CN117785476A - Vehicle-mounted resource optimization method, device, equipment and storage medium - Google Patents
Vehicle-mounted resource optimization method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117785476A CN117785476A CN202410059575.4A CN202410059575A CN117785476A CN 117785476 A CN117785476 A CN 117785476A CN 202410059575 A CN202410059575 A CN 202410059575A CN 117785476 A CN117785476 A CN 117785476A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- module
- mounted application
- resources
- important
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000005457 optimization Methods 0.000 title claims abstract description 45
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000009467 reduction Effects 0.000 claims abstract description 21
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 230000015654 memory Effects 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 15
- 230000008859 change Effects 0.000 claims description 14
- 230000005540 biological transmission Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000000694 effects Effects 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 230000007423 decrease Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000008447 perception Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 5
- 230000006399 behavior Effects 0.000 description 3
- 230000015556 catabolic process Effects 0.000 description 3
- 238000006731 degradation reaction Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000000593 degrading effect Effects 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000011076 safety test Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of intelligent driving, and discloses a vehicle-mounted resource optimization method, device, equipment and storage medium, wherein the method comprises the following steps: dividing a vehicle-mounted application module in a vehicle into a plurality of important levels according to the importance level of operation; monitoring the real-time state of critical resources of the system; and according to the reduction condition of the available resources of the critical resources of the real-time state analysis system, and according to the reduction condition of the available resources, optimizing each vehicle-mounted application module according to the order from least importance to most importance of importance levels. The invention solves the problem of low degree of both vehicle-mounted resource optimization and vehicle safety running.
Description
Technical Field
The invention relates to the technical field of intelligent driving, in particular to a vehicle-mounted resource optimization method, device, equipment and storage medium.
Background
With the continuous perfection of the automatic driving technology, the automatic driving technology provides higher requirements on the performance of the computer, but the performance of the vehicle-mounted computer is limited by space, heat dissipation and power consumption, so that the requirements of the vehicle-mounted system on the performance of the computer cannot be met, and the challenge is provided for software and hardware resources of the vehicle-mounted system.
Although the existing optimization scheme can select to close some vehicle-mounted application programs when the hardware resources of the computer are insufficient, the blind closing of the application programs can have serious influence on the safe driving of the vehicle, so that the existing resource optimization scheme needs to be improved.
Disclosure of Invention
In view of the above, the invention provides a vehicle-mounted resource optimization method, a device, equipment and a storage medium, so as to solve the problem that the vehicle-mounted resource optimization and the vehicle safety driving function have low compatibility.
In a first aspect, the present invention provides a vehicle-mounted resource optimization method, which includes: dividing a vehicle-mounted application module in a vehicle into a plurality of important levels according to the importance level of operation; monitoring the real-time state of critical resources of the system; and analyzing the reduction condition of the available resources of the critical resources of the system according to the real-time state, and optimizing each vehicle-mounted application module according to the reduction condition of the available resources and the order from least important to most important of importance levels.
In an alternative embodiment, the dividing the on-board application module in the vehicle into a plurality of importance levels according to the importance level of the operation includes: according to different performance modes, under different automatic driving task scenes, vehicle-mounted application modules for normal and safe execution of tasks are divided into important module sets, vehicle-mounted application modules for optimizing task effects are divided into extension module sets, and useless vehicle-mounted application modules under the current scene are divided into irrelevant module sets.
In an optional implementation manner, the analyzing the reduction condition of the available resources of the critical resources of the system according to the real-time state, and optimizing each vehicle-mounted application module according to the reduction condition of the available resources according to the order from least important to most important of importance levels, includes: when the real-time state indicates that the available resources of the critical resources of the system are insufficient, enabling the vehicle-mounted application modules in the important module set to continue to run; the performance of the vehicle-mounted application module in the expansion module set is adjusted to be gradually reduced; and stopping running the vehicle-mounted application modules in the irrelevant module set.
In an alternative embodiment, the vehicle-mounted application modules in the expansion module set are given priority from high to low according to the importance degree from small to large, and the adjusting the performance of the vehicle-mounted application modules in the expansion module set gradually decreases includes: sequentially optimizing the performance of each vehicle-mounted application module in the expansion module set according to the order of the priority from high to low until the real-time state indicates that the available resources of the critical resources of the system reach a preset sufficient state; and when all the vehicle-mounted application modules in the expansion module set are optimized, the real-time state indicates that the available resources of the critical resources of the system are still insufficient, and each vehicle-mounted application module in the expansion module set is sequentially stopped according to the order of the priority from high to low until the real-time state indicates that the available resources of the critical resources of the system reach a preset sufficient state.
In an optional implementation manner, the optimizing the performance of each vehicle-mounted application module in the expansion module set sequentially according to the order of priority from high to low includes: adjusting the working frequency of a target vehicle-mounted application module; and/or compressing input and output data of the target vehicle-mounted application module and/or changing a parallel data transmission mode of the target vehicle-mounted application module into serial data transmission; and/or adjusting the calculation precision of the target vehicle-mounted application module.
