Vehicle control method and device

Abstract

The invention discloses a vehicle control method and device which are applied to the technical field of vehicles. A control device and a plurality of intelligent driving chips are deployed on the vehicle, and the plurality of intelligent driving chips share calculation required by the first intelligent driving system together. When the first intelligent driving system operates normally, the control device can receive a first vehicle control command and predictive vehicle control information at the current moment, and the predictive vehicle control information is used for indicating a vehicle control command to be executed on the vehicle within a predictive time range. The first intelligent driving system can fully utilize all computing power of the plurality of intelligent driving chips to execute calculation, so that the utilization rate of the computing power of the system is improved. In addition, when some intelligent driving chips break down, some normal intelligent driving chips start the second intelligent driving system, and the computing power needed by operation of the second intelligent driving system is smaller than that needed by operation of the first intelligent driving system. In the starting process of the second intelligent driving system, the control device executes vehicle control based on the predictive vehicle control information, time is provided for starting of the second intelligent driving system, and the safety of the vehicle is ensured.

Description

Technical Field

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

[0002] To ensure autonomous vehicles can handle any emergencies promptly, they typically add intelligent driving chips to achieve redundant computing power. This redundancy significantly enhances the safety of autonomous driving systems. Currently, high-level intelligent driving systems typically use at least two intelligent driving chips (such as system-on-chips (SOCs)).

[0003] Taking two SOCs as an example, these two SOCs obtain data from sensors and use the perception and control algorithms of the intelligent driving system to perform the same processing. Based on the results of the processing, they respectively send vehicle control commands to the microcontroller unit (MCU). The MCU compares and arbitrates the received vehicle control commands to determine that the two vehicle control commands match. Then, the MCU sends the vehicle control command to the corresponding actuator to realize vehicle control. When one of the SOCs fails, the other SOC can also control the vehicle in real time to ensure vehicle safety. It can be seen that the redundant intelligent driving chip only repeats the calculation of the intelligent driving chip. The actual computing power used by the current perception and control algorithm is only half of the entire system, and the resource utilization rate is low. Summary of the Invention

[0004] This application discloses a vehicle control method and device that can utilize the full computing power of multiple intelligent driving chips, improving the utilization rate of system computing power. In addition, it is also beneficial to ensure vehicle safety in the event of a single intelligent driving chip failure.

[0005] In the first aspect, the present application provides a vehicle control method, which is applied to a control device of a vehicle. The vehicle also includes multiple intelligent driving chips, which share the calculations required by the first intelligent driving system. The vehicle control method includes: receiving a first vehicle control command and predicted vehicle control information, and sending the first vehicle control command to the corresponding actuator in the vehicle. The first vehicle control command and the predicted vehicle control information come from at least one of the multiple intelligent driving chips mentioned above. The first vehicle control command is the vehicle control command at the current moment, and the predicted vehicle control information is used to indicate the vehicle control command to be executed on the vehicle within the predicted time range.

[0006] Illustratively, multiple intelligent driving chips share the calculations required by the first intelligent driving system, which means that: in terms of computing power, the computing power that each of the multiple intelligent driving chips can provide is less than the computing power required for the operation of the first intelligent driving system, but the sum of the computing power that the multiple intelligent driving chips can provide is greater than or equal to the computing power required for the operation of the first intelligent driving system; in terms of function, the multiple intelligent driving chips respectively perform different computing tasks to realize different functions of the first intelligent driving system, and the multiple intelligent driving chips work together to jointly realize the first intelligent driving system.

[0007] The predicted time range refers to the predicted time range in which the vehicle control command may need to be executed, and is not necessarily the time range in which the vehicle control command will actually be executed. Here, the predicted time range can be a future time range, which provides a vehicle control command sequence in advance, which can be used to facilitate the control device to control the vehicle in the event that one of the multiple intelligent driving chips fails at the next moment, thereby ensuring vehicle safety; or the predicted time range can include the current time point and a future time range, or even a past time point.

[0008] In the above method, while the first intelligent driving system is operating normally (i.e., all multiple intelligent driving chips are operating normally), the vehicle control device can obtain the current first vehicle control command and predicted vehicle control information from at least one of the multiple intelligent driving chips, fully utilizing the computing power of the multiple intelligent driving chips and improving the utilization rate of the system computing power. In addition, the predicted vehicle control information can be used by the control device to control the vehicle when a fault occurs in one of the intelligent driving chips, which helps ensure the safety of the vehicle.

[0009] In a possible implementation of the first aspect, the above-mentioned multiple intelligent driving chips include a first intelligent driving chip and other intelligent driving chips, and the vehicle control method also includes: when a failure of the first intelligent driving chip is detected, executing vehicle control based on predicted vehicle control information, and sending indication information to other intelligent driving chips, where the indication information is used to instruct the startup of a second intelligent driving system, wherein the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

[0010] There is no limit on the number of other intelligent driving chips; it could be one or more. If there is only one other intelligent driving chip, the other chip can independently run the second intelligent driving system, and the computing power provided by the other chip is greater than or equal to the computing power required for the second intelligent driving system to operate. If there are multiple other intelligent driving chips, the other chips share the computations required for the second intelligent driving system, and the sum of the computing power provided by the other chips is greater than or equal to the computing power required for the second intelligent driving system to operate.

[0011] Under this implementation, if the failure of the first intelligent driving chip causes the first intelligent driving system to be unable to continue normal operation, the control device takes over the vehicle and promptly notifies the normal intelligent driving chip (such as other intelligent driving chips) to start the second intelligent driving system. During the startup of the second intelligent driving system, the control device executes vehicle control based on the predicted vehicle control information, thereby improving the safety of the vehicle.

[0012] In a possible implementation of the first aspect, the first intelligent driving system is deployed on the above-mentioned multiple intelligent driving chips, and the second intelligent driving system is deployed on at least one intelligent driving chip among the above-mentioned multiple intelligent driving chips.

[0013] Here, deploying the first intelligent driving system on multiple intelligent driving chips means that the various functional modules (or algorithms) of the first intelligent driving system are distributed across these multiple intelligent driving chips. In other words, each of the multiple intelligent driving chips can implement part of the functions of the first intelligent driving system. Therefore, deploying the first intelligent driving system on a single intelligent driving chip is a partial deployment.

[0014] The deployment of the second intelligent driving system on at least one of the multiple intelligent driving chips means that: at least one of the multiple intelligent driving chips deploys various functional modules (or algorithms) of the second intelligent driving system, that is, a single intelligent driving chip deployed with the second intelligent driving system can realize all the functions of the second intelligent driving system. It can be seen that the deployment of the second intelligent driving system on a single intelligent driving chip is a complete deployment. In this case, the single intelligent driving chip can independently run the second intelligent driving system, and the second intelligent driving system supports a single intelligent driving chip to independently control the vehicle. In some schemes, the deployment of the second intelligent driving system on a single intelligent driving chip can also be a partial deployment. In this case, the number of intelligent driving chips required for the deployment of the second intelligent driving system is less than the number of intelligent driving chips required for the deployment of the first intelligent driving system.

[0015] To implement this embodiment, the first intelligent driving system requires multiple intelligent driving chips to be implemented together, and the second intelligent driving system supports the implementation of a single intelligent driving chip.

[0016] In a possible implementation of the first aspect, the predicted vehicle control information is the most recently received information in history before the control device detects a failure in the first intelligent driving chip, and the second intelligent driving system is started within the above-mentioned predicted time range.

[0017] In this implementation, the vehicle's positional movement is within the tolerance range, and the difference between the vehicle's driving environment when the predicted vehicle control information is obtained and the vehicle's current driving environment when the first intelligent driving chip is detected is relatively small. This improves vehicle control accuracy and contributes to improving vehicle safety. Furthermore, the second intelligent driving system is activated within the predicted time range, providing ample time for the second intelligent driving system to start.

[0018] In a possible implementation of the first aspect, the vehicle control method further includes: receiving feedback information from other intelligent driving chips, the feedback information being used to indicate that the startup of the second intelligent driving system is complete; and in response to the feedback information, stopping the execution of vehicle control through the predicted vehicle control information.

[0019] In this implementation, the control device only briefly takes over the vehicle during the startup of the second intelligent driving system. After the startup of the second intelligent driving system is completed, the control device stops controlling the vehicle through predictive vehicle control, and the right to control the vehicle is handed over to the other intelligent driving chips mentioned above, which is beneficial to improving the safety of the vehicle.

[0020] In a possible implementation of the first aspect, after stopping vehicle control through predicted vehicle control information, the vehicle control method further includes: receiving a second vehicle control command from other intelligent driving chips; and sending the second vehicle control command to a corresponding actuator in the vehicle.

[0021] By implementing the above implementation method, after the second intelligent driving system is started, the control device can also assist the first intelligent driving chip in controlling the vehicle.

[0022] In a possible implementation of the first aspect, the above-mentioned multiple intelligent driving chips include a first intelligent driving chip and other intelligent driving chips, and the vehicle control method also includes: when a failure of the first intelligent driving chip is detected, obtaining monitoring perception data of the current environment from other intelligent driving chips; and executing vehicle control based on the predicted vehicle control information and the monitoring perception data.

[0023] As the vehicle moves, an obstacle may suddenly appear in front of the vehicle. The control device can perceive this change in time by obtaining the monitoring and perception data of the current environment. It can improve the accuracy of decision-making by combining the monitoring and perception data of the current environment with the predicted vehicle control information to execute vehicle control.

[0024] In a possible implementation of the first aspect, vehicle control is performed according to the predicted vehicle control information and the monitored perception data, including: controlling the vehicle to pull over or park in its own lane according to the predicted vehicle control information and the monitored perception data.

[0025] In this way, the vehicle can be parked safely and the intelligent driving system can be prevented from losing control due to a failure of the intelligent driving chip.

[0026] In a possible implementation of the first aspect, the above-mentioned multiple intelligent driving chips are all system-on-chip (SOC), and the control device is a microcontroller unit (MCU).

[0027] In a second aspect, the present application provides a vehicle control method, which is applied to a target intelligent driving chip. The target intelligent driving chip belongs to multiple intelligent driving chips of the vehicle. These multiple intelligent driving chips share the calculations required by the first intelligent driving system, and these multiple intelligent driving chips also include the first intelligent driving chip. The vehicle control method includes: in the event of a failure of the first intelligent driving chip, starting a second intelligent driving system. The computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

[0028] Here, please refer to the description of the corresponding content of the first aspect above for the first intelligent driving system and the second intelligent driving system, and will not be repeated here.

[0029] In this method, the computations required by the first intelligent driving system are shared across multiple intelligent driving chips. This means that the multiple intelligent driving chips work together to enable the normal operation of the first intelligent driving system, fully utilizing the computing power of multiple intelligent driving chips and improving system computing power utilization. Furthermore, the second intelligent driving system is only activated when one intelligent driving chip fails. This second intelligent driving system can be considered a backup system, ensuring vehicle safety in the event of a chip failure, and the second intelligent driving system does not need to be online in real time.

[0030] In a possible implementation of the second aspect, the first intelligent driving system is deployed on the above-mentioned multiple intelligent driving chips, and the second intelligent driving system is deployed on at least one intelligent driving chip among the above-mentioned multiple intelligent driving chips, and the at least one intelligent driving chip includes the target intelligent driving chip.

[0031] Under this implementation method, the deployment of the first intelligent driving system on a single intelligent driving chip is a partial deployment, and the deployment of the second intelligent driving system on a single intelligent driving chip is a complete deployment. Therefore, the first intelligent driving system requires multiple intelligent driving chips to be implemented together, and the second intelligent driving system supports the implementation of a single intelligent driving chip.

[0032] In a possible implementation of the second aspect, the vehicle control method further includes: in the event that the first intelligent driving chip fails, receiving indication information from the vehicle's control device, the indication information instructing to start the second intelligent driving system; the above-mentioned starting of the second intelligent driving system means: starting the second intelligent driving system in response to the indication information.

