one embodiment, the determination of abnormal operation of the first processor may be performed by the error detection unit 230 and may be based on the defect list 300 stored in the memory 232.

In response to the determination in step 650 that the first processor is operating abnormally, step 660 of transferring main control to the second processor may be performed. In one embodiment, the second processor 221B may receive main control and generate a driving control signal by applying data from a different sensor set and/or an object recognition model with a different computational processing capacity.

Step 670 of generating a first set of control signals may be executed in a second processor. In one embodiment, the first control signal set may be a control signal set with a larger range than the second control signal set generated by the second processor 221B before error detection by the first processor 221A.

In response to the determination in step 650 that the first processor 221A is operating normally, step 652 requesting different levels of autonomous driving may be executed.

In response to the determination in step 652 that different levels of autonomous driving are required, step 654 of applying different weights for each sensor to signals received from a plurality of sensors may be performed. In one embodiment, when entering a city from a highway or when the number of vehicles 160 increases around the autonomous vehicle 110, a high weight may be applied to all sensors. For example, the shadow block 124 applies a high weight to the camera 130 for low-level autonomous driving control when the surrounding environment is relatively simple and the risk of an accident is low, while other sensors 140 and 150 ), a low weight can be applied. In another example, the shadow block 124 may apply a high weight to all sensors 130, 140, and 150 for high-level autonomous driving control when the surrounding environment is relatively complex and the risk of an accident is high.

A step 656 in which the second processor applies an object recognition model with a different computational processing capacity may be executed. Additionally, step 658 may be performed in which the second processor generates a second control signal set. In one embodiment, the second processor 221B may generate a control signal set even without control authority. The second control signal set generated by the second processor 221B may have a smaller range than the first control signal set generated by the first processor 221A.

According to the above-described embodiments, in the autonomous driving control system including a plurality of processors with a duplicated structure, the processor with main control rights (e.g., the first processor) recognizes the surrounding environment and performs autonomous driving based on this. While executing control, another processor (eg, a second processor) may only perform awareness of the surrounding environment. In this configuration, when a defect occurs in the first processor with main control, the second processor is in a state of recognizing the surrounding environment, so when main control is transferred from the first processor to the second processor, the second processor The processor can immediately execute autonomous driving control according to the main control authority based on the results of recognizing the surrounding environment. Accordingly, while the main control right is transferred from the first processor to the second processor, the blank period of normal autonomous driving control can be minimized and system stability can be guaranteed. Additionally, the second processor can minimize overall system power consumption by only recognizing the surrounding environment while not in main control, thereby reducing standby power consumption while not in main control.

The above-described method may be provided as a computer program stored in a computer-readable recording medium for execution on a computer. The medium may continuously store a computer-executable program, or may temporarily store it for execution or download. In addition, the medium may be a variety of recording or storage means in the form of a single or several pieces of hardware combined. It is not limited to a medium directly connected to a computer system and may be distributed over a network. Examples of media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, And there may be something configured to store program instructions, including ROM, RAM, flash memory, etc. Additionally, examples of other media include recording or storage media managed by app stores that distribute applications, sites or servers that supply or distribute various other software, etc.

The methods, operations, or techniques of this disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate this interchange of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and design requirements imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementations should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques may include one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs). ), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, and other electronic units designed to perform the functions described in this disclosure. , a computer, or a combination thereof.

Accordingly, the various illustrative logical blocks, modules, and circuits described in connection with this disclosure may be general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or It may be implemented or performed as any combination of those designed to perform the functions described in. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other configuration.

For firmware and/or software implementations, techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), and PROM ( on computer-readable media such as programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage devices, etc. It may also be implemented as stored instructions. Instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described in this disclosure.

Although the above-described embodiments have been described as utilizing aspects of the presently disclosed subject matter in one or more standalone computer systems, the disclosure is not limited thereto and may also be implemented in conjunction with any computing environment, such as a network or distributed computing environment. . Furthermore, aspects of the subject matter of this disclosure may be implemented in multiple processing chips or devices, and storage may be similarly effected across the multiple devices. These devices may include PCs, network servers, and portable devices.

Although the present disclosure has been described in relation to some embodiments in the specification, it should be noted that various modifications and changes can be made without departing from the scope of the present disclosure as can be understood by those skilled in the art. something to do. Additionally, such modifications and changes should be considered to fall within the scope of the claims appended hereto.

110: autonomous vehicle 120: autonomous driving module
122: Main Block 124: Shadow Block
130: Camera 140: LIDAR
150: Radar 160: Vehicle
200: Autonomous driving control system 210: Sensor unit
220: control instruction unit 221A: first processor
222A: Sensor bus interface 223A: Main operation unit
224A: Driving control unit 225A: Surrounding detection unit
221B: Second processor 222B: Sensor bus interface
223B: Sub-operation unit 224B: Driving control unit
225B: Perimeter detection unit 230: Error detection unit
232: Memory 234: Error pattern detection unit
240: Emergency response unit 242: Alarm unit
244: Emergency route creation unit 250: Weight assignment unit
252: Memory 254: Sensor weight determination unit
300: Fault List (300) 410: Sensor set decision unit
430: Object recognition model application unit 440: Memory
450: Sensor set decision unit 460: Object recognition model application unit
470: Memory

Claims (10)

In an autonomous driving control system based on a redundant structure,
A plurality of sensors configured to detect information about the surrounding environment of the autonomous vehicle;
a first processor that holds main control rights of the autonomous vehicle and is configured to process signals received from the plurality of sensors to generate a first set of control signals used to control the autonomous vehicle; and
A second processor configured to detect the surrounding environment of the vehicle by processing signals received from at least some of the plurality of sensors,
When an operation error by the first processor is detected, the first processor transfers the main control to the second processor so that the second processor is reconfigured to generate the first control signal set,
While the first processor processes signals received from at least some of the plurality of sensors to generate the first set of control signals, the second processor:
Signals received from at least some of the plurality of sensors are independently processed to generate a second control signal set having a smaller range than the first control signal set,
The second processor to which the main control rights have been transferred,
It is reconfigured to generate at least a portion of the first control signal set according to the sensed surrounding environment, and when the sensed surrounding environment requires different levels of autonomous driving control, signals received from the plurality of sensors are adjusted for each different sensor. An autonomous driving control system that is reconfigured to apply weights and to apply an object recognition model with different computational processing capacity to signals received from the plurality of sensors when the sensed surrounding environment requires a different level of autonomous driving control. . According to paragraph 1,
It further includes a memory that stores a plurality of pattern information related to operation errors in the autonomous driving control system,
Autonomous driving control that determines that an operation error of the first processor has occurred when the operation pattern of the first processor or a peripheral device associated with the first processor is the same or similar to at least one of a plurality of pattern information stored in the memory. system.
According to paragraph 2,
The plurality of pattern information includes at least one of an EMI or EMC operation error pattern, a temperature error pattern, a processor error pattern, a power error pattern, a memory CRC error pattern, and a memory bit error pattern.
delete delete delete delete According to paragraph 1,
The plurality of sensors include at least one of a LiDAR sensor, a laser sensor, an infrared sensor, and a camera.
delete delete

Images