In an alternative embodiment, the system critical resource is a central processing unit, and the monitoring the real-time status of the system critical resource includes: monitoring the average load rate, the average waiting task number and the running state information fed back by the central processing unit every second by a preset frequency, and calculating a comprehensive change curve of system resources according to the average load rate, the average waiting task number and the running state information fed back by the central processing unit; triggering optimization when the average value of the comprehensive change curve of the system resources exceeds a preset threshold value.
In an alternative embodiment, the method further comprises: when one vehicle-mounted application module in the expansion module set stops and the current automatic driving task cannot achieve the driving target, controlling the vehicle to enter an emergency parking state.
In a second aspect, the present invention provides an on-vehicle resource optimizing apparatus, the apparatus comprising: the application grade dividing unit is used for dividing a vehicle-mounted application module in the vehicle into a plurality of important grades according to the running importance degree; the state monitoring unit is used for monitoring the real-time state of the critical resources of the system; and the optimizing unit is used for analyzing the reduction condition of the available resources of the critical resources of the system according to the real-time state and optimizing each vehicle-mounted application module according to the reduction condition of the available resources from the least important to the most important order of the importance level.
In a third aspect, the present invention provides a computer device comprising: the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions to perform the method of the first aspect or any implementation manner corresponding to the first aspect.
In a fourth aspect, the present invention provides a computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of the first aspect or any of its corresponding embodiments.
The technical scheme provided by the invention has the following advantages:
according to the embodiment of the invention, the vehicle-mounted application modules in the vehicle are divided into a plurality of important grades according to the importance degree of operation, the real-time state of the critical resources of the system is monitored, if the available resources of the critical resources of the system are found to be reduced to be insufficient to support the basic driving function of the vehicle, the vehicle-mounted application modules are optimized according to the order from least important to most important of the importance grades, and the use of the critical resources of the system by the unimportant vehicle-mounted application modules is gradually reduced, so that the stability of the critical resources of the system is maintained under the condition of ensuring the optimal running state of the vehicle, the condition that the vehicle directly enters the emergency stop state and the like is avoided, and the influence of the optimization of the resources on the running state of the vehicle is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for optimizing vehicle resources according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a partitioning of an in-vehicle application module according to an embodiment of the present invention;
FIG. 3 is a block diagram of a software and hardware system of an unmanned forklift according to an embodiment of the present invention;
FIG. 4 is a flow diagram of an optimization strategy according to an embodiment of the invention;
FIG. 5 is a schematic diagram of a vehicle-mounted resource optimizing apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of a hardware structure of a computer device according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
According to an embodiment of the present invention, there is provided an on-vehicle resource optimization method embodiment, it should be noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowchart, in some cases, the steps illustrated or described may be performed in an order different from that herein.
In this embodiment, a vehicle-mounted resource optimization method is provided, which may be used for the above-mentioned computer device installed in an engineering vehicle, and fig. 1 is a flowchart of a vehicle-mounted resource optimization method according to an embodiment of the present invention, where the flowchart includes the following steps:
in step S101, the vehicle-mounted application module in the vehicle is classified into a plurality of importance levels according to the importance level of the operation.
Step S102, monitoring the real-time state of the critical resources of the system.
And step S103, analyzing the reduction condition of the available resources of the critical resources of the system according to the real-time state, and optimizing each vehicle-mounted application module according to the reduction condition of the available resources and the order from least important to most important of the importance levels.
Specifically, the complex operation scene and the high safety requirement in the automatic driving of the engineering vehicle lead to the engineering vehicle needing to put the safety factor of the vehicle at the first place, but the current vehicle-mounted resource optimization strategy often does not fully consider the safety driving factor of the vehicle, so that the problem that the driving cannot be operated safely when the vehicle-mounted resource is optimized is caused. For the above-mentioned situations, in the embodiment of the present invention, a plurality of importance levels are firstly divided according to the importance level of operation for the vehicle-mounted application module in the vehicle, for example, the more important the vehicle-mounted application module is, the higher the corresponding importance level is, which is only by way of example, but not by way of limitation. The most important vehicle-mounted application module is used for indicating that the engineering vehicle has to be used for safe driving, if the most important vehicle-mounted application module stops, the vehicle can be directly stopped and down, potential safety hazards appear, and the module with lower importance degree is more important to optimize driving effect on the basis of safe driving of the vehicle, such as optimizing the bumping degree of the vehicle, optimizing the swing amplitude of the vehicle and the like.
The system critical resource is a concept in the computer field, and refers to a resource which is shared by all processes in a software and hardware system and can only be used by limited processes at the same time, including but not limited to a CPU, a memory, a disk, a network bandwidth, and the like. The real-time status represents an index of the state of the critical resource of the system, including but not limited to the utilization rate, waiting time, software response time, etc., and may also include a combination, a sub-combination, a weighted average, a prediction estimation, an index obtained by algorithm processing, etc. of the above indexes as inputs.