[0033] Under this implementation method, the operation of the target intelligent driving chip to start the second intelligent driving system can be triggered by the instruction information sent by the vehicle's control device. The target intelligent driving chip does not need to monitor the status of other intelligent driving chips in real time, which reduces the power consumption of the target intelligent driving chip and is also conducive to reducing the difficulty of hardware and software design of the target intelligent driving chip.

[0034] In a possible implementation of the second aspect, the number of the plurality of intelligent driving chips is two, and initiating the second intelligent driving system in the event of a failure of the first intelligent driving chip refers to: upon detecting a failure of the first intelligent driving chip, activating the second intelligent driving system and sending a notification message to a control device of the vehicle. The notification message indicates to the control device that the vehicle is under control and / or that the first intelligent driving chip has failed.

[0035] In this implementation, the target intelligent driving chip can also actively start the second intelligent driving system. That is, the target intelligent driving chip can monitor the status of each intelligent driving chip in real time. When the target intelligent driving chip detects a fault in an intelligent driving chip (such as the first intelligent driving chip), the target intelligent driving chip can actively start the second intelligent driving system and synchronize the information of the first intelligent driving chip fault to the control device in a timely manner, so that the control device can execute vehicle control based on the predicted vehicle control information. The target intelligent driving chip has a fast response speed, which improves the startup speed of the second intelligent driving system and is also conducive to improving the safety of the vehicle during the startup of the second intelligent driving system.

[0036] In a possible implementation of the second aspect, the vehicle control method further includes: after the second intelligent driving system is started, sending feedback information to the control device, where the feedback information is used to indicate that the second intelligent driving system is started.

[0037] Under this implementation method, after the second intelligent driving system is started, the target intelligent driving chip can also inform the control device of the completion of the startup of the second intelligent driving system through feedback information, so that the control device stops executing vehicle control through predicting vehicle control information.

[0038] In a possible implementation of the second aspect, the vehicle control method further includes: after the second intelligent driving system is started, controlling the vehicle to perform pull-over parking or self-lane parking.

[0039] In this implementation, after the second intelligent driving system is started, the target intelligent driving chip takes over the vehicle. This implementation method can be applied to scenarios that do not require a driver to be in the loop. For example, for the autonomous driving system level defined by the Society of Automatic Engineers (SAE), the second intelligent driving system can be an autonomous driving system above the L3+ level, or the second intelligent driving system can be a subsystem of an autonomous driving system above the L3+ level, which is used to implement some functions of an autonomous driving system above the L3+ level. In this way, by controlling the vehicle to stop, the safety of the vehicle can be improved, avoiding vehicle loss of control due to intelligent driving chip failure under high-level intelligent driving systems, and protecting the safety of passengers.

[0040] In a possible implementation of the second aspect, after controlling the vehicle to perform pull-over parking or self-lane parking, the vehicle control method further includes: controlling the vehicle to travel in response to a start instruction.

[0041] In this implementation, after controlling the vehicle to park, the target intelligent driving chip can also control the vehicle's movement in response to a start-up command from the vehicle user. When applied to an autonomous driving system with a second intelligent driving system at level L3+ or above, it can support the vehicle in completing the functions of autonomous driving systems below level L2, and of course, it can also support the vehicle in implementing the functions of the second intelligent driving system itself. Here, if the level of the second intelligent driving system is the same as that of the first intelligent driving system, for example, both are at level L3, the functional complexity of the second intelligent driving system is lower than that of the first intelligent driving system, that is, the functions implemented by the second intelligent driving system are not as rich as those implemented by the first intelligent driving system.

[0042] In one possible implementation of the second aspect, when the multiple intelligent driving chips described above are not faulty, the vehicle control method further includes: determining a first vehicle control command and / or predicted vehicle control information based on a processing result, and transmitting the first vehicle control command and / or predicted vehicle control information. The processing result includes calculation results of some or all of the multiple intelligent driving chips, the processing result being associated with the first intelligent driving system, the first vehicle control command being the current vehicle control command, and the predicted vehicle control information being used to indicate a vehicle control command to be executed on the vehicle within a predicted time range.

[0043] When implementing the above-mentioned implementation method, during the normal operation of the first intelligent driving system, the target intelligent driving chip may also generate a first vehicle control command and / or predicted vehicle control information. The first vehicle control command can meet the current vehicle control needs, and the predicted vehicle control information can be used by the control device to control the vehicle when there is a failure in the intelligent driving chip, which is beneficial to improving the safety of the vehicle.

[0044] In a possible implementation of the second aspect, sending the first vehicle control command and / or predicted vehicle control information includes: sending the first vehicle control command and / or predicted vehicle control information to the control device when the control device has no faults.

[0045] When implementing the above-mentioned implementation method, during the operation of the first intelligent driving system, if the control device works normally, the target intelligent driving chip can also provide the control device with the current vehicle control command and / or a vehicle control command sequence within the predicted time range, so that the control device can take over the vehicle in time when there is a failure of the intelligent driving chip, which is beneficial to improving the safety of the vehicle.

[0046] In a possible implementation of the second aspect, sending the first vehicle control command and / or predicted vehicle control information includes: in the event of a control device failure, sending the first vehicle control command to a corresponding actuator in the vehicle.

[0047] Under this implementation method, in the event of a control device failure, the target intelligent driving chip can directly issue the first vehicle control command without going through the control device, which is conducive to improving communication efficiency.

[0048] In a possible implementation of the second aspect, the above-mentioned multiple intelligent driving chips are all system-on-chip (SOC), and the control device is a microcontroller unit (MCU).

[0049] On the third aspect, the present application provides a device for vehicle control, which is a control device for the vehicle or is included in the control device. The vehicle also includes a plurality of intelligent driving chips, and these multiple intelligent driving chips share the calculations required by the first intelligent driving system. The above-mentioned device includes: a receiving unit for receiving a first vehicle control command and predicted vehicle control information; a sending unit for sending the first vehicle control command to the corresponding actuator in the vehicle. The first vehicle control command and the predicted vehicle control information come from at least one of the above-mentioned multiple intelligent driving chips, the first vehicle control command is the vehicle control command at the current moment, and the predicted vehicle control information is used to indicate the vehicle control command to be executed on the vehicle within the predicted time range.

[0050] In a possible implementation of the third aspect, the above-mentioned multiple intelligent driving chips include a first intelligent driving chip and other intelligent driving chips, and the above-mentioned device also includes a processing unit, which is used to: when a failure of the first intelligent driving chip is detected, perform vehicle control based on predicted vehicle control information; the sending unit is also used to send indication information to other intelligent driving chips, and the indication information is used to instruct the startup of a second intelligent driving system, wherein the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

[0051] In a possible implementation of the third aspect, the predicted vehicle control information is the most recently received information in history before the control device detects a failure in the first intelligent driving chip, and the second intelligent driving system is started within the above-mentioned predicted time range.

[0052] In a possible implementation of the third aspect, the first intelligent driving system is deployed on the above-mentioned multiple intelligent driving chips, and the second intelligent driving system is deployed on at least one intelligent driving chip among the above-mentioned multiple intelligent driving chips.

[0053] In a possible implementation of the third aspect, the receiving unit is further used to receive feedback information from other intelligent driving chips, where the feedback information is used to indicate that the startup of the second intelligent driving system is complete; the processing unit is further used to: in response to the feedback information, stop executing vehicle control through predicting vehicle control information.

[0054] In a possible implementation of the third aspect, after stopping vehicle control through predicted vehicle control information, the receiving unit is also used to: receive a second vehicle control command from other intelligent driving chips; the sending unit is also used to send the second vehicle control command to the corresponding actuator in the vehicle.

[0055] In a possible implementation of the third aspect, the above-mentioned multiple intelligent driving chips include a first intelligent driving chip and other intelligent driving chips, and the receiving unit is further used to: when the processing unit detects a failure of the first intelligent driving chip, obtain monitoring perception data of the current environment from other intelligent driving chips; the processing unit is also used to execute vehicle control based on the predicted vehicle control information and the monitoring perception data.

[0056] In a possible implementation of the third aspect, the processing unit is specifically used to control the vehicle to park on the side of the road or in its own lane based on the predicted vehicle control information and the monitoring perception data.

[0057] In a possible implementation of the third aspect, the above-mentioned multiple intelligent driving chips are all system-on-chip (SOC), and the control device is a microcontroller unit (MCU).

[0058] In a fourth aspect, the present application provides a device for vehicle control, which is a target intelligent driving chip or is included in a target intelligent driving chip. The target driving chip belongs to multiple intelligent driving chips of the vehicle, and the multiple intelligent driving chips share the calculations required by the first intelligent driving system. These multiple intelligent driving chips also include the first intelligent driving chip. The above-mentioned device includes: a processing unit, which is used to start the second intelligent driving system in the event of a failure of the first intelligent driving chip; wherein the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

[0059] In a possible implementation of the fourth aspect, the first intelligent driving system is deployed on the above-mentioned multiple intelligent driving chips, and the second intelligent driving system is deployed on at least one intelligent driving chip among the above-mentioned multiple intelligent driving chips, and the at least one intelligent driving chip includes the target intelligent driving chip.

[0060] In a possible implementation of the fourth aspect, the above-mentioned device also includes: a receiving unit, used to receive indication information from the control device of the vehicle when the first intelligent driving chip fails, the indication information is used to instruct the startup of the second intelligent driving system; the processing unit is specifically used to: start the second intelligent driving system in response to the indication information.

[0061] In a possible implementation of the fourth aspect, the number of the above-mentioned multiple intelligent driving chips is two, and the processing unit is specifically used to: start the second intelligent driving system when the processing unit detects a failure of the first intelligent driving chip; the above-mentioned device also includes a sending unit, which is used to send notification information to the control device of the vehicle, wherein the notification information is used to indicate that the control device controls the vehicle and / or the first intelligent driving chip has failed.

[0062] In a possible implementation of the fourth aspect, the sending unit of the above-mentioned device is also used to: after the second intelligent driving system is started up, send feedback information to the control device, and the feedback information is used to indicate that the startup of the second intelligent driving system is completed.

[0063] In a possible implementation of the fourth aspect, the processing unit is further used to: after the second intelligent driving system is started, control the vehicle to perform pull-over parking or self-lane parking.

[0064] In a possible implementation of the fourth aspect, the processing unit is further configured to: after controlling the vehicle to perform pull-over parking or self-lane parking, respond to a start instruction to control the vehicle to travel.

[0065] In one possible implementation of the fourth aspect, when the multiple intelligent driving chips described above are not faulty, the processing unit is further configured to: determine a first vehicle control command and / or predicted vehicle control information based on a processing result; and the sending unit is further configured to: send the first vehicle control command and / or predicted vehicle control information. The processing result includes calculation results of some or all of the multiple intelligent driving chips, and the processing result is associated with the first intelligent driving system. The first vehicle control command is the current vehicle control command, and the predicted vehicle control information indicates the vehicle control command to be executed on the vehicle within a predicted time range.

[0066] In a possible implementation manner of the fourth aspect, the sending unit is specifically configured to: when the control device is fault-free, send the first vehicle control command and / or predicted vehicle control information to the control device.

[0067] In a possible implementation of the fourth aspect, the sending unit is specifically configured to: in the event of a failure of the control device, send a first vehicle control command to a corresponding actuator in the vehicle.

[0068] In a possible implementation of the fourth aspect, the above-mentioned multiple intelligent driving chips are all system-on-chip (SOC), and the control device is a microcontroller unit (MCU).

[0069] In a fifth aspect, the present application provides a chip for vehicle control, which includes a processor and a memory, wherein the memory is used to store program instructions; the processor calls the program instructions in the memory, so that the chip executes the method in the first aspect or any possible implementation of the first aspect, or executes the method in the second aspect or any possible implementation of the second aspect.

[0070] In the sixth aspect, the present application provides a vehicle control system, which includes multiple intelligent driving chips and a control device, wherein the control device is used to implement the method in the above-mentioned first aspect or any possible implementation of the first aspect, and the first intelligent driving chip among the multiple intelligent driving chips is used to implement the method in the second aspect or any possible implementation of the second aspect.