Therefore, according to the real-time state of vehicle monitoring, judging the reduction condition of the available resources of the critical resources of the system, if the reduction condition of the available resources of the critical resources of the system is found to be insufficient to support the basic driving function of the vehicle, optimizing each vehicle-mounted application module according to the order from least important to most important of importance levels, and gradually reducing the use of the critical resources of the system by the non-important vehicle-mounted application modules, thereby maintaining the stability of the critical resources of the system under the condition of ensuring the safe driving state of the vehicle, avoiding the vehicle from directly entering the emergency stopping state and the like, and reducing the influence of the resource optimization on the driving state of the vehicle.
In some optional embodiments, the step S101 includes:
and a1, dividing the vehicle-mounted application modules for normal and safe execution of the tasks into important module sets, dividing the vehicle-mounted application modules for optimizing the task effect into extension module sets, and dividing useless vehicle-mounted application modules in the current scene into irrelevant module sets under different automatic driving task scenes according to different performance modes.
Specifically, the vehicle-mounted application modules are divided from two dimensions of different performance modes and different automatic driving task scenes, different vehicle-mounted application modules which are used under different automatic driving task scenes are fully considered, and the safety factor evaluation accuracy of safe driving of the vehicle can be further improved due to the fact that the vehicle has different energy consumption and requirements on the energy source in an energy saving mode, a balance mode and a high performance mode, and therefore certain modules are important modules or unimportant modules according to different energy source availability.
In addition, in the embodiment of the invention, the vehicle-mounted application modules are divided into the important module set, the extension module set and the irrelevant module set, so that the thought that the important module set stably operates, the extension module operates as much as possible and the irrelevant module stops operating can be realized, the irrelevant module is directly stopped, and the optimization is sequentially carried out from the extension module, and the optimization efficiency of the vehicle-mounted resources can be obviously improved.
In the embodiment of the invention, the important module set capable of ensuring the system safety is identified according to the behavior of the vehicle in the application scene, the combination can only ensure the safety and cannot ensure that the targets are certain to be achieved, and the module optimization priorities in the safety module set can be the same or can be adjusted according to the actual conditions of the safety test. Taking a tracking task as an example, vehicle behavior is that a vehicle is displaced horizontally and longitudinally, so that the vehicle is ensured to be controllable and the condition of the environment in the horizontal and longitudinal directions can be obtained, and important module sets comprise sensing (for sensing the input of the external condition around), positioning, vehicle control (comprising chassis driving and chassis control, wherein the chassis driving is used for controlling the input of the internal state and the instruction execution of the vehicle, and the chassis control is used for data processing of control signals) and basic planning. Taking the task of inserting and taking cargoes by an unmanned forklift as an example, the vehicle behavior comprises up-and-down displacement of a fork and longitudinal movement of the vehicle, so that the important module set comprises fork direction sensing, fork control and vehicle control.
In the embodiment of the invention, the expansion module set in the operation scene is determined according to the vehicle targets and various requirements in the application scene, and the vehicle-mounted application modules in the set also have optimized priority, and the priority is adjusted according to the principle of meeting the driving target and improving the efficiency. Taking a tracking task as an example, a vehicle target reaches a target point, so the extension module set comprises a navigation module, a track smooth planning module can be added for improving the smoothness of tracking, and a cloud communication module can be added for reporting the state. Taking a fork truck as an example, a truck is used for inserting goods, and a vehicle target is used for inserting goods, so that a goods detection module can be added to the expansion module set. Finally, the remaining modules outside the important module and the expansion module are irrelevant modules.
For example, in one specific embodiment, as shown in fig. 2, assuming that the engineering vehicle is an unmanned forklift, the vehicle-mounted application module in the engineering vehicle includes: the vehicle is controlled, perceived, positioned, planned, recorded, voice broadcast, operation control and operation detection, the performance modes of the vehicle are divided into an energy-saving mode and a high-performance mode, the vehicle running efficiency is prioritized in the high-performance mode, and the electric energy and fuel are saved in the energy-saving mode. Aiming at the tracking task, important modules in a high-performance mode comprise vehicle control, sensing, positioning and planning, so that the safety of the vehicle is ensured to track; the expansion module comprises video and voice broadcasting, is used for increasing real-time perception of a user on the tracking process on the premise that the vehicle completes a basic tracking task, improves driving efficiency and improves the completion degree of the tracking task, so that the modules are optimized in sequence when the vehicle-mounted resources are released; the irrelevant module comprises operation control and operation detection, namely, the tasks such as inserting and taking goods, detecting a goods tray and the like are not needed when the engineering vehicle executes the tracking task, so that the irrelevant module is directly closed, and the occupation of vehicle-mounted resources is reduced to the greatest extent. In the energy-saving mode, the important modules of the tracking task comprise vehicle control, perception, positioning and planning, the expansion module only plays a role in voice broadcasting, and the irrelevant modules are used for job control, job detection and video recording, so that the most electricity-consuming video recording function is preferably closed when the vehicle-mounted resources are optimized, and fuel is saved. Similarly, for example, the module division of the inserting task and the stacking task in the high performance mode and the energy saving mode respectively refer to fig. 2, and will not be described herein.
In some alternative embodiments, the step S103 includes:
step b1, when the real-time state indicates that the available resources of the critical resources of the system are insufficient, enabling the vehicle-mounted application modules in the important module set to continue to operate;
step b2, the performance of the vehicle-mounted application module in the expansion module set is gradually reduced;
and b3, stopping running the vehicle-mounted application modules in the irrelevant module set.
Specifically, in the embodiment of the present invention, based on the module dividing mechanism in the foregoing embodiment, the embodiment of the present invention releases more critical resources of the system according to the idea that the important module set operates stably, the expansion module operates as much as possible, and the irrelevant module stops operating. In this embodiment, even if the available resources of the critical resources of the system are insufficient, the vehicle-mounted application modules in the important module set are not stopped, so that the most basic safe driving is ensured, and in some special cases, the running performance parameters of the vehicle-mounted application modules in the important module set may be slightly reduced, so that the safe driving of the vehicle is ensured to the greatest extent. The vehicle-mounted application modules in the irrelevant module set directly stop running, so that more critical resources of the system are ensured to be released. For the vehicle-mounted application modules in the extension module set, the extension modules are not directly closed when being optimized, but the performance of the vehicle-mounted application modules in the extension module set is gradually reduced, so that the optimization effects of comfort, flexibility, target completion and the like of the automatic driving task of the vehicle can be maintained while the critical resources of the system are released, and the relation between safety and driving targets is considered. Specific operations for adjusting the performance of an in-vehicle application module in a collection of expansion modules include, but are not limited to: limiting the operating frequency of the expansion module, limiting the access frequency of the expansion module to the resource frequency and limiting the network bandwidth of the expansion module, and switching the expansion module to operate in a low-precision mode.
In some optional embodiments, the vehicle-mounted application modules in the extension module set are given priority from high to low according to the importance degree from small to large, and the step b2 includes:
step b21, sequentially optimizing the performance of each vehicle-mounted application module in the expansion module set according to the order of the priority from high to low until the real-time state indicates that the available resources of the critical resources of the system reach the preset sufficient state;
and b22, when the available resources of the critical resources of the system are still insufficient by the real-time state after the vehicle-mounted application modules in the expansion module set are completely optimized, stopping each vehicle-mounted application module in the expansion module set in sequence according to the priority from high to low until the available resources of the critical resources of the system are in a preset sufficient state by the real-time state.
Specifically, the optimization strategy provided by the embodiment of the invention refers to different service degradation strategies adopted by different modules in combination with the module level, the scene and the real-time state of system resources or a subset of the three, so that different service degradation modes are flexibly adopted for different modules and different conditions, and targeted optimization is completed.
In this embodiment, for the vehicle-mounted application modules in the extension module set, the performance of each vehicle-mounted application module in the extension module set is sequentially optimized according to the order of the priority of each vehicle-mounted application module from high to low, for example, the functions of the video and voice broadcasting modules are timely uploaded and optimized from 30 frames of data per record to 10 frames of data per record, and the data are stored once in batches for 3 times; the control module is used for reducing the frequency from 10hz operation to 1hz operation; the network bandwidth is reduced from 100MB to 50MB until the real-time state indicates that the available resources of the critical resources of the system reach a preset sufficient state, and the optimization of each vehicle-mounted application module in the expansion module set is stopped. If each vehicle-mounted application module in the expansion module set performs one-time performance reduction optimization, and the available resources of the critical resources of the system still do not reach a preset sufficient state, each vehicle-mounted application module in the expansion module set is closed in sequence, when the available resources of the critical resources of the system reach the preset sufficient state when the vehicle-mounted application module is closed to a target module, the closing is stopped. According to the scheme provided by the embodiment of the invention, on the premise of maintaining safe driving of the vehicle, the running time of each vehicle-mounted application module in the expansion module set is increased, the target completion degree is further improved, and the completion efficiency of the driving target is ensured.
In addition, in some optional embodiments, if the current automatic driving task cannot achieve the driving target because one vehicle-mounted application module in the extended module set stops, the vehicle is controlled to enter an emergency parking state, the working target is changed from completing the scene task to guaranteeing safety, and the system takes emergency measures, such as side parking, emergency parking, power failure and the like, so that the driving safety is primarily guaranteed, and the driving safety is improved.
In some alternative embodiments, step b21 above includes:
step c1, adjusting the working frequency of a target vehicle-mounted application module;
step c2, and/or compressing the input/output data of the target vehicle-mounted application module
Step c3, and/or changing the parallel data transmission mode of the target vehicle-mounted application module into serial data transmission;
and c4, and/or adjusting the calculation accuracy of the target vehicle-mounted application module.