[0071] In the seventh aspect, the present application provides a vehicle, which includes the device of any possible implementation of the third aspect or the first aspect, and / or includes the device of the fourth aspect or any possible implementation of the fourth aspect; or includes the chip of the fifth aspect; or includes the vehicle control system of the sixth aspect.

[0072] In an eighth aspect, the present application provides a computer-readable storage medium comprising computer instructions, which, when executed by a processor, implement the method of the above-mentioned first aspect or any possible implementation of the first aspect, or implement the method of the above-mentioned second aspect or any possible implementation of the second aspect.

[0073] In the ninth aspect, the present application provides a computer program product, which, when executed by a processor, implements the method in the above-mentioned first aspect or any possible embodiment of the first aspect, or implements the method in the above-mentioned second aspect or any possible implementation of the second aspect.

[0074] Illustratively, a computer program product may include a software product (eg, a software installation package) or a hardware product (eg, a computer-readable storage medium). BRIEF DESCRIPTION OF THE DRAWINGS

[0075] Figure 1 This is a schematic diagram of the architecture of a vehicle control system provided by an embodiment of the present application;

[0076] Figure 2 This is a schematic diagram of the deployment of an intelligent driving system in multiple intelligent driving chips provided in an embodiment of the present application;

[0077] Figure 3A This is a schematic diagram of deploying a first intelligent driving system on multiple intelligent driving chips provided by an embodiment of the present application;

[0078] Figure 3B This is a schematic diagram of another deployment of a first intelligent driving system on multiple intelligent driving chips provided by an embodiment of the present application;

[0079] Figure 3C This is a schematic diagram of another deployment of a first intelligent driving system on multiple intelligent driving chips provided by an embodiment of the present application;

[0080] Figure 4 is a flow chart of a vehicle control method provided by an embodiment of the present application;

[0081] Figure 5 This is a flow chart of another vehicle control method provided by an embodiment of the present application;

[0082] Figure 6This is a flow chart of another vehicle control method provided by an embodiment of the present application;

[0083] Figure 7 is a schematic structural diagram of a computing device provided in an embodiment of the present application;

[0084] Figure 8 It is a structural diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0085] In this solution, prefixes such as "first" and "second" are used only to distinguish different description objects, and do not have any limiting effect on the position, order, priority, quantity or content of the described objects. For example, if the described object is a "field", then the ordinal number before the "field" in the "first field" and the "second field" does not limit the position or order between the "fields". "First" and "second" do not limit whether the "fields" they modify are in the same message, nor do they limit the order of the "first field" and the "second field". For another example, if the described object is a "level", then the ordinal number before the "level" in the "first level" and the "second level" does not limit the priority between the "levels". For another example, the number of described objects is not limited by the prefix and can be one or more. Taking "first device" as an example, the number of "devices" can be one or more. In addition, the objects modified by different prefixes can be the same or different. For example, if the described object is a "device," then the "first device" and the "second device" can be the same device, the same type of device, or different types of devices. For another example, if the described object is "information," then the "first information" and the "second information" can be information of the same content or information of different contents. In short, the use of prefixes to distinguish the described objects in the embodiments of this application does not constitute a limitation on the described objects. For the description of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.

[0086] In this solution, descriptions such as "at least one of a1, a2, ..., and an" include any one of a1, a2, ..., and an, as well as any combination of any number of a1, a2, ..., and an. Each of these can exist alone. For example, the description "at least one of a, b, and c" includes a alone, b alone, c alone, a combination of a and b, a combination of a and c, a combination of b and c, or a combination of a, b, and c.

[0087] To facilitate understanding, the following first introduces relevant terms that may be involved in the embodiments of this application.

[0088] (1) Autonomous driving, or intelligent driving (also referred to as smart driving), refers to a computer system that uses data collected by a perception system (e.g., multiple sensors) to identify or detect objects, generates results through calculation and analysis, and controls the terminal or assists a human driver or other decision-making body in controlling the terminal. An intelligent driving algorithm is an algorithm that processes data to generate output results that can be used directly to control the vehicle and / or to assist other decision-making bodies (e.g., human drivers) in controlling the vehicle. In some solutions, the intelligent driving algorithm is integrated into the intelligent driving system.

[0089] The Society of Automotive Engineers (SAE) provides a driving automation grading standard, including driving levels L0 to L5.

[0090] Among them, Level 0 means no automation, and the human driver has full control over the vehicle. During driving, the driver can receive warnings or assistance from the driving system, such as autonomous emergency braking (AEB), blind spot monitoring (BSM) or lane departure warning (LDW).

[0091] Level L1 is driving assistance, in which driving operations are completed jointly by the human driver and the driving system. The driving system can provide driving assistance for steering wheel or acceleration and deceleration operations based on the driving environment. Other driving operations are performed by the human driver, such as adaptive cruise control (ACC) or lane keep assistance / support (LKA / LKS).

[0092] Level 2 is partial automation, which provides driving assistance for multiple aspects of steering and acceleration and deceleration based on the driving environment. Other driving actions are performed by human drivers, such as the following function that combines adaptive cruise control (ACC) and lane keep assistance (LKA).

[0093] Level L3 is conditional automation, where all driving operations can be completed by the driving system, but the human driver needs to respond to the driving system's requests at the appropriate time, that is, the human driver needs to be prepared to take over the driving system.

[0094] Level L4 is highly automated, and all driving operations can be completed by the driving system. The human driver does not necessarily need to respond to the driving system's requests. For example, when road and environmental conditions permit (such as closed campuses, highways, urban roads or fixed driving routes), the human driver may not take over driving.

[0095] Level L5 is fully automated, and all driving operations under various road and environmental conditions that human drivers can handle can be completed autonomously by the driving system.

[0096] As can be seen, at levels L0 to L2, the driving system mainly provides support to the driver. The driver still needs to supervise the driving and steer, brake, or accelerate as needed to ensure safety. At levels L3 to L5, the driving system can complete all driving operations on behalf of the driver. At level L3, the driver must be prepared to take over the driving. At levels L4 and L5, the driving system can achieve full driving under some or all conditions, and the driver can choose whether to take over.

[0097] The above classification is an example. With the evolution of technology or different regulations in different countries or regions, the above classification may change. For example, the vehicle automation classification proposed by the Ministry of Industry and Information Technology of China includes 6 levels of vehicle driving automation, of which 0-2 is driving assistance, the system assists humans in performing dynamic driving tasks, and the driving subject remains the driver; 3-5 is autonomous driving, the system replaces humans in performing dynamic driving tasks under the designed operating conditions, and when the function is activated, the driving subject is the system. The names and definitions of each level are as follows:

[0098] Level 0 driving automation (emergency assistance) systems cannot continuously perform lateral or longitudinal vehicle motion control during dynamic driving tasks, but have the ability to continuously perform some object and event detection and response capabilities during dynamic driving tasks;

[0099] Level 1 driving automation (partial driver assistance) systems continuously perform lateral or longitudinal vehicle motion control in dynamic driving tasks under their designed operating conditions (or designed operating range (ODD)) and have the ability to detect and respond to some targets and events that are compatible with the executed lateral or longitudinal vehicle motion control;

[0100] Level 2 driving automation (combined driver assistance) systems continuously perform lateral and longitudinal vehicle motion control in dynamic driving tasks under their designed operating conditions, and have the ability to detect and respond to certain objects and events that are appropriate to the lateral and longitudinal vehicle motion control performed;

[0101] Level 3 driving automation (conditionally automated driving) means the system continuously performs all dynamic driving tasks under the conditions for which it is designed.

[0102] Level 4 driving automation (highly automated driving) systems continuously perform all dynamic driving tasks under their designed operating conditions and automatically implement minimal risk strategies;

[0103] Level 5 driving automation (fully automated driving) systems continuously perform all dynamic driving tasks and automatically implement minimal risk strategies under all drivable conditions.

[0104] The above-mentioned lateral control is mainly used for controlling the steering of the vehicle, for example, controlling the steering wheel torque or angle to control the direction of the vehicle; the longitudinal control is mainly used for controlling the speed of the vehicle, for example, controlling the brake pedal, accelerator pedal, or gear position to control the acceleration / deceleration, braking, etc. of the vehicle.

[0105] Here, the autonomous driving in this solution can be any level of autonomous driving that can partially or fully participate in vehicle driving.

[0106] (2) The driver is in real time

[0107] Driver-in-the-loop (DITL) refers to an operating mode in which the driver of an automated or assisted driving system maintains constant monitoring of the vehicle and can immediately take control when necessary. This constant presence is crucial for safe driving, especially in the less mature state of automated driving technology. By maintaining driver engagement, automated driving systems can mitigate safety risks caused by technical failures or unexpected situations.

[0108] Taking the autonomous driving classification standards provided by the above-mentioned SAE as an example, autonomous driving systems at levels L0 to L2 require the driver to be in the loop in real time, while autonomous driving systems at levels L3 and above do not require the driver to be in the loop in real time.

[0109] (3) Driving scenario, or simply scenario, refers to the environmental space in which a vehicle is traveling, including but not limited to traffic participants and the surrounding environment. Driving scenarios can be used to test the responsiveness and performance of autonomous driving systems in various situations.

[0110] The above terms may be optionally used in the following embodiments.

[0111] This solution provides a vehicle control system that fully utilizes the computing power of the vehicle's intelligent driving chip when the intelligent driving system is operating normally, achieving high resource utilization. In the event of an intelligent driving chip failure, this vehicle control system can support a single intelligent driving chip to activate a backup intelligent driving system, enabling independent control of the vehicle by the single intelligent driving chip, thus ensuring vehicle safety.

[0112] The following describes the components of the vehicle control system. Figure 1 , Figure 1 This is a schematic diagram of the architecture of a vehicle control system provided by an embodiment of the present application. Figure 1 As shown, the vehicle control system includes a control device and the above-mentioned multiple intelligent driving chips, wherein each of the multiple intelligent driving chips can communicate with the control device in a wireless or wired manner. The multiple intelligent driving chips can also communicate with each other in a wireless or wired manner.

[0113] Here, the term "intelligent driving chip" refers to a chip specifically designed for autonomous driving systems. Autonomous driving systems are also referred to as intelligent driving systems, or simply "intelligent driving systems." The primary function of an intelligent driving chip is to process data from sensors surrounding the vehicle (such as image acquisition devices (e.g., cameras), lidar, radar, etc.) to enable real-time environmental perception, vehicle decision-making, and control.

[0114] Exemplarily, the intelligent driving chip can be a system on chip (SOC), an artificial intelligence (AI) acceleration chip, etc., or it can be a component within the chip, such as an integrated circuit, a processor, etc.

[0115] Control devices are generally used for functional safety-related monitoring, diagnosis, and vehicle control, and possess a high level of safety. In this solution, for example, if the control device detects a fault in one of the multiple intelligent driving chips, it can temporarily take over the vehicle to ensure vehicle safety.

[0116] Exemplarily, the control device may be a microcontroller unit (MCU) or a component within the MCU.

[0117] The following describes how the control device and multiple intelligent driving chips are deployed on the vehicle.

[0118] Here, the above-mentioned control device and multiple intelligent driving chips can be deployed on the vehicle's controller. Exemplarily, the controller includes but is not limited to a hardware and software integrated platform for supporting intelligent driving, namely a vehicle computing platform (vehicle computing platform), such as a mobile data center (MDC); a hardware and software integrated platform for supporting body control and chassis control, such as a vehicle domain controller (VDC); a hardware and software integrated platform for providing in-vehicle multimedia services (such as head-up display, instrument panel display, entertainment audio and video, etc.), such as a cockpit domain controller (CDC). In some schemes, the above-mentioned MDC can also be called an advanced driving assistance system domain controller (ADASDC) or an automatic drive domain controller (AD DC).

[0119] In some solutions, the controller may also be a domain controller that performs the functions of at least one of the MDC, VDC, and CDC. When a controller integrates the functions of the MDC, VDC, and CDC, the controller may also be called a central computing unit.

[0120] As an example, the above-mentioned control device and multiple intelligent driving chips can be deployed on the same controller (such as the above-mentioned MDC).

[0121] In some solutions, the control device and multiple intelligent driving chips can also be deployed separately on different controllers. For example, the control device is deployed on the VDC, and the multiple intelligent driving chips are deployed on the MDC.

[0122] In some solutions, the multiple intelligent driving chips can be deployed separately on different controllers, or some of the multiple intelligent driving chips can be deployed on one controller and others on another controller. For example, the multiple intelligent driving chips include intelligent driving chip 1 and intelligent driving chip 2, where intelligent driving chip 1 can be deployed on the MDC and intelligent driving chip 2 can be deployed on the VDC.

[0123] Figure 1The vehicle control system shown can be applied to a variety of application scenarios, such as the following: mobile internet (MI), industrial control, self-driving, transportation safety, Internet of Things (IoT), smart city, or smart home.

[0124] Figure 1 The vehicle control system shown can be applied to multiple network types, for example, one or more of the following network types: SparkLink, long term evolution (LTE) network, 5th generation mobile communication technology (5G), wireless local area network (for example, Wi-Fi), Bluetooth (BT), Zigbee, or vehicle-mounted short-range wireless communication network, etc.

[0125] Figure 1 This is only an exemplary architecture diagram, but not limited to Figure 1 The system shown includes the number of network elements. Figure 1 Not shown, but Figure 1 In addition to the functional entities shown, Figure 1 Other functional entities may also be included. In addition, the method provided in the embodiment of the present application can be applied to Figure 1 The vehicle control system shown, of course, the method provided in the embodiment of the present application can also be applied to other vehicle control systems, for example, also including connected sensors.

[0126] In this plan, Figure 1 Multiple intelligent driving chips in the system share the computations required by the first intelligent driving system. Optionally, a second intelligent driving system is deployed on at least one of the multiple intelligent driving chips, and the computing power required to operate the second intelligent driving system is less than the computing power required to operate the first intelligent driving system. When the second intelligent driving system is stored in the memory of a single intelligent driving chip, the second intelligent driving system supports implementation on a single intelligent driving chip.

[0127] In this solution, when all of the above-mentioned multiple intelligent driving chips are in good working order, the first intelligent driving system is started. This working mode can be called, for example, a multi-chip intelligent driving mode or a normal mode. For example, in the case where a single intelligent driving chip is deployed with a second intelligent driving system, if one of the above-mentioned multiple intelligent driving chips fails, the second intelligent driving system is started. This working mode can be called a single-chip intelligent driving mode. From this, it can be seen that the second intelligent driving system can be regarded as an intelligent driving system that serves as a backup, which can ensure vehicle safety when there is a failure of the intelligent driving chip, and the second intelligent driving system does not need to be online in real time.

[0128] As an example, the functional complexity of the first intelligent driving system is higher than that of the second intelligent driving system. In some embodiments, the level of the first intelligent driving system is higher than or equal to the level of the second intelligent driving system. It is understood that the higher the level of the intelligent driving system, the richer the functions of the intelligent driving system. Here, when the level of the first intelligent driving system is equal to the level of the second intelligent driving system, the functions of the first intelligent driving system are richer than those of the second intelligent driving system.

[0129] Illustratively, multiple intelligent driving chips share the calculations required by the first intelligent driving system, which means that: in terms of computing power, the computing power that each of the multiple intelligent driving chips can provide is less than the computing power required for the operation of the first intelligent driving system, but the sum of the computing power that the multiple intelligent driving chips can provide is greater than or equal to the computing power required for the operation of the first intelligent driving system; in terms of function, the multiple intelligent driving chips respectively perform different computing tasks to realize different functions of the first intelligent driving system, and the multiple intelligent driving chips work together to jointly realize the first intelligent driving system.

[0130] Here, the first intelligent driving system is deployed on multiple intelligent driving chips. The deployment of the first intelligent driving system on multiple intelligent driving chips means that the various functional modules (or algorithms) of the first intelligent driving system are dispersed across these multiple intelligent driving chips. In other words, each of the multiple intelligent driving chips can implement part of the functions of the first intelligent driving system. It can be seen that the deployment of the first intelligent driving system on a single intelligent driving chip is a partial deployment.

[0131] The deployment of the second intelligent driving system on at least one of the multiple intelligent driving chips means that at least one of the multiple intelligent driving chips has its memory storing the various functional modules (or algorithms) of the second intelligent driving system. Therefore, the deployment of the second intelligent driving system on a single intelligent driving chip is a complete deployment. In this case, the second intelligent driving system supports implementation on a single intelligent driving chip. Support for a single intelligent driving chip by the second intelligent driving system means that, in terms of computing power, the computing power provided by the single intelligent driving chip is greater than or equal to the computing power required for the operation of the second intelligent driving system; and in terms of functionality, the single intelligent driving chip on which the second intelligent driving system is deployed can implement all the functions of the second intelligent driving system.

[0132] In some solutions, the deployment of the second intelligent driving system on a single intelligent driving chip can also be partial deployment. For example, the second intelligent driving system is deployed on M intelligent driving chips among multiple intelligent driving chips, where M is an integer greater than 1 and M is less than the total number of intelligent driving chips. Then, the various functional modules (or algorithms) of the second intelligent driving system are dispersedly deployed on these M intelligent driving chips. These M intelligent driving chips share the calculations required by the second intelligent driving system. In this case, the second intelligent driving system needs to be jointly implemented by these M intelligent driving chips. It can be understood that the number of intelligent driving chips involved in the dispersed deployment of the second intelligent driving system is less than the number of intelligent driving chips involved in the deployment of the first intelligent driving system.

[0133] See also Figure 2 , Figure 2 This is a schematic diagram of the deployment of a plurality of intelligent driving systems in intelligent driving chips provided in an embodiment of the present application. Figure 2 In this article, taking multiple intelligent driving chips including intelligent driving chip 1 and intelligent driving chip 2 as an example, the deployment method of the above-mentioned first intelligent driving system and the second intelligent driving system on these multiple intelligent driving chips is described, and the multiple intelligent driving chips are not limited to only including intelligent driving chip 1 and intelligent driving chip 2.

[0134] exist Figure 2 In the example, both intelligent driving chip 1 and intelligent driving chip 2 are fully connected to the vehicle's sensors, so that both intelligent driving chip 1 and intelligent driving chip 2 can obtain monitoring and perception data of the current environment from the vehicle's sensors. Here, the vehicle's sensors include but are not limited to image acquisition devices, Lidar, and Radar. For example, the image acquisition device can be a camera, etc.

[0135] Depend on Figure 2 It can be seen that the first intelligent driving system is dispersedly deployed on intelligent driving chip 1 and intelligent driving chip 2, and intelligent driving chip 1 and intelligent driving chip 2 share the calculation required by the first intelligent driving system. Optionally, a second intelligent driving system is also deployed on intelligent driving chip 1 and intelligent driving chip 2 respectively. Figure 2 It can be seen that the deployment of the second intelligent driving system on a single intelligent driving chip is a complete deployment. Figure 2 The above is only an example of the deployment of the second intelligent driving system. In some scenarios, the deployment of the second intelligent driving system on a single intelligent driving chip can also be the partial deployment mentioned above.

[0136] Both the first and second intelligent driving systems have perception and regulation functions. In other words, each system has its own perception module and regulation module. The perception module is used to implement the perception function, and the regulation module is used to implement the regulation function. In some solutions, the perception module is also called the perception algorithm, and the regulation module is also called the regulation algorithm.

[0137] Since multiple intelligent driving chips jointly implement the first intelligent driving system, the deployment methods of the perception module of the first intelligent driving system and the regulation and control module of the first intelligent driving system on these multiple intelligent driving chips are relatively flexible. Please mainly refer to the following first implementation method to the third implementation method.

[0138] First implementation method: The perception module of the first intelligent driving system can be deployed in a dispersed manner on multiple intelligent driving chips, and the regulation and control module of the first intelligent driving system can also be deployed in a dispersed manner on these multiple intelligent driving chips.

[0139] Figure 3A As Figure 2 An example of the deployment of the first intelligent driving system on multiple intelligent driving chips. Figure 3A In the figure, the perception module of the first intelligent driving system includes perception module A and perception module B, wherein perception module A is deployed on intelligent driving chip 1 and perception module B is deployed on intelligent driving chip 2; the regulation and control module of the first intelligent driving system includes regulation and control module C and regulation and control module D, wherein regulation and control module C is deployed on intelligent driving chip 1 and regulation and control module D is deployed on intelligent driving chip 2. In other words, intelligent driving chip 1 stores part of the perception modules of the first intelligent driving system and part of the regulation and control modules of the first intelligent driving system, so the types of computing tasks executed by intelligent driving chip 1 include perception tasks and regulation and control tasks; intelligent driving chip 2 stores part of the perception modules of the first intelligent driving system and part of the regulation and control modules of the first intelligent driving system, so the types of computing tasks executed on intelligent driving chip 2 include perception tasks and regulation and control tasks.

[0140] Second implementation method: The perception module of the first intelligent driving system can be dispersedly deployed on at least one intelligent driving chip, and the regulation and control module of the first intelligent driving system can also be dispersedly deployed on these multiple intelligent driving chips.

[0141] Figure 3B As Figure 2 An example of the deployment of the first intelligent driving system on multiple intelligent driving chips. Figure 3B It can be seen that the perception module of the first intelligent driving system includes perception module A and perception module B, and the regulation and control module of the first intelligent driving system includes regulation and control module C and regulation and control module D. Among them, perception module A, perception module B, and regulation and control module C are all deployed on intelligent driving chip 1, and regulation and control module D is deployed on intelligent driving chip 2.

[0142] In some solutions, the perception module of the first intelligent driving system can also be deployed in a distributed manner on multiple intelligent driving chips, and the regulation and control module of the first intelligent driving system can also be deployed in a distributed manner on at least one intelligent driving chip. Figure 3B The above-mentioned perception module A, regulation and control module C and regulation and control module D are all deployed on the intelligent driving chip 1, and the perception module B is deployed on the intelligent driving chip 2.

[0143] Third implementation method: The above-mentioned multiple intelligent driving chips include a first group of intelligent driving chips and a second group of intelligent driving chips, wherein the perception modules of the first intelligent driving system are dispersedly deployed on the first group of intelligent driving chips, and the regulation and control modules of the first intelligent driving system are dispersedly deployed on the second group of intelligent driving chips.

[0144] Figure 3C As Figure 2 An example of the deployment of the first intelligent driving system on multiple intelligent driving chips. Figure 3C It can be seen that the first intelligent driving system includes a perception module and a regulation and control module. Among them, the perception module of the first intelligent driving system is deployed on the intelligent driving chip 1, and the regulation and control module of the first intelligent driving system is deployed on the intelligent driving chip 2. This means that the type of computing task performed by the intelligent driving chip 1 is a perception task, and the type of computing task performed by the intelligent driving chip 2 is a regulation and control task.

[0145] Here, the deployment of the first intelligent driving system on these multiple intelligent driving chips can be flexibly deployed according to the computing power that each intelligent driving chip can provide. The more computing power the intelligent driving chip can provide, the more modules of the first intelligent driving system can be deployed on the intelligent driving chip. This solution does not limit the deployment of the first intelligent driving system on multiple intelligent driving chips to only Figure 3A-3C In some solutions, it is not limited to fully connecting each of the multiple intelligent driving chips with the vehicle's sensors.

[0146] See also Figure 4 , Figure 4 This is a flow chart of a vehicle control method provided by an embodiment of the present application. This method can be applied to Figure 1 The vehicle control system of the vehicle shown is specifically applied between the control device and multiple intelligent driving chips, wherein the multiple intelligent driving chips include at least intelligent driving chip 1 and intelligent driving chip 2.