Specifically, when the real-time state indicates that the available resources of the critical resources of the system are insufficient, the embodiment of the invention adopts a resource optimization strategy of changing the space in time, so that the working frequency of the target vehicle-mounted application module is adjusted, and the working frequency is adjusted from a larger working frequency to a smaller working frequency, for example, the control module is reduced from 10hz to 1 hz. The input and output data of the target vehicle-mounted application module can be compressed, so that the input and output data of the target vehicle-mounted application module occupy smaller storage space, the data are packaged and then transmitted, the data are not transmitted in real time, and the occupation of a CPU is reduced. The parallel data transmission mode of the target vehicle-mounted application module can be changed into serial data transmission, and occupation of a CPU channel is reduced by reducing the data transmission speed. The calculation precision of the target vehicle-mounted application module can be adjusted, so that low-precision calculation is performed when the target vehicle-mounted application module is automatically driven, and the calculation time of the CPU is reduced. Through the steps, the available resources of certain system critical resources are released, the corresponding functions are not closed, the time for reaching the driving target is prolonged, and meanwhile, the completion condition of the driving target and the optimization condition of the system critical resources are considered.
In some alternative embodiments, the system critical resource is a central processing unit, and step S102 includes:
step d1, monitoring the average load rate, the average waiting task number and the running state information fed back by the central processing unit every second of the central processing unit at a preset frequency, and calculating a comprehensive change curve of system resources according to the average load rate, the average waiting task number and the running state information fed back by the central processing unit;
and d2, triggering optimization when the average value of the comprehensive change curve of the system resources exceeds a preset threshold value.
Specifically, in the embodiment of the invention, the CPU is mainly used as a monitoring object of critical resources of the system, so that in order to determine whether available resources of the CPU are insufficient, the CPU is detected from multiple parameter angles, and the average load rate of the CPU per second, the average waiting task number and running state information fed back by the CPU, such as the remaining cache capacity of the CPU, the running queue of the CPU and the like, are periodically monitored by preset frequency. Then, the embodiment draws an index change curve for each index, so that the index change curves of each index are integrated into a comprehensive change curve of system resources in a mode of calculating an average value, a median value or a weighted average. Setting a preset threshold value for alarming the condition of insufficient temporary resources of the system, including, but not limited to, setting a single preset threshold value and a step-type threshold value, when the preset threshold value is the single threshold value, triggering optimization can directly reduce performance parameters related to the CPU to target setting parameters, such as working frequency and the like described in the previous embodiment; when the preset threshold is a step threshold, the average value of the comprehensive change curve of the system resources triggers the optimization once when exceeding the sub-threshold in one step threshold, and the trigger optimization does not directly reduce the performance parameters related to the CPU to the target setting parameters, but gradually reduces the performance parameters related to the CPU until the sub-threshold in the last step threshold is triggered. By means of the monitoring scheme of the system critical resources, which is provided by the embodiment of the invention, various system critical resource indexes are fused, and the accuracy of real-time state evaluation of the system critical resources is further improved.
In a specific application scenario embodiment, when the engineering vehicle is an unmanned forklift comprising an 8-core CPU, the vehicle-mounted resource optimization method provided by the invention comprises the following complete steps.
1. As shown in fig. 3, the system architecture diagram is a software and hardware system architecture diagram of the unmanned forklift, firstly, the unmanned forklift makes service decisions through a service decision module, and the vehicle-mounted application module is divided into three levels according to an important module, an expansion module and an irrelevant module. The divided task scenes comprise three tasks of tracking, inserting and picking and stacking, and the dividing is carried out according to the three task scenes in two modes of an energy-saving mode and a high-performance mode, wherein the dividing result is as follows:
in a high-performance mode, the important modules of the tracking task comprise four types of vehicle control, perception, positioning and planning, the expansion module comprises video recording and voice broadcasting, and the irrelevant module comprises operation control and operation detection; the important modules of the inserting task comprise four types of vehicle control, perception, operation detection and operation control, the expansion module comprises four types of positioning, planning, video recording and voice broadcasting, and no irrelevant module exists; the important modules of the stacking task comprise three types of sensing, operation detection and operation control, the expansion module comprises video recording and voice broadcasting, and the irrelevant module comprises control, positioning and planning.
In the energy-saving mode, the important modules of the tracking task comprise four types of vehicle control, perception, positioning and planning, the expansion module comprises voice broadcasting, and the irrelevant modules comprise video recording, operation control and operation detection; the important modules of the inserting task comprise four types of vehicle control, perception, operation detection and operation control, the expansion module comprises four types of positioning, planning and voice broadcasting, and the irrelevant module comprises video; the important modules of the stacking task comprise three types of sensing, operation detection and operation control, the expansion module comprises voice broadcasting, and the irrelevant modules comprise video recording, vehicle control, positioning and planning.
The business decision layer stores the classified module grades and the optimization strategies into the scene information module.
2. The unmanned forklift monitors the average load rate of the CPU per second, the average waiting task number of the CPU per 5 minutes and the running state information fed back by the working node per se through the resource monitoring module at the frequency of 1Hz, and generates a comprehensive change curve of system resources.
3. Intercepting on a comprehensive change curve of the system resources at intervals of 5 minutes, calculating the average value of each intercepting segment, and triggering system optimization when the average value exceeds a preset threshold value.
4. As shown in fig. 4, each module in the application layer is optimized by an optimization strategy in the optimization module in combination with the module level, the module type and the system resource, and in this embodiment, the optimization strategy is mainly optimized for 5 modules of vehicle control, perception, positioning, job control and video recording.
When the 5 modules belong to an important module or an expansion module before optimization, the running state is as follows: the vehicle control operates at 10Hz, senses to operate at 10Hz, positions to operate at 50Hz, the operation control operates at 50Hz, and the video records 30 frames each time and uploads the video to the cloud in real time;
when the 5 modules belong to the expansion module, the optimized running state is as follows:
the vehicle control operates at 1Hz standby, perceives to operate at 5Hz, positions to operate at 25Hz, the operation control operates at 1Hz standby, and the video records 10 frames of video each time and uploads the video to the cloud end in batches;
when the 5 modules belong to unrelated modules, the optimized running state is as follows:
and stopping the vehicle control, sensing and stopping, positioning to run at 10Hz, stopping the operation control, recording 0.5 frame of video each time, locally storing, and uploading to the cloud end when the critical resources of the system are sufficient.
The technical scheme provided by the invention mainly comprises the following advantages:
no additional hardware is required to be added, and no vehicle cost is required to be increased; the service capacity is transversely expanded, the modules are operated according to requirements under different scenes, and under the limited performance, the requirements of various tasks are met; the system capacity is longitudinally expanded, and under different system modes, the system capacity is operated through a control module, so that the requirements of the different system modes are met; the modules, task scenes and real-time states of system resources are combined, targeted degradation measures are adopted for the modules, the system resources of important modules are guaranteed, and the robustness and the safety of the self-driving system under different conditions such as high temperature, hardware faults and the like are improved; by degrading the non-key modules in the task scene, the operation efficiency of the key modules is improved.
The embodiment also provides a vehicle-mounted resource optimizing device, which is used for realizing the embodiment and the preferred implementation manner, and the description is omitted. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.
The present embodiment provides a vehicle-mounted resource optimizing apparatus, as shown in fig. 5, including:
an application level classification unit 501, configured to classify a vehicle-mounted application module in a vehicle into a plurality of importance levels according to an importance level of operation;
a state monitoring unit 502, configured to monitor a real-time state of a critical resource of the system;
and the optimizing unit 503 is configured to analyze the reduction condition of the available resources of the critical resources of the system according to the real-time status, and optimize each vehicle-mounted application module according to the reduction condition of the available resources according to the order from least importance to most importance of the importance level.
In some alternative embodiments, the application ranking unit 501 includes:
and the dividing sub-unit is used for dividing the vehicle-mounted application modules for normally and safely executing the task into important module sets, dividing the vehicle-mounted application modules for optimizing the task effect into extension module sets and dividing the useless vehicle-mounted application modules in the current scene into irrelevant module sets under different automatic driving task scenes according to different performance modes.
In some alternative embodiments, the optimization unit 503 includes:
the important module operation unit is used for enabling the vehicle-mounted application modules in the important module set to continue to operate when the real-time state indicates that the available resources of the critical resources of the system are insufficient;
the expansion module optimizing unit is used for adjusting the performance of the vehicle-mounted application module in the expansion module set to gradually decrease;
and the irrelevant module stopping unit is used for stopping the operation of the vehicle-mounted application modules in the irrelevant module set.
In some alternative embodiments, the expansion module optimizing unit includes:
the optimizing subunit is used for sequentially optimizing the performance of each vehicle-mounted application module in the expansion module set according to the order of the priority from high to low until the real-time state indicates that the available resources of the critical resources of the system reach the preset sufficient state;
and the stopping subunit is used for sequentially stopping each vehicle-mounted application module in the expansion module set according to the order of the priority from high to low when the real-time state indicates that the available resources of the critical resources of the system are insufficient after all the vehicle-mounted application modules in the expansion module set are optimized, until the real-time state indicates that the available resources of the critical resources of the system reach a preset sufficient state.
In some alternative embodiments, the optimizing subunit includes:
the frequency adjusting unit is used for adjusting the working frequency of the target vehicle-mounted application module;
the compression unit is used for compressing input and output data of the target vehicle-mounted application module
The transmission mode adjusting unit is used for changing the parallel data transmission mode of the target vehicle-mounted application module into serial data transmission;
and the precision adjusting unit is used for adjusting the calculation precision of the target vehicle-mounted application module.