[0147] In this solution, vehicles can be new energy vehicles or traditional vehicles, depending on their power sources. Traditional vehicles refer to fuel vehicles, such as gasoline vehicles and diesel vehicles; new energy vehicles include electric vehicles (EVs), hybrid electric vehicles (HEVs), range-extended EVs, plug-in hybrid vehicles (HEVs), fuel cell vehicles, or other new energy vehicles.

[0148] Figure 4 The method shown in the embodiment includes but is not limited to the following steps S401-S407.

[0149] S401: At least one intelligent driving chip among the multiple intelligent driving chips sends a first vehicle control command and predicted vehicle control information to a control device, and the multiple intelligent driving chips jointly share the calculations required by the first intelligent driving system.

[0150] Correspondingly, the control device receives the first vehicle control command and the predicted vehicle control information, wherein the first vehicle control command and the predicted vehicle control information come from at least one intelligent driving chip among the above-mentioned multiple intelligent driving chips.

[0151] The first vehicle control command is the vehicle control command at the current moment. Exemplarily, the first vehicle control command includes an identifier of a target actuator and vehicle control parameters. The target actuator is the actuator that executes the first vehicle control command.

[0152] For example, when the type of the first vehicle control command is a speed control command, the vehicle control parameters include acceleration / deceleration and the specific speed indicated to be reached; when the first vehicle control command is a steering control command, the vehicle control parameters include the steering wheel speed, the steering wheel rotation angle, etc.; when the first vehicle control command is a braking command, the vehicle control parameters include braking intensity (such as emergency braking or light braking) and braking duration.

[0153] Here, the first vehicle control command is not limited to the above-mentioned speed control command, steering control command or braking command, and may also be other vehicle control commands (such as a parking command, etc.). In addition, the first vehicle control command is not limited to only one command, and may also be a combination of multiple commands, such as a compound command of accelerating first and then braking.

[0154] The predicted vehicle control information is used to indicate the vehicle control commands that will be executed on the vehicle within the predicted time range. The predicted time range refers to the predicted time range in which the vehicle control command may need to be executed, and is not necessarily the time range in which the vehicle control command is actually executed. Here, the predicted time range can be a future time range, so that a vehicle control command sequence is provided in advance, which is used to facilitate the control device to control the vehicle in the next moment when one of the multiple intelligent driving chips fails, thereby ensuring vehicle safety; or the predicted time range can include the current time point and the future time range, and can even include the past time point.

[0155] Exemplarily, the predicted time range can be a time segment, which can be expressed in an absolute time format, for example, the time segment is expressed based on a start time and an end time; the time segment can also be expressed in a relative manner, for example, the time segment is expressed based on a start time and a duration.

[0156] As an example, the predicted vehicle control information includes at least one vehicle control command to be executed within the predicted time range and time information corresponding to each control command. The time information can be an execution moment or an execution time interval.

[0157] Exemplarily, the above-mentioned first vehicle control command and predicted vehicle control information can be obtained by calculating multiple intelligent driving chips based on the driving environment information within the visual range currently detected by the vehicle's sensors by executing the perception and control algorithms of the first intelligent driving system. In some schemes, the above-mentioned multiple intelligent driving chips can also perform predictions in combination with map information from a cloud server. The map information stored in the cloud server includes driving environment information of the road where the vehicle is currently located, wherein the driving environment information includes multiple items of the following information: weather, visibility, light intensity, road type, number of lanes, road flatness, road smoothness, road construction conditions, and obstacles on the road (including static obstacles and dynamic obstacles that affect vehicle driving, etc.). In this way, the first intelligent driving system can maximize the computing power of multiple intelligent driving chips.

[0158] Here, the first intelligent driving system is deployed on the above-mentioned multiple intelligent driving chips. For the specific deployment form of the first intelligent driving system, please refer to the above Figure 2 The description of the corresponding contents in the embodiments will not be repeated here.

[0159] It can be understood that as the vehicle travels, the driving environment information within the current line of sight detected by the vehicle's sensors and the above-mentioned map information can be obtained in real time or periodically, so the above-mentioned first vehicle control command and predicted vehicle control information can also be sent periodically or periodically.

[0160] As an example, when the first intelligent driving system operates normally (that is, the above-mentioned multiple intelligent driving chips are all fault-free), at least one of the multiple intelligent driving chips sends a first control command and predicted vehicle control information to the control device.

[0161] In one implementation, one of the multiple intelligent driving chips may send the first vehicle control command and predicted vehicle control information to the control device, including: intelligent driving chip 1 sending the first vehicle control command and predicted vehicle control information to the control device, or intelligent driving chip 2 sending the first vehicle control command and predicted vehicle control information to the control device. In some solutions, when the number of the multiple intelligent driving chips is greater than two, one of the multiple intelligent driving chips other than intelligent driving chip 1 and intelligent driving chip 2 may also send the first vehicle control command and predicted vehicle control information to the control device.

[0162] Taking the intelligent driving chip 1 as an example, assuming that the first vehicle control command and predicted vehicle control information are sent by the intelligent driving chip 1, it means that part or all of the regulation and control algorithms of the first intelligent driving system are deployed on the intelligent driving chip 1, or a module that implements the regulation and control function in the first intelligent driving system is deployed on the intelligent driving chip 1. Therefore, the type of computing task executed by the intelligent driving chip 1 includes regulation and control tasks.

[0163] In another implementation, some of the multiple intelligent driving chips can send the first vehicle control command and predicted vehicle control information to the control device, including: intelligent driving chip 1 sending the first vehicle control command to the control device, and intelligent driving chip 2 sending the predicted vehicle control information. In other words, the first vehicle control command and predicted vehicle control information can be sent by different intelligent driving chips among the multiple intelligent driving chips.

[0164] It can be understood that the first vehicle control command is sent by the intelligent driving chip 1 and the predicted vehicle control information is sent by the intelligent driving chip 2, which means that the regulation and control algorithms of the first intelligent driving system are distributed on the intelligent driving chip 1 and the intelligent driving chip 2. Therefore, the type of computing tasks executed by the intelligent driving chip 1 at least includes the regulation and control tasks, and the type of computing tasks executed by the intelligent driving chip 2 at least includes the regulation and control tasks.

[0165] S402: The control device stores the predicted vehicle control information and sends a first vehicle control command to an actuator corresponding to the vehicle.

[0166] Exemplarily, when the control device has no faults, the control device receives the first vehicle control command and the predicted vehicle control information.

[0167] Exemplarily, the control device sends a first vehicle control command to a corresponding actuator, including: the control device sends the first vehicle control command to a target actuator based on an identifier of the target actuator in the first vehicle control command. It can be seen that when the multiple intelligent driving chips described above operate normally, vehicle control is achieved by these multiple intelligent driving chips.

[0168] S403: When the control device detects a fault in the intelligent driving chip 1, it controls the vehicle according to the predicted vehicle control information and sends instruction information to other intelligent driving chips. Correspondingly, the other intelligent driving chips receive the instruction information from the control device.

[0169] Among them, the instruction information is used to instruct the startup of the second intelligent driving system. The computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system. Here, please refer to the aforementioned second intelligent driving system, the first intelligent driving system, the relationship between the two, the deployment form, etc. Figure 2 The description of the corresponding contents of the embodiment will not be repeated here.

[0170] Here, the other intelligent driving chips include at least intelligent driving chip 2. The number of intelligent driving chips included in the other intelligent driving chips can be one or more. A second intelligent driving system is deployed on the other intelligent driving chips. It can be understood that the other intelligent driving chips are all intelligent driving chips with normal functions (i.e., no failures).

[0171] In one implementation, the deployment of the second intelligent driving system on a single intelligent driving chip is a complete deployment. For complete deployment, please refer to Figure 2The deployment form of the second intelligent driving system is shown. In this case, the other intelligent driving chip is any intelligent driving chip deployed with the second intelligent driving system among the multiple intelligent driving chips except the faulty intelligent driving chip (i.e., intelligent driving chip 1), that is, the number of other intelligent driving chips is one.

[0172] For example, if the number of the aforementioned multiple intelligent driving chips is two, that is, the multiple intelligent driving chips include intelligent driving chip 1 and intelligent driving chip 2, then the other intelligent driving chip is intelligent driving chip 2. Therefore, when a fault in intelligent driving chip 1 is detected, the control device sends indication information to intelligent driving chip 2. For another example, if the number of the aforementioned multiple intelligent driving chips is three, that is, the multiple intelligent driving chips include intelligent driving chip 1, intelligent driving chip 2, and intelligent driving chip 3, then the other intelligent driving chip is intelligent driving chip 2 or intelligent driving chip 3. When a fault in intelligent driving chip 1 is detected, the control device may send indication information to intelligent driving chip 2, or the control device may send indication information to intelligent driving chip 3.

[0173] In another implementation, the deployment of the second intelligent driving system on a single intelligent driving chip is a partial deployment, then the number of other intelligent driving chips is multiple, and the other intelligent driving chips share the calculations required by the second intelligent driving system. In this case, the control device sends indication information to other intelligent driving chips, which means: the control device sends indication information to each of the other intelligent driving chips. For example, the other intelligent driving chips include intelligent driving chip 2 and intelligent driving chip 3, then the control device sends indication information to one of the other intelligent driving chips, which can be: the control device sends indication information to intelligent driving chip 2 and intelligent driving chip 3.

[0174] For example, the control device may initiate vehicle control based on the predicted vehicle control information and send instruction information to other intelligent driving chips simultaneously. In some embodiments, the control device may first initiate vehicle control based on the predicted vehicle control information and, during the vehicle control process, also send instruction information to other intelligent driving chips.

[0175] For example, the control device can determine whether the intelligent driving chip has failed by monitoring at least one of the following information: the power supply voltage, operating temperature, and information stored in the status register (which stores the operating status information of the intelligent driving chip) of each of the multiple intelligent driving chips. When the control device detects that the intelligent driving chip 1 meets any of the following conditions, it is determined that the intelligent driving chip 1 has failed:

[0176] The power supply voltage is not within the normal operating range;

[0177] The operating temperature is greater than the upper temperature limit; or,

[0178] The status register stores information including fault signals.

[0179] In some solutions, a fault detection and reporting mechanism can be designed on the intelligent driving chip. When the intelligent driving chip fails, the intelligent driving chip will send an alarm message or fault code. In this case, the control device may receive an alarm message or fault code from the intelligent driving chip 1, so the control device determines that the intelligent driving chip 1 is faulty. In some solutions, the control device can also use a watchdog timer (WDT) to monitor the operation of the intelligent driving chip. If the control device does not receive a response from the intelligent driving chip 1 within the agreed time, the control device determines that the intelligent driving chip 1 is faulty.

[0180] In some solutions, the control device detects a fault in the intelligent driving chip 1, and it can also be: the control device receives notification information, the notification information is used to indicate that the intelligent driving chip 1 has failed; the control device determines that the intelligent driving chip 1 has failed based on the notification information. In other words, fault detection can also be performed between intelligent driving chips. When a certain intelligent driving chip detects that another intelligent driving chip has failed, the intelligent driving chip actively informs the control device in the form of a notification information. Furthermore, the control device can also determine that the intelligent driving chip 1 has failed only when it receives multiple notifications from different intelligent driving chips that the intelligent driving chip 1 has failed, thereby improving credibility.

[0181] Since the above-mentioned multiple intelligent driving chips share the calculations required by the first intelligent driving system, when an intelligent driving chip (such as intelligent driving chip 1) among the multiple intelligent driving chips fails, it means that the first intelligent driving system will not be able to continue to operate normally.

[0182] When the vehicle control device detects a fault in the intelligent driving chip 1, it controls the vehicle based on the predicted vehicle control information. This predicted vehicle control information is obtained during the normal operation of the first intelligent driving system. Even if the first intelligent driving system cannot continue to operate normally due to a fault in the intelligent driving chip, the predicted vehicle control information can support the control device to control the vehicle within a certain period of time. In this case, control of the vehicle is switched from the multiple intelligent driving chips to the control device, which helps improve vehicle safety.

[0183] For example, assume that the predicted vehicle control information includes vehicle control command 1, the execution time of vehicle control command 1 at time 1, vehicle control command 2, the execution time of vehicle control command 2 at time 2, and vehicle control command 3, with the execution time of vehicle control command 3 at time 3, where time 1 is earlier than time 2, and time 2 is earlier than time 3, vehicle control command 1 includes the identifier of actuator 1, vehicle control command 2 includes the identifier of actuator 2, and vehicle control command 3 includes the identifier of actuator 3. The control device then executes vehicle control according to the predicted vehicle control information, which may be: the control device sends vehicle control command 1 to actuator 1 at time 1, sends vehicle control command 2 to actuator 2 at time 2, and sends vehicle control command 3 to actuator 3 at time 3. There is a time delay between sending and receiving vehicle control commands, but in this solution, the time delay between sending and receiving vehicle control commands can be ignored.

[0184] In some schemes, it is predicted that the time information corresponding to a certain vehicle control command (such as vehicle control command 1) may appear in the vehicle control information as an execution time interval, and the control device can issue the vehicle control command based on the execution time interval corresponding to the vehicle control command.

[0185] As an example, the execution time interval corresponding to vehicle control command 1 represents a time period during which execution of control command 1 may occur. In this case, the control device issues vehicle control command 1 based on the execution time interval corresponding to vehicle control command 1. This can be done by: the control device sends vehicle control command 1 to the actuator corresponding to vehicle control command 1 at a target time, where the target time falls within the execution time interval corresponding to vehicle control command 1. The target time can be any time within the execution time interval corresponding to vehicle control command 1.

[0186] In one implementation, the predicted vehicle control information is the most recent information received by the control device before the fault in the intelligent driving chip 1 was detected. This ensures that the vehicle's positional movement is within an acceptable error range, and the difference between the vehicle's driving environment when the predicted vehicle control information was obtained and the vehicle's current driving environment when the intelligent driving chip 1 was detected is minimal. This improves vehicle control accuracy and contributes to enhanced vehicle safety.

[0187] The second intelligent driving system is activated within the predicted time range in the predictive vehicle control information, and the activation duration of the second intelligent driving system is shorter than the duration included in the above predicted time range. This provides time for the activation of the second intelligent driving system.

[0188] S404: In response to the instruction information, other intelligent driving chips start the second intelligent driving system.

[0189] For example, the number of other intelligent driving chips is one, and the second intelligent driving system is fully deployed in the other intelligent driving chips. In response to the indication information, the other intelligent driving chip reads the second intelligent driving system from its own memory to start the second intelligent driving system.

[0190] For another example, there are multiple other intelligent driving chips, and the second intelligent driving system is dispersedly deployed on each of the other intelligent driving chips. In response to the indication information, each of the other intelligent driving chips reads part of the modules (or algorithms) of the second intelligent driving system from its own memory to start the second intelligent driving system.

[0191] S405: When the second intelligent driving system is started, the other intelligent driving chips send feedback information to the control device. Correspondingly, the control device receives the feedback information from the other intelligent driving chips.

[0192] Among them, the feedback information is used to indicate that the startup of the second intelligent driving system is complete.

[0193] S406: In response to the feedback information, the control device stops executing vehicle control through the predicted vehicle control information.

[0194] That is, once the second intelligent driving system is activated, the control device will stop using the predicted vehicle control information to control the vehicle, and control of the vehicle will be transferred from the control device back to the intelligent driving chip.

[0195] S407: After the second intelligent driving system is started, other intelligent driving chips control the vehicle to park on the side of the road or in its own lane.

[0196] That is, when the second intelligent driving system is activated, the other intelligent driving chips will take control of the vehicle. Combined with S406, it can be seen that the control right of the vehicle will be transferred from the control device to the other intelligent driving chips.

[0197] As an example, the other intelligent driving chip is intelligent driving chip 2, which controls the vehicle to park by the side of the road or in its own lane. This implementation method is applicable to scenarios where the driver is not required to be in the loop. For example, for the aforementioned SAE-defined autonomous driving system level, the second intelligent driving system can be an autonomous driving system above the L3+ level, or the second intelligent driving system can also be a subsystem of an autonomous driving system above the L3+ level, which is used to implement some functions of an autonomous driving system above the L3+ level. In this way, the safety of the vehicle can be improved, and the loss of control of the vehicle due to intelligent driving chip failure in a high-level intelligent driving system can be avoided, and the safety of passengers can also be protected.

[0198] In some schemes, other intelligent driving chips still take intelligent driving chip 2 as an example. When the second intelligent driving system is started, intelligent driving chip 2 can prompt the driver to take over the vehicle; intelligent driving chip 2 controls the vehicle to pull over or park in the lane, which can be: when it is detected that the driver has not taken over the vehicle within a preset time, intelligent driving chip 2 controls the vehicle to pull over or park in the lane.

[0199] In some possible embodiments, after controlling the vehicle to pull over or park in the lane, the intelligent driving chip 2 may also receive a start instruction from the vehicle user; in response to the start instruction, the intelligent driving chip 2 controls the vehicle to travel. The start instruction is used to instruct the vehicle to start. Here, when this embodiment is applied to the above-mentioned second intelligent driving system as an automatic driving system above the L3+ level, it is sufficient to support the vehicle to complete the functions of the automatic driving system below the L2 level, and of course it can also support the vehicle to realize the functions of the second intelligent driving system itself. Here, if the level of the second intelligent driving system is the same as that of the first intelligent driving system, for example, the L3 level, the functional complexity of the second intelligent driving system is lower than that of the first intelligent driving system, that is, the functions realized by the second intelligent driving system are not as rich as those realized by the first intelligent driving system.

[0200] For example, the vehicle user may be a driver, a passenger, etc.

[0201] Furthermore, during the process of the intelligent driving chip 2 controlling the driving of the vehicle, the intelligent driving chip 2 can send a second vehicle control command to the control device; after receiving the second vehicle control command, the control device can send the second vehicle control command to the corresponding actuator in the vehicle.

[0202] In some possible embodiments, the above-mentioned multiple intelligent driving chips obtain the first vehicle control command and predicted vehicle control information. When a control device failure is detected, the generating end of the first vehicle control command (such as the intelligent driving chip 2) can also directly send the first vehicle control command to the actuator corresponding to the vehicle without going through the control device, which is conducive to improving communication efficiency.

[0203] Implementation Figure 4 In an embodiment, under normal circumstances, the first intelligent driving system can use the full computing power of multiple intelligent driving chips to perform calculations, thereby improving the utilization rate of the system computing power. In addition, during the normal operation of the first intelligent driving system (i.e., multiple intelligent driving chips are all fault-free), these multiple intelligent driving chips can not only provide the control device with the current vehicle control command, but also provide the control device with predicted vehicle control information. The predicted vehicle control information includes the sequence of control commands to be executed in the future. In this way, when the control device detects that a fault in the intelligent driving chip has caused the first intelligent driving system to be unable to continue operating, it can perform safe vehicle control based on the predicted vehicle control information, which is conducive to improving vehicle safety.

[0204] When executing vehicle control based on the predicted vehicle control information, the control device can also instruct at least one intelligent driving chip (e.g., intelligent driving chip 2) to activate the second intelligent driving system. The predicted vehicle control information provides sufficient time for the activation of the second intelligent driving system. During the activation of the second intelligent driving system, the control device controls the vehicle, thereby improving vehicle safety. Only after the second intelligent driving system is activated does the control device switch to intelligent driving chip 2 to execute vehicle control.

[0205] In some possible embodiments, the activation of the second intelligent driving system may also be autonomous activation of the intelligent driving chip, rather than the above-mentioned Figure 4 The embodiment shown is based on the instruction information from the control device to start. Figure 5 Description of embodiments.

[0206] See also Figure 5 , Figure 5 This is a flow chart of another vehicle control method provided by the embodiment of the present application. This method can be applied to Figure 1 The vehicle control system of the vehicle shown is specifically applied between the control device and multiple intelligent driving chips. Figure 4 Example, in Figure 5 In the embodiment, the number of the multiple intelligent driving chips is two, that is, the multiple intelligent driving chips include intelligent driving chip 1 and intelligent driving chip 2.

[0207] Figure 5 The method shown in the embodiment includes but is not limited to the following steps S501-S507, wherein S501 is the same as S401, S502 is the same as S402, S505 is the same as S405, S506 is the same as S406, and S507 is the same as S407. For the sake of brevity, they are not described here in detail. The following mainly describes S503 and S504.

[0208] S503: When a fault in the intelligent driving chip 1 is detected, the intelligent driving chip 2 starts the second intelligent driving system and sends a notification message to the control device.

[0209] Among them, the notification information is used to indicate that the intelligent driving chip 1 has failed and / or the control device has executed vehicle control.

[0210] For example, the two operations of the intelligent driving chip 2 starting the second intelligent driving system and sending notification information to the control device can be performed simultaneously. In some schemes, the intelligent driving chip 2 can also first send the notification information to the control device and then start the second intelligent driving system.

[0211] For example, the intelligent driving chip 2 can determine whether the intelligent driving chip 1 has failed by monitoring at least one of the following information: the power supply voltage, operating temperature, and information stored in the status register (which stores the operating status information of the intelligent driving chip 1). When the control device detects that the intelligent driving chip 1 meets any of the following conditions, it determines that the intelligent driving chip 1 has failed:

[0212] The power supply voltage is not within the normal operating range;

[0213] The operating temperature is greater than the upper temperature limit; or,

[0214] The status register stores information including fault signals.

[0215] In some schemes, the intelligent driving chip 2 detects a fault in the intelligent driving chip 1, including: the intelligent driving chip 2 receives an alarm message or a fault code from the intelligent driving chip 1, and the alarm message or fault code is used to indicate a fault in the intelligent driving chip 1; the intelligent driving chip 2 determines that the intelligent driving chip 1 has a fault based on the received alarm message or fault code.

[0216] In some solutions, intelligent driving chip 2 and intelligent driving chip 1 may also agree to monitor each other for faults using a watchdog timer. In this case, intelligent driving chip 2 detects a fault in intelligent driving chip 1 by: If intelligent driving chip 2 does not receive a response from intelligent driving chip 1 within the agreed time, then intelligent driving chip 2 determines that intelligent driving chip 1 has failed.

[0217] S504: In response to the notification information, the control device performs vehicle control according to the predicted vehicle control information.

[0218] Here, the control device performs the vehicle control process according to the predicted vehicle control information. Please refer to the above Figure 4 For the sake of brevity, the description of the corresponding contents in Example S403 will not be repeated here.

[0219] Implementation Figure 5 In this embodiment, multiple intelligent driving chips jointly implement a first intelligent driving system. During normal operation of the first intelligent driving system (i.e., all multiple intelligent driving chips are fault-free), at least one of the multiple intelligent driving chips can send current vehicle control commands and predicted vehicle control information to a control device in real time. The first intelligent driving system fully utilizes the computing power of the multiple intelligent driving chips, improving system computing power utilization.

[0220] When a normal intelligent driving chip detects that other intelligent driving chips have faults, the normal intelligent driving chip can actively start the second intelligent driving system stored locally, and send a notification message to the vehicle's control device to simultaneously inform it that there is a fault in the intelligent driving chip, so that the control device can execute vehicle control according to the predicted vehicle control information received in advance during the startup of the second intelligent driving system, thereby ensuring the safety of the vehicle during the startup of the second intelligent driving system.

[0221] In some possible embodiments, if the computing power of the control device is sufficient, the second intelligent driving system may not be deployed on the above multiple intelligent driving chips. For the vehicle control method, please refer to the following Figure 6 shown. Figure 6 This is a flow chart of another vehicle control method provided by the embodiment of the present application. This method can be applied to Figure 1 The vehicle control system of the vehicle shown is specifically applied between the control device and multiple intelligent driving chips, and the multiple intelligent driving chips include at least intelligent driving chip 1 and intelligent driving chip 2.