In some alternative embodiments, the system critical resource is a central processor and the status monitoring unit 502 includes:
the curve fitting unit is used for monitoring the average load rate, the average waiting task number and the running state information fed back by the central processing unit every second of the central processing unit at a preset frequency, and calculating a comprehensive change curve of the system resources according to the average load rate, the average waiting task number and the running state information fed back by the central processing unit;
and the triggering optimization unit is used for triggering optimization when the average value of the comprehensive change curve of the system resources exceeds a preset threshold value.
In some alternative embodiments, further comprising:
and the emergency parking unit is used for controlling the vehicle to enter an emergency parking state when the current automatic driving task cannot achieve the driving target due to the fact that one vehicle-mounted application module is stopped in the expansion module set.
Further functional descriptions of the above respective modules and units are the same as those of the above corresponding embodiments, and are not repeated here.
The vehicle resource optimizing device in this embodiment is presented in the form of functional units, where the units refer to ASIC (Application Specific Integrated Circuit ) circuits, processors and memories executing one or more software or fixed programs, and/or other devices that can provide the above-described functions.
The embodiment of the invention also provides a computer device which is provided with the vehicle-mounted resource optimizing device shown in the figure 5.
Referring to fig. 6, fig. 6 is a schematic structural diagram of a computer device according to an alternative embodiment of the present invention, as shown in fig. 6, the computer device includes: one or more processors 10, memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components are communicatively coupled to each other using different buses and may be mounted on a common motherboard or in other manners as desired. The processor may process instructions executing within the computer device, including instructions stored in or on memory to display graphical information of the GUI on an external input/output device, such as a display device coupled to the interface. In some alternative embodiments, multiple processors and/or multiple buses may be used, if desired, along with multiple memories and multiple memories. Also, multiple computer devices may be connected, each providing a portion of the necessary operations (e.g., as a server array, a set of blade servers, or a multiprocessor system). One processor 10 is illustrated in fig. 6.
The processor 10 may be a central processor, a network processor, or a combination thereof. The processor 10 may further include a hardware chip, among others. The hardware chip may be an application specific integrated circuit, a programmable logic device, or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general-purpose array logic, or any combination thereof.
Wherein the memory 20 stores instructions executable by the at least one processor 10 to cause the at least one processor 10 to perform a method for implementing the embodiments described above.
The memory 20 may include a storage program area that may store an operating system, at least one application program required for functions, and a storage data area; the storage data area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, memory 20 may optionally include memory located remotely from processor 10, which may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
Memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk, or solid state disk; the memory 20 may also comprise a combination of the above types of memories.
The computer device also includes a communication interface 30 for the computer device to communicate with other devices or communication networks.
The embodiments of the present invention also provide a computer readable storage medium, and the method according to the embodiments of the present invention described above may be implemented in hardware, firmware, or as a computer code which may be recorded on a storage medium, or as original stored in a remote storage medium or a non-transitory machine readable storage medium downloaded through a network and to be stored in a local storage medium, so that the method described herein may be stored on such software process on a storage medium using a general purpose computer, a special purpose processor, or programmable or special purpose hardware. The storage medium can be a magnetic disk, an optical disk, a read-only memory, a random access memory, a flash memory, a hard disk, a solid state disk or the like; further, the storage medium may also comprise a combination of memories of the kind described above. It will be appreciated that a computer, processor, microprocessor controller or programmable hardware includes a storage element that can store or receive software or computer code that, when accessed and executed by the computer, processor or hardware, implements the methods illustrated by the above embodiments.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (10)
1. A vehicle-mounted resource optimization method, characterized in that the method comprises:
dividing a vehicle-mounted application module in a vehicle into a plurality of important levels according to the importance level of operation;
monitoring the real-time state of critical resources of the system;
and analyzing the reduction condition of the available resources of the critical resources of the system according to the real-time state, and optimizing each vehicle-mounted application module according to the reduction condition of the available resources and the order from least important to most important of importance levels.
2. The method of claim 1, wherein the classifying the on-board application module in the vehicle into a plurality of importance levels according to the importance level of the operation comprises:
according to different performance modes, under different automatic driving task scenes, the vehicle-mounted application modules for safely executing the tasks are divided into important module sets, the vehicle-mounted application modules for optimizing the task effect are divided into extension module sets, and useless vehicle-mounted application modules under the current scene are divided into irrelevant module sets.
3. The method according to claim 2, wherein analyzing the available resource reduction of the critical resources of the system according to the real-time status, and optimizing each in-vehicle application module according to the available resource reduction in order of importance level from least important to most important, comprises:
when the real-time state indicates that the available resources of the critical resources of the system are insufficient, enabling the vehicle-mounted application modules in the important module set to continue to run;
the performance of the vehicle-mounted application module in the expansion module set is adjusted to be gradually reduced;
and stopping running the vehicle-mounted application modules in the irrelevant module set.