[0222] Figure 6The method shown in the embodiment includes but is not limited to the following steps S601-S604, wherein S601 is the same as S401, and S602 is the same as S402. For the sake of brevity, they are not described here. The following mainly describes S603 and S604.

[0223] S603: In the event of a fault in the intelligent driving chip, at least one of the multiple intelligent driving chips sends monitoring perception data of the current environment to the control device.

[0224] Here, the at least one intelligent driving chip mentioned above does not include a faulty intelligent driving chip.

[0225] The monitoring perception data of the current environment is the driving environment information of the road where the vehicle is located, collected by the vehicle's sensors within the detection capability range. The driving environment information includes multiple items of the following information: weather, visibility, light intensity, road type, number of lanes, road flatness, road smoothness, road construction conditions, and obstacles on the road (including static obstacles and dynamic obstacles that affect vehicle driving, etc.).

[0226] For example, an intelligent driving chip among multiple intelligent driving chips that is deployed with a perception module of the first intelligent driving system can send monitoring perception data of the current environment to the control device. Alternatively, an intelligent driving chip among multiple intelligent driving chips that is connected to the vehicle's sensors can also send monitoring perception data of the current environment to the control device. In some solutions, when the above-mentioned monitoring perception data comes from multiple intelligent driving chips other than the faulty intelligent driving chip, these multiple intelligent driving chips can also provide some or all of the above-mentioned monitoring perception data.

[0227] Here, the fault detection of the intelligent driving chip can be performed by the control device or by the intelligent driving chip.

[0228] For example, the fault detection of the intelligent driving chip is performed by the control device. Assuming that the control device detects a fault in the intelligent driving chip 1, in this case, the control device sends a fault prompt information to at least one of the multiple intelligent driving chips, and the fault prompt information is used to indicate a fault in the intelligent driving chip 1. At least one of the multiple intelligent driving chips sends monitoring perception data of the current environment to the control device, which means that in response to the fault prompt information, at least one of the multiple intelligent driving chips sends monitoring perception data of the current environment to the control device. Here, please refer to the aforementioned fault detection method. Figure 4 The description of the corresponding content in Example S403 will not be repeated here.

[0229] For another example, the fault detection of the intelligent driving chip is performed by the intelligent driving chip. Assuming that at least one of the multiple intelligent driving chips detects a fault in the intelligent driving chip 1, please refer to the aforementioned fault detection method. Figure 5The description of the corresponding content in Example S503 will not be repeated here.

[0230] S604: The control device performs vehicle control according to the predicted vehicle control information and the monitoring perception data of the current environment.

[0231] In one implementation, a control device performs vehicle control based on predicted vehicle control information and monitoring perception data of a current environment, including: when the control device detects that a target event has occurred in the current environment based on the monitoring perception data of the current environment, the control device updates the predicted vehicle control information based on the monitoring perception data of the current environment to obtain updated predicted vehicle control information; and the control device performs vehicle control based on the updated predicted vehicle control information. The target event may be any of the following events:

[0232] The vehicle ahead suddenly slows down;

[0233] An object (such as a cardboard box, a branch, etc.) falls from a vehicle carrying goods in front of you; or

[0234] A vehicle suddenly cuts into your lane.

[0235] For example, compared with the predicted vehicle control information before the update, at least one of the following contents in the updated predicted vehicle control information has changed: the vehicle control command, the execution time of the vehicle control command, and the predicted time range.

[0236] It is understandable that as the vehicle is driving, an obstacle may suddenly appear in front of the vehicle (such as another vehicle, an animal, or a fallen tire, cardboard box, branch, etc.). The control device can perceive this change in time by obtaining monitoring perception data of the current environment, so that it can make correct vehicle control decisions.

[0237] Exemplarily, the control device executes vehicle control based on the updated predicted vehicle control information, including: the control device controls the vehicle to pull over or park in its own lane based on the updated predicted vehicle control information. This ensures safe parking of the vehicle and prevents the intelligent driving system from causing loss of control due to a malfunction of the intelligent driving chip.

[0238] Implementation Figure 6 In this embodiment, multiple intelligent driving chips jointly implement the intelligent driving system. During the normal operation of the intelligent driving system (i.e., all multiple intelligent driving chips are fault-free), they can send current control commands and predicted vehicle control information to the control device, fully utilizing the computing power of multiple intelligent driving chips and improving the utilization rate of the system computing power. In addition, when an intelligent driving chip fails, the control device can also obtain monitoring and perception data of the current environment from other normal intelligent driving chips, and combine this monitoring and perception data with the predicted vehicle control information to execute vehicle control, thereby improving the accuracy of vehicle control and enhancing vehicle safety.

[0239] See also Figure 7 , Figure 7 3 is a schematic diagram of the structure of a computing device provided in an embodiment of the present application. The computing device 30 includes a receiving unit 310, a processing unit 312, and a sending unit 314. In some embodiments, the receiving unit 310 and the sending unit 314 may also be collectively referred to as a communication unit. The computing device 30 may be implemented using hardware, software, or a combination of hardware and software.

[0240] In one implementation, the computing device 30 may be the control device of the above-mentioned vehicle or included in the control device. Among them, the receiving unit 310 is used to receive the first vehicle control command and the predicted vehicle control information; the sending unit 314 is used to send the first vehicle control command to the actuator corresponding to the vehicle. Here, the first vehicle control command is the vehicle control command at the current moment, and the predicted vehicle control information is used to indicate the vehicle control command to be executed on the vehicle within the predicted time range. The first vehicle control command and the predicted vehicle control information come from at least one of the multiple intelligent driving chips of the vehicle, and these multiple intelligent driving chips share the calculations required for the first intelligent driving system. In addition, the processing unit 312 is used to execute vehicle control according to the predicted vehicle control information during the process of starting the second intelligent driving system with other intelligent driving chips (such as the above-mentioned intelligent driving chip 2). The start-up of the second intelligent driving system is triggered by a failure of one of the above-mentioned multiple intelligent driving chips.

[0241] In this case, the computing device 30 may be used to implement Figure 4 The method of controlling the device side described in the embodiment. Figure 4 In an embodiment, the receiving unit 310 may be used to execute S401 and S405 , the processing unit 312 and the sending unit 314 may jointly execute S402 and S403 , and the processing unit 312 may also be used to execute S406 .

[0242] In some aspects, computing device 30 may be used to implement Figure 5 The method of controlling the device side described in the embodiment. Figure 5 In an embodiment, the receiving unit 310 may be used to execute S501, S503 and S505, the processing unit 312 and the sending unit 314 may jointly execute S502, and the processing unit 312 may also execute S504 and S506. In some embodiments, the computing device 30 is used to implement Figure 6 For the sake of brevity, the method on the control device side described in the embodiment will not be repeated here.

[0243] In another implementation, the computing device 30 may be a target intelligent driving chip or included in a target intelligent driving chip, and the target intelligent driving chip belongs to a plurality of intelligent driving chips of the vehicle, and these plurality of intelligent driving chips jointly share the calculations required by the first intelligent driving system, and these plurality of intelligent driving chips also include the first intelligent driving chip. Among them, the processing unit 312 is used to start the second intelligent driving system in the event of a failure of the first intelligent driving chip, wherein the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system. Exemplarily, the receiving unit 310 is used to receive indication information from the control device of the vehicle when the first intelligent driving chip fails, and the indication information is used to instruct the start of the second intelligent driving system; or, when the processing unit 312 detects a failure of the first intelligent driving chip, the sending unit 314 is used to send notification information to the control device, and the notification information is used to instruct the control device to control the vehicle and / or the first intelligent driving chip fails.

[0244] As an example, the computing device 30 may be used to implement Figure 4 The method of the intelligent driving chip side (such as other intelligent driving chips) described in the embodiment. Figure 4 In the embodiment, the sending unit 314 can be used to execute S401 and S405, the processing unit 312 can be used to execute S404 and S407, and the receiving unit 310 can be used to execute S403. Here, the first intelligent driving chip is equivalent to the aforementioned Figure 4 The smart driving chip 1 in the embodiment is equivalent to the target smart driving chip Figure 4 Other intelligent driving chips in the embodiment may be, for example, the intelligent driving chip 2.

[0245] As another example, computing device 30 may be used to implement Figure 5 The method of the intelligent driving chip side (such as the intelligent driving chip 2) described in the embodiment. Figure 5 In an embodiment, the sending unit 314 may be used to execute S501 and S505, the processing unit 312 and the sending unit 314 may jointly execute S503, and the processing unit 312 may also be used to execute S507. In some embodiments, the computing device 30 may be used to implement Figure 6 For the sake of brevity, the method on the intelligent driving chip side described in the embodiment will not be repeated here.

[0246] It should be understood that the division of the various units in the computing device 30 described above is merely a division of logical functions. In actual implementation, they may be fully or partially integrated into a single physical entity, or they may be physically separated. Furthermore, the units in the device may be implemented in the form of a processor calling software; for example, the device may include a processor connected to a memory storing instructions, and the processor calling the instructions stored in the memory to implement any of the above methods or functions of the various units of the device, wherein the processor may be, for example, a general-purpose processor such as a central processing unit (CPU) or a microprocessor, and the memory may be a memory within the device or a memory external to the device. Alternatively, the units in the device can be implemented in the form of hardware circuits, and the functions of some or all of the units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units by designing the logical relationship of the components in the circuit. For another example, in another implementation, the hardware circuit can be implemented by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units. All units of the above devices can be implemented in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0247] In an embodiment of the present application, a processor is a circuit with a signal processing capability. In one implementation, the processor can be a circuit with instruction reading and execution capability, such as a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationship of a hardware circuit. The logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by a processor as an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the processor loads a configuration document to implement the process of hardware circuit configuration, which can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc.

[0248] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0249] In addition, the various units in the above devices can be fully or partially integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a system-on-a-chip (SOC). The SOC may include at least one processor for implementing any of the above methods or implementing the functions of the various units of the device. The type of the at least one processor can be different, for example, including a CPU and FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0250] See also Figure 8 , Figure 8 This is a schematic diagram of the structure of a computing device provided in an embodiment of the present application. Figure 8As shown, computing device 40 includes: processor 401, communication interface 402, memory 403 and bus 404. Processor 401, memory 403 and communication interface 402 communicate with each other via bus 404. It should be understood that this application does not limit the number of processors and memories in computing device 40.

[0251] In one implementation, the computing device 40 may be the aforementioned intelligent driving chip. For example, the intelligent driving chip may be a system-on-chip (SOC), an artificial intelligence acceleration chip, or a component within the chip, such as an integrated circuit or a processor.

[0252] In another implementation, the computing device 40 may be the aforementioned control device, such as an MCU or a component within the MCU.

[0253] The bus 404 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 8 The bus 404 may include a path for transmitting information between various components of the computing device 40 (eg, the memory 403, the processor 401, and the communication interface 402).

[0254] The processor 401 can refer to the relevant description of the processor in the above embodiment, which will not be repeated here.

[0255] Memory 403 is used to provide storage space for data such as the operating system and computer programs. Memory 403 can be one or a combination of random access memory (RAM), erasable programmable read-only memory (EPROM), read-only memory (ROM), or compact disc read-only memory (CD-ROM). Memory 403 can exist independently or be integrated into processor 401.

[0256] The communication interface 402 can be used to provide information input or output for the processor 401. Alternatively, the communication interface 402 can be used to receive data transmitted externally and / or transmit data externally. It can be a wired link interface such as an Ethernet cable, or a wireless link interface (such as Wi-Fi, Bluetooth, general wireless transmission, etc.). Alternatively, the communication interface 402 can also include a transmitter (such as a radio frequency transmitter, antenna, etc.) or a receiver coupled to the interface.

[0257] The processor 401 in the computing device 40 is used to read the computer program stored in the memory 403 to execute the aforementioned method, for example Figure 4 、 Figure 5 or Figure 6 The method described.

[0258] In one possible design, the computing device 40 may be a processor for executing Figure 4 One or more modules in the execution subject (e.g., control device) of the method shown, the processor 401 can be used to read one or more computer programs stored in the memory to perform the following operations:

[0259] Receiving the first vehicle control command and the predicted vehicle control information through the receiving unit 310;

[0260] The first vehicle control command is sent to the actuator corresponding to the vehicle via the sending unit 314. The first vehicle control command is the current vehicle control command, and the predicted vehicle control information indicates the vehicle control command that will be executed on the vehicle within a predicted time range. The first vehicle control command and the predicted vehicle control information are generated by at least one of the vehicle's multiple intelligent driving chips. These multiple intelligent driving chips jointly share the computation required by the first intelligent driving system.

[0261] In one possible design, the computing device 40 may be a processor for executing Figure 4 One or more modules in the execution body of the method shown (such as other intelligent driving chips), the processor 401 can be used to read one or more computer programs stored in the memory to perform the following operations:

[0262] In the event that one of the multiple intelligent driving chips fails, a second intelligent driving system is started, wherein these multiple intelligent driving chips jointly share the calculations required by the first intelligent driving system, and the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

[0263] In the embodiments described above, the descriptions of each embodiment have their own emphasis. For parts not described in detail in a particular embodiment, please refer to the relevant descriptions of other embodiments. In addition, in the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between the various embodiments are consistent and can be referenced to each other. The technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0264] It should be noted that, those skilled in the art can see that all or part of the steps in the various methods of the above embodiments can be completed by a program to instruct relevant hardware. The program can be stored in a computer-readable storage medium, and the storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0265] The technical solution of the present application may essentially or contribute to the part or all or part of the technical solution in the form of a software product. The computer program product is stored in a storage medium and includes a number of instructions for enabling a device (which may be a personal computer, a server, or a network device, a robot, a single-chip microcomputer, a chip, a robot, etc.) to execute all or part of the steps of the method described in each embodiment of the present application.

Claims

1. A vehicle control method, characterized in that: The method is applied to a control device of the vehicle, wherein the vehicle further includes a plurality of intelligent driving chips, and the plurality of intelligent driving chips jointly share calculations required by the first intelligent driving system. The method includes: receiving a first vehicle control command and predicted vehicle control information, wherein the first vehicle control command is a vehicle control command at a current moment, the predicted vehicle control information is used to indicate a vehicle control command to be executed on the vehicle within a predicted time range, and the first vehicle control command and the predicted vehicle control information are from at least one intelligent driving chip among the multiple intelligent driving chips; The first vehicle control command is sent to the corresponding actuator in the vehicle.

2. The method according to claim 1, characterized in that The multiple intelligent driving chips include a first intelligent driving chip and other intelligent driving chips, and the method further includes: When a failure of the first intelligent driving chip is detected, vehicle control is performed based on the predicted vehicle control information, and instruction information is sent to the other intelligent driving chips, where the instruction information is used to instruct the startup of a second intelligent driving system, wherein the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

3. The method according to claim 2, characterized in that The predicted vehicle control information is the most recently received information in history before the control device detects a failure in the first intelligent driving chip, and the second intelligent driving system completes startup within the predicted time range.

4. The method according to claim 2 or 3, characterized in that The first intelligent driving system is deployed on the multiple intelligent driving chips, and the second intelligent driving system is deployed on at least one intelligent driving chip among the multiple intelligent driving chips.

5. The method according to any one of claims 2 to 4, characterized in that: The method further comprises: receiving feedback information from the other intelligent driving chip, where the feedback information is used to indicate that the second intelligent driving system has completed startup; In response to the feedback information, the vehicle control performed by using the predicted vehicle control information is stopped.

6. The method according to claim 5, characterized in that The method further comprises: Receiving a second vehicle control command from the other intelligent driving chip; The second vehicle control command is sent to the corresponding actuator in the vehicle.

7. The method according to claim 1, characterized in that The multiple intelligent driving chips include a first intelligent driving chip and other intelligent driving chips, and the method further includes: When a fault is detected in the first intelligent driving chip, obtaining monitoring and perception data of the current environment from the other intelligent driving chips; The vehicle control is performed according to the predicted vehicle control information and the monitoring perception data.

8. The method according to claim 7, characterized in that The executing vehicle control according to the predicted vehicle control information and the monitoring perception data includes: The vehicle is controlled to park on the side of the road or in its own lane according to the predicted vehicle control information and the monitoring perception data.

9. The method according to any one of claims 1 to 8, characterized in that The multiple intelligent driving chips are all system-on-chip (SOC), and the control device is a microcontroller unit (MCU).

10. A vehicle control method, characterized in that: The method is applied to a target intelligent driving chip, where the target intelligent driving chip belongs to multiple intelligent driving chips of the vehicle, the multiple intelligent driving chips also include a first intelligent driving chip, and the multiple intelligent driving chips jointly share calculations required by the first intelligent driving system. The method includes: In the event of a failure of the first intelligent driving chip, starting the second intelligent driving system; Among them, the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

11. The method according to claim 10, characterized in that The first intelligent driving system is deployed on the multiple intelligent driving chips, and the second intelligent driving system is deployed on at least one intelligent driving chip among the multiple intelligent driving chips, and the at least one intelligent driving chip includes the target intelligent driving chip.

12. The method according to claim 10 or 11, characterized in that The method further comprises: In the event that the first intelligent driving chip fails, receiving instruction information from the control device of the vehicle, the instruction information being used to instruct to activate the second intelligent driving system; The starting the second intelligent driving system includes: starting the second intelligent driving system in response to the indication information.

13. The method according to claim 10 or 11, characterized in that The number of the plurality of intelligent driving chips is two, and in the event that the first intelligent driving chip fails, starting the second intelligent driving system includes: When a failure of the first intelligent driving chip is detected, the second intelligent driving system is started, and a notification message is sent to the control device of the vehicle, wherein the notification message is used to instruct the control device to control the vehicle and / or the first intelligent driving chip to fail.

14. The method according to claim 12 or 13, characterized in that The method further comprises: After the second intelligent driving system is started, feedback information is sent to the control device, where the feedback information is used to indicate that the second intelligent driving system is started.

15. The method according to any one of claims 12 to 14, characterized in that: The method further comprises: After the second intelligent driving system is started, the vehicle is controlled to perform pull-over parking or self-lane parking.

16. The method according to claim 15, characterized in that After controlling the vehicle to perform pull-over parking or lane parking, the method further includes: In response to the start command, the vehicle is controlled to travel.

17. The method according to any one of claims 12 to 16, characterized in that: When the multiple intelligent driving chips are not faulty, the method further includes: Determining a first vehicle control command and / or predicted vehicle control information based on the processing result; wherein the processing result includes calculation results of some or all of the multiple intelligent driving chips, the processing result is associated with the first intelligent driving system, the first vehicle control command is the vehicle control command at the current moment, and the predicted vehicle control information is used to indicate the vehicle control command to be executed on the vehicle within a predicted time range; Sending the first vehicle control command and / or the predicted vehicle control information.

18. The method according to claim 17, characterized in that Sending the first vehicle control command and / or the predicted vehicle control information includes: When the control device has no faults, the first vehicle control command and / or the predicted vehicle control information is sent to the control device.

19. The method according to claim 17, wherein Sending the first vehicle control command and / or the predicted vehicle control information includes: In the event of a failure of the control device, the first vehicle control command is sent to a corresponding actuator in the vehicle.

20. The method according to any one of claims 12 to 19, characterized in that: The multiple intelligent driving chips are all system-on-chip (SOC), and the control device is a microcontroller unit (MCU).

21. A device for vehicle control, characterized in that: The device comprises a communication unit and a processing unit, and is configured to execute the method according to any one of claims 1 to 9.

22. A device for vehicle control, characterized in that: The device is a target intelligent driving chip or is included in the target intelligent driving chip. The target intelligent driving chip belongs to multiple intelligent driving chips of the vehicle. The multiple intelligent driving chips also include a first intelligent driving chip. The multiple intelligent driving chips jointly share the calculation required by the first intelligent driving system. The device includes: a processing unit, configured to activate a second intelligent driving system in the event that the first intelligent driving chip fails; Among them, the computing power required for the operation of the second intelligent driving system is less than the computing power required for the operation of the first intelligent driving system.

23. The device according to claim 22, characterized in that The first intelligent driving system is deployed on the multiple intelligent driving chips, and the second intelligent driving system is deployed on at least one intelligent driving chip among the multiple intelligent driving chips, and the at least one intelligent driving chip includes the target intelligent driving chip.

24. The device according to claim 22 or 23, characterized in that The device further comprises: a receiving unit, configured to receive instruction information from a control device of the vehicle when the first intelligent driving chip fails, the instruction information being used to instruct activation of the second intelligent driving system; The processing unit is specifically used to: start the second intelligent driving system in response to the indication information.

25. The device according to claim 22 or 23, characterized in that The number of the multiple intelligent driving chips is two, and the processing unit is specifically used to: When the processing unit detects a fault in the first intelligent driving chip, starting the second intelligent driving system; The device also includes a sending unit, which is used to send notification information to the control device of the vehicle, wherein the notification information is used to indicate that the control device controls the vehicle and / or the first intelligent driving chip fails.

26. The device according to claim 24 or 25, characterized in that The sending unit of the device is also used to send feedback information to the control device after the second intelligent driving system is started up, and the feedback information is used to indicate that the startup of the second intelligent driving system is completed.

27. The device according to any one of claims 24 to 26, characterized in that The processing unit is further configured to: After the second intelligent driving system is started, the vehicle is controlled to perform pull-over parking or self-lane parking.

28. The device according to claim 27, characterized in that The processing unit is further configured to: After controlling the vehicle to perform pull-over parking or self-lane parking, in response to a start instruction, controlling the vehicle to travel.

29. The device according to any one of claims 24 to 28, characterized in that When the multiple intelligent driving chips are not faulty, the processing unit is further configured to determine a first vehicle control command and / or predicted vehicle control information based on a processing result; wherein the processing result includes calculation results of some or all of the multiple intelligent driving chips, the processing result is associated with the first intelligent driving system, the first vehicle control command is a vehicle control command at the current moment, and the predicted vehicle control information is used to indicate a vehicle control command to be executed on the vehicle within a predicted time range; The sending unit of the device is further configured to send the first vehicle control command and / or the predicted vehicle control information.

30. The device according to claim 29, characterized in that The sending unit is specifically configured to: When the control device has no faults, the first vehicle control command and / or the predicted vehicle control information is sent to the control device.

31. The device according to claim 29, characterized in that The sending unit is specifically configured to: In the event of a failure of the control device, the first vehicle control command is sent to a corresponding actuator in the vehicle.

32. The device according to any one of claims 24 to 31, characterized in that The multiple intelligent driving chips are all system-on-chip (SOC), and the control device is a microcontroller unit (MCU).

33. A chip for vehicle control, characterized in that: The chip includes a memory and a processor, the memory stores computer program instructions, and the processor runs the computer program instructions to enable the chip to execute the method according to any one of claims 1 to 9, or implement the method according to any one of claims 10 to 20.

34. A vehicle control system, characterized in that: The vehicle control system includes multiple intelligent driving chips and a control device, wherein the control device is used to execute the method described in any one of claims 1 to 9, and the intelligent driving chip is used to execute the method described in any one of claims 10 to 20.

35. A vehicle, characterized in that: The vehicle includes the device according to claim 21 and / or the device according to any one of claims 22 to 32, or includes the chip according to claim 33, or includes the vehicle control system according to claim 34.

36. A computer-readable storage medium containing program instructions, characterized in that: When the program instructions are executed by a processor, the method according to any one of claims 1 to 9 is implemented, or the method according to any one of claims 10 to 20 is executed.

37. A computer program product comprising instructions, characterized in that When the instructions are executed by a computing device, the computing device implements the method according to any one of claims 1 to 9, or implements the method according to any one of claims 10 to 20.

Images