4. The method of claim 3, wherein the vehicle-mounted application modules in the set of expansion modules are given priority from high to low according to the importance level from small to large, and the adjusting the performance of the vehicle-mounted application modules in the set of expansion modules gradually decreases includes:
sequentially optimizing the performance of each vehicle-mounted application module in the expansion module set according to the order of the priority from high to low until the real-time state indicates that the available resources of the critical resources of the system reach a preset sufficient state;
and when all the vehicle-mounted application modules in the expansion module set are optimized, the real-time state indicates that the available resources of the critical resources of the system are still insufficient, and each vehicle-mounted application module in the expansion module set is sequentially stopped according to the order of the priority from high to low until the real-time state indicates that the available resources of the critical resources of the system reach a preset sufficient state.
5. The method according to claim 4, wherein optimizing the performance of each in-vehicle application module in the set of expansion modules sequentially according to the order of priority from high to low comprises:
adjusting the working frequency of a target vehicle-mounted application module;
and/or compressing input/output data of the target vehicle-mounted application module
And/or changing the parallel data transmission mode of the target vehicle-mounted application module into serial data transmission;
and/or adjusting the calculation precision of the target vehicle-mounted application module.
6. The method of claim 1, wherein the system critical resource is a central processing unit, and wherein monitoring the real-time status of the system critical resource comprises:
monitoring the average load rate, the average waiting task number and the running state information fed back by the central processing unit every second by a preset frequency, and calculating a comprehensive change curve of system resources according to the average load rate, the average waiting task number and the running state information fed back by the central processing unit;
triggering optimization when the average value of the comprehensive change curve of the system resources exceeds a preset threshold value.
7. The method according to claim 4, wherein the method further comprises:
when one vehicle-mounted application module in the expansion module set stops and the current automatic driving task cannot achieve the driving target, controlling the vehicle to enter an emergency parking state.
8. An in-vehicle resource optimization apparatus, characterized by comprising:
the application grade dividing unit is used for dividing a vehicle-mounted application module in the vehicle into a plurality of important grades according to the running importance degree;
the state monitoring unit is used for monitoring the real-time state of the critical resources of the system;
and the optimizing unit is used for analyzing the reduction condition of the available resources of the critical resources of the system according to the real-time state and optimizing each vehicle-mounted application module according to the reduction condition of the available resources from the least important to the most important order of the importance level.
9. A computer device, comprising:
a memory and a processor in communication with each other, the memory having stored therein computer instructions which, upon execution, cause the processor to perform the method of any of claims 1 to 7.
10. A computer readable storage medium having stored thereon computer instructions for causing a computer to perform the method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410059575.4A CN117785476A (en) | 2024-01-15 | 2024-01-15 | Vehicle-mounted resource optimization method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410059575.4A CN117785476A (en) | 2024-01-15 | 2024-01-15 | Vehicle-mounted resource optimization method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117785476A true CN117785476A (en) | 2024-03-29 |
Family
ID=90391022
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410059575.4A Pending CN117785476A (en) | 2024-01-15 | 2024-01-15 | Vehicle-mounted resource optimization method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117785476A (en) |
-
2024
- 2024-01-15 CN CN202410059575.4A patent/CN117785476A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102111337B (en) | Method and system for task scheduling | |
| CN109743369B (en) | Real-time data processing device, method and system based on Internet of vehicles | |
| CN109962858B (en) | CAN bus data transmission method and control system | |
| JP2019049969A (en) | Safety control of network-connected autonomous vehicle | |
| US9342245B2 (en) | Method and system for allocating a resource of a storage device to a storage optimization operation | |
| US11897490B2 (en) | Autonomous driving vehicle health monitoring | |
| CN114661574A (en) | Method and device for acquiring sample deviation data and electronic equipment | |
| CN114697324B (en) | Real-time video analysis and processing method based on edge cloud cooperation | |
| CN107395735B (en) | Delay and capacity reduction scheduling method and system for container cluster | |
| CN114475893B (en) | Control method and device of riding equipment and riding equipment | |
| CN117648199B (en) | Wireless edge computing system based on camera | |
| CN117785476A (en) | Vehicle-mounted resource optimization method, device, equipment and storage medium | |
| CN109726080B (en) | Method and device for monitoring working state of heterogeneous computing system | |
| CN113377573A (en) | Abnormity processing method, device, equipment and storage medium for automatic driving vehicle | |
| CN107272874B (en) | Method and system for adjusting state of storage driver of server | |
| CN115391051A (en) | Video computing task scheduling method, device and computer readable medium | |
| CN114281069A (en) | Control method and device of unmanned equipment | |
| CN115080233A (en) | Resource allocation management method, device, equipment and storage medium for application software | |
| CN114987494A (en) | Driving scene processing method and device and electronic equipment | |
| CN115123302A (en) | Decision planning system and method for automatic driving vehicle and vehicle | |
| CN114330944A (en) | Scheduling method and system, and computer storage medium | |
| CN116708445B (en) | Distribution method, distribution network system, device and storage medium for edge computing task | |
| CN113805546B (en) | Model deployment method and device, computer equipment and storage medium | |
| CN115065685B (en) | Cloud computing resource scheduling method, device, equipment and medium | |
| CN118242185B (en) | Engine torque control method, device, gearbox controller and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |