A power consumption control method, device and equipment of an automatic driving system and a storage medium

Abstract

The application discloses a power consumption control method, device and equipment of an automatic driving system and a storage medium. The method comprises the following steps: acquiring road information and vehicle information of a target vehicle in a current driving environment; extracting road scene features from the road information and vehicle posture control features from the vehicle information; and based on the extracted features, using a trained proportion prediction model to predict a demand proportion of the target vehicle for a sensor in the current road scene. According to the predicted demand proportion, a matching power consumption control state level is searched from a preset power consumption control state level library. Based on the driving mode and the executable sensor identifier in the searched power consumption control state level, a target driving mode and a target sensor are determined, the target vehicle is controlled to run the target sensor, and automatic driving control is performed in the target driving mode. Thus, the prediction accuracy of the demand proportion is improved, the energy consumption is managed in stages, and the overall vehicle power consumption is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of automatic driving, in particular to the technical field of power consumption control and sensor management, and specifically relates to a power consumption control method and device of an automatic driving system, equipment and a storage medium. BACKGROUND

[0002] Automatic driving is a technology that uses advanced communication, computer, network and control technologies to realize real-time and continuous control of vehicles by relying on multi-sensor fusion and high-computing-power platforms. This technology is a redundant design for automatic driving in all scenarios to meet extremely complex automatic driving extreme scenarios through data fusion of multiple sensors and high-computing-power data processing platforms.

[0003] However, this redundant design, i.e., the design that multiple sensors and high-computing-power data processing platforms are needed regardless of the scenario to assist in processing data, directly leads to high energy consumption required for vehicle operation and additional energy consumption caused by heat dissipation of too many devices or components, thereby increasing the power consumption of the vehicle in the automatic driving process. SUMMARY

[0004] The present application provides a power consumption control method, device, equipment and storage medium of an automatic driving system to solve the problem of high power consumption caused by running redundant multiple sensors and high-computing-power data processing platforms in existing automatic driving systems to adapt to various complex automatic driving scenarios.

[0005] The technical solution is as follows:

[0006] In a first aspect, a power consumption control method of an automatic driving system is provided, comprising:

[0007] obtaining road information and vehicle information of a target vehicle in a current driving environment;

[0008] extracting road scene features from the road information and vehicle attitude control features from the vehicle information, and using a trained proportion prediction model to predict a demand proportion of sensors of the target vehicle in the current road scene based on the road scene features and the vehicle attitude control features;

[0009] According to the predicted demand proportion, a matched power consumption control state level is searched from a preset power consumption control state level library, wherein the preset power consumption control state level library stores a plurality of power consumption control state levels, and each power consumption control state level is configured with a driving mode, a demand proportion and a runnable sensor identifier;

[0010] Based on the driving mode and the executable sensor identifier in the found power consumption control state level, a target driving mode and a target sensor are determined respectively, the target vehicle is controlled to operate the target sensor, and automatic driving control is performed in the target driving mode.

[0011] In a possible implementation, based on the road scene feature and the vehicle attitude control feature, a trained proportion prediction model is used to predict the demand proportion of the target vehicle to the sensor in the current road scene, specifically including

[0012] The road scene feature and the vehicle attitude control feature are input into a trained proportion prediction model respectively, and the demand proportion of the target vehicle to the sensor in the current road scene is predicted; wherein the trained proportion prediction model is a multi-modal prediction model.

[0013] In a possible implementation, the proportion prediction model is trained by the following method:

[0014] Obtain the automatic driving historical data of a sample vehicle of the same model as the target vehicle when the sample vehicle runs at full power in multiple road scenes;

[0015] Filter a sample data set for training from the automatic driving historical data; wherein the sample data set contains multiple sample data and a sample label corresponding to each sample data, and each sample data at least contains a road scene feature and a vehicle attitude control feature; and the sample label is the running proportion of multiple sensors on the sample vehicle;

[0016] Input the multiple sample data composed of the road scene feature and the vehicle attitude control feature and the sample label in the sample data set into a preset neural network model for training;

[0017] Based on the optimal control strategy, the model is repeatedly adjusted to obtain a converged proportion prediction model.

[0018] In a possible implementation, the method further includes:

[0019] Periodically detect road information of the target vehicle in the current driving environment;

[0020] If it is detected that the road information changes, the latest road information and vehicle information of the target vehicle in the current driving environment are reacquired, the road scene feature and the vehicle attitude control feature are extracted based on the latest road information and vehicle information respectively, and a trained proportion prediction model is used to predict the latest demand proportion of the target vehicle to the sensor in the current road scene;

[0021] According to the predicted latest demand proportion, a matching latest power consumption control state level is searched from a preset power consumption control state level library;

[0022] The target vehicle is controlled to switch from a current power consumption control state level to a latest power consumption control state level.

[0023] In a possible implementation, the method further includes:

[0024] Periodically receiving whole-vehicle control data and automatic driving control data, and performing parsing;

[0025] According to the parsing result, it is evaluated whether a power consumption control state level of the target vehicle in a current driving environment matches;

[0026] If not, the power consumption control state level is exited, and a direct control mode of the whole-vehicle control system and the automatic driving system is triggered to enter.

[0027] In a second aspect, a power consumption control device of an automatic driving system is provided, including:

[0028] An acquisition module is configured to acquire road information and vehicle information of a target vehicle in a current driving environment;

[0029] A prediction module is configured to extract road scene features from the road information, extract vehicle attitude control features from the vehicle information, and use a trained proportion prediction model to predict a demand proportion of a sensor of the target vehicle in a current road scene based on the road scene features and the vehicle attitude control features;

[0030] A searching module is configured to search a matching power consumption control state level from a preset power consumption control state level library according to the predicted demand proportion, wherein the preset power consumption control state level library stores a plurality of power consumption control state levels, and each power consumption control state level is configured with a driving mode, a demand proportion, and a runnable sensor identifier;

[0031] A control module is configured to determine a target driving mode and a target sensor based on the driving mode and the runnable sensor identifier in the searched power consumption control state level, control the target vehicle to run the target sensor, and perform automatic driving control in the target driving mode.

[0032] In a third aspect, a computer readable storage medium is provided, the storage medium stores at least one instruction, and the at least one instruction is loaded and executed by a processor to implement the method of the above aspects and any possible implementation.

[0033] In a fourth aspect, an electronic device is provided, including:

[0034] at least one processor; and

[0035] a memory communicatively connected with the at least one processor; wherein

[0036] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method of the aspects and any possible implementation manners as described above.

[0037] In a fifth aspect, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the method of the aspects and any possible implementation manners as described above.

[0038] In a sixth aspect, an autonomous vehicle is provided, comprising the electronic device as described above.

[0039] The beneficial effects of the technical solutions provided in the present application at least include:

[0040] From the above technical solutions, it can be seen that the embodiments of the present application obtain road information and vehicle information of a target vehicle in a current driving environment; extract road scene features from the road information and vehicle posture control features from the vehicle information, and based on the road scene features and the vehicle posture control features, use a trained proportion prediction model to predict a demand proportion of a sensor of the target vehicle in the current road scene. Then, according to the predicted demand proportion, a matching power consumption control state level is searched from a preset power consumption control state level library. Subsequently, based on the driving mode and the executable sensor identifier in the searched power consumption control state level, a target driving mode and a target sensor are determined respectively, the target vehicle is controlled to run the target sensor, and automatic driving control is performed in the target driving mode. Thus, the prediction accuracy of the demand proportion of the sensor is improved, and under the condition of ensuring the safety of the autonomous driving of the autonomous vehicle, the energy consumption is managed in stages by controlling the running number and the on-off state of the sensor in different working condition modes, thereby reducing the energy consumption.

[0041] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative labor based on these drawings.

[0043] Figure 1 is a schematic diagram of steps of the power consumption control method of the automatic driving system provided by an embodiment of the present application.

[0044] Figure 2 is a schematic diagram of the power consumption control flow of the automatic driving system provided by an embodiment of the present application.

[0045] Figure 3 is a schematic diagram of the structure of the power consumption control device of the automatic driving system provided by an embodiment of the present application.

[0046] Figure 4 is a structural block diagram of the power consumption control system of the automatic driving system provided by another embodiment of the present application.

[0047] Figure 5 is a block diagram of the electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0048] The exemplary embodiments of the present application will be described below with reference to the accompanying drawings, which include various details of the embodiments of the present application to help the understanding, and should be considered as merely exemplary. Therefore, those skilled in the art should realize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Also, in order to be clear and concise, the description below omits the description of well-known functions and structures.

[0049] Obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0050] It should be noted that the terminal device involved in the embodiments of the present application can include but is not limited to mobile phones, personal digital assistants (PDA), wireless handheld devices, tablet computers, and other smart devices; the display device can include but is not limited to personal computers, televisions, and other devices with display functions.

[0051] In addition, the term "and / or" in this document merely describes an association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects.

[0052] The current automatic driving development technology route mostly relies on a multi-sensor fusion and a high-computing-power platform architecture scheme, and its essence is to make a redundant design for automatic driving in all scenarios, so as to meet extremely complex automatic driving extreme scenarios through data fusion of multiple sensors and a high-computing-power data processing platform. For example, in some scenarios, only certain sensor data is needed, but all sensors are in a working state, which leads to high energy consumption of data processing and additional energy consumption caused by heat dissipation of the computing platform, greatly increasing the power consumption of the vehicle.

[0053] In view of this, the embodiment of the present application provides a power consumption control scheme of an automatic driving system, and the main inventive concept is to: obtain road information and vehicle information of a target vehicle in a current driving environment; extract road scene features from the road information and vehicle posture control features from the vehicle information, and based on the road scene features and the vehicle posture control features, use a trained proportion prediction model to predict a demand proportion of sensors of the target vehicle in the current road scene. Then, according to the predicted demand proportion, a matching power consumption control state level is searched from a preset power consumption control state level library. Subsequently, based on the driving mode and the executable sensor identifier in the searched power consumption control state level, a target driving mode and a target sensor are respectively determined, the target vehicle is controlled to run the target sensor, and automatic driving control is performed in the target driving mode. Thus, under the condition of ensuring the safety of automatic driving of the vehicle, the running number and the on-off state of the sensors, the computing power platform, and the auxiliary heat dissipation device in different working condition modes are controlled to realize hierarchical management of energy consumption and reduce energy consumption.

[0054] Referring to Figure 1 FIG. 1 shows a step schematic diagram of a power consumption control method of an automatic driving system provided by the embodiment of the present application. The execution subject of the power consumption control method is a power consumption control device of an automatic driving system. In the present application, the power consumption control device of the automatic driving system can be a software module with computing and data processing capabilities, or an electronic device integrated with a similar software module. In fact, the device has a relatively optimal effect when applied to a functional low-speed automatic driving vehicle, such as an automatic driving shuttle, a logistics vehicle, a cleaning vehicle, etc., which can determine the optimal minimum working boundary required for automatic driving according to different working conditions, interact with the automatic driving system according to the boundary, enter different working modes, and adopt different automatic driving strategies to achieve the purpose of controlling energy consumption.

[0055] As shown in the power consumption control method of the automatic driving system, Figure 1 may specifically include the following steps:

[0056] Step 102: Obtain road information and vehicle information of a target vehicle in a current driving environment.

[0057] In the scheme of the present application, the target vehicle can be a shuttle vehicle, a logistics vehicle, a delivery vehicle, a cleaning vehicle, etc. with automatic driving function; the road information in the current driving environment can include road identification, road layout, traffic signals, lane lines, etc. The vehicle information can include the speed, body posture, driving direction, brake condition, etc. of the target vehicle related to driving. It should be understood that, under the condition of permission, the vehicle information can also include the driving information of other vehicles and obstacle information in the current driving environment.

[0058] Step 104: Extract road scene features from the road information, and extract vehicle posture control features from the vehicle information, and based on the road scene features and the vehicle posture control features, use the trained proportion prediction model to predict the demand proportion of the target vehicle to the sensor in the current road scene.

[0059] Then, the road scene in the current driving environment is determined based on the obtained road information, and the road scene features are extracted. For example, highway scene, expressway scene, urban road scene, rural road scene, tunnel scene, viaduct scene, cross-sea bridge scene, etc. Each different road scene has different road scene features, which can be used as a feature vector of the road scene. At the same time, the vehicle posture can be screened from the vehicle information, and the vehicle posture control features used to represent the vehicle posture vector are extracted based on the vehicle posture. The vehicle posture control features can be used as a feature vector of the vehicle posture. The extracted road scene features and vehicle posture control features are sent to the trained proportion prediction model, and the demand proportion of the target vehicle to the sensor in the current road scene is predicted by model processing.

[0060] In the scheme of the present application, the demand proportion of the sensor can be predicted in the following two ways.

[0061] The first way is to fuse the road scene features and the vehicle posture control features; the fused features are input into the trained proportion prediction model to predict the demand proportion of the target vehicle to the sensor in the current road scene.

[0062] The second mode is that the road scene features and the vehicle attitude control features are respectively input into a trained proportion prediction model to predict the demand proportion of the target vehicle for the sensor in the current road scene.

[0063] The first mode is to extract the two features first, then fuse the two different features, and then input the fused features into a trained proportion prediction model for prediction. Correspondingly, the proportion prediction model in this mode is also trained repeatedly based on the fused features in the model training stage.

[0064] The second mode is not to fuse the two features, but to input the two features into a trained proportion prediction model for prediction. The proportion prediction model in this mode is trained repeatedly based on the two features in the model training stage.

[0065] Regardless of which mode is used for prediction, the accuracy and processing efficiency of determining the sensor demand proportion can be improved based on a learning algorithm, thereby facilitating subsequent control of a proper number of sensors to work and saving the power consumption of the whole vehicle.

[0066] In the scheme of the present application, the second mode can be selected for prediction. Correspondingly, the proportion prediction model corresponding to this mode can be trained by the following steps:

[0067] First, the automatic driving historical data of a sample vehicle of the same model as the target vehicle in full-power running in multiple road scenes is obtained.

[0068] Firstly, the model of the target vehicle to be sampled needs to be determined, and one or more sample vehicles for testing are selected according to the determined model. Then, the sample vehicle is controlled to drive in different road scenes, and the sample vehicle needs to be controlled to drive in a full-power running state at this time. After that, the automatic driving historical data of the sample vehicle in full-power running in multiple road scenes is collected.

[0069] The automatic driving historical data can include vehicle information such as the speed, driving direction, brake condition, steering, and body attitude of the sample vehicle, and road information such as the road layout, road signs, traffic signals, and lane lines in the road scene where the sample vehicle is sampled. In addition, it also includes the actual working sensor quantity or sensor identifier of the sample vehicle in full-power running.

[0070] Secondly, a sample data set for training is screened from the automatic driving history data; wherein the sample data set contains a plurality of sample data and a sample label corresponding to each sample data, and each sample data at least contains a road scene feature and a vehicle attitude control feature; the sample label is an operation proportion of a plurality of sensors on a sample vehicle.

[0071] It should be understood that each sample vehicle can obtain an automatic driving history data when driving a sample in each road scene, so that a sufficient amount of automatic driving history data can be obtained through driving a sample in a plurality of road scenes by a plurality of sample vehicles. The road scene feature and the vehicle attitude control feature are screened from each automatic driving history data as the sample data for training, and the operation proportion of the sensor is determined as the sample label of the sample data according to the number or the sensor identifier of the sensor actually working when the sample vehicle is running at full power in the automatic driving history data.

[0072] Thirdly, the plurality of sample data and the sample label constituted by the road scene feature and the vehicle attitude control feature in the sample data set are input into a preset neural network model for training.

[0073] After a large amount of sample data (road scene feature and vehicle attitude control feature) and sample label (operation proportion of sensor) are obtained, they are input into a preset neural network model for model training. The preset neural network model here can be a feedback neural network model such as a long short-term memory network model LSTM and a recurrent neural network model RNN, or can be a feedforward neural network model such as a radial basis function neural network model RBF and a convolutional neural network model CNN. The type of the preset neural network model is not limited in the application, and LSTM is preferably used so as to obtain a better model effect.

[0074] Fourthly, the proportion prediction model is obtained by repeatedly adjusting the parameters of the model based on the optimal control strategy.

[0075] After the preset neural network model is repeatedly adjusted and learned based on the optimal control strategy, the proportion prediction model is obtained, which can accurately predict the operation proportion of the sensor of the target vehicle and improve the processing efficiency of the target vehicle.

[0076] Step 106: According to the predicted demand proportion, a matching power consumption control state level is searched from a preset power consumption control state level library; wherein the preset power consumption control state level library stores a plurality of power consumption control state levels, and each power consumption control state level is configured with a driving mode, a demand proportion and a runnable sensor identifier.

[0077] In the scheme of the present application, a power consumption control state classification library can be created in advance, which can be stored on the Internet of Vehicles platform or other cloud devices, or stored locally on the target vehicle.

[0078] The power consumption control state classification library stores a plurality of power consumption control state levels, each of which is configured with a driving mode, a demand ratio, and a runnable sensor identifier. The driving mode involved in the present application can include an automatic driving mode, a remote takeover mode, and a manual operation mode. The target vehicle can switch and adjust between different driving modes according to driving requirements to adapt to the current road scene and perform safe and reliable driving operations.

[0079] The specific number of levels can be set according to the sensor demand ratio or power consumption ratio. For example, there are a total of 20 corresponding sensors on the vehicle, which can be roughly divided into 10 levels, i.e. 10%, 20%, 30%...80%, 90%, 100%. For another example, according to the computing power and power consumption ratio of the sensor, it can be roughly divided into 4 levels, i.e. 0%, 20%, 60%, and 100% of full power consumption. Each level includes a driving mode, a demand ratio, and a runnable sensor identifier.

[0080] In the scheme of the present application, it can be divided into 4 levels according to the power consumption ratio, i.e. the power consumption control state level library is configured with 4 levels:

[0081] Power consumption control state level 1: the target vehicle is in remote takeover mode and manual operation mode, and the computing unit platform and sensors of the automatic driving system are in a power-on standby state. This mode has the lowest power consumption (0% of full power consumption).

[0082] Power consumption control state level 2: the target vehicle is in automatic driving mode, the automatic driving system computing unit platform is in a calibrated low-power mode (20% of full power consumption), the sensor only has a front binocular camera and a front millimeter wave radar working, and other sensors are in a standby sleep state, realizing the automatic driving ability of automatic following and autonomous cruise.

[0083] Power consumption control state level 3: the target vehicle is in automatic driving mode, the automatic driving system computing unit is in a calibrated medium power consumption (60% of full power consumption), the sensor only has a front double laser radar and a front monocular camera working, and other sensors are in a standby sleep state, realizing the automatic driving ability of automatic following and autonomous cruise, and realizing the obstacle avoidance and lane changing function.

[0084] Power consumption control state level 4: the target vehicle is in automatic driving mode, the automatic driving system computing unit is in a calibrated full power consumption, and all sensors are in a working state, realizing all high-level automatic driving functions.

[0085] It should be understood that in the scheme of the present application, the running proportion of the sensor can be equivalent to the power consumption proportion of the sensor and the computing power platform. That is, the running proportion of the sensor is approximately equal to the full power consumption proportion mentioned above.

[0086] In this way, after predicting the running proportion of the sensor of the target vehicle in the current road scene according to step 104, the power consumption control state level corresponding to the predicted running proportion of the sensor can be matched from the power consumption control state level library. For example, the predicted running proportion of the sensor is 20%, and power consumption control state level 2 can be selected. For another example, the predicted running proportion of the sensor is 30%, but there is no running proportion value of 30% in the power consumption control state level library. At this time, the level closest to the running proportion value of 30% can be selected, 30% is close to 20% and far from 60%, so power consumption control state level 2 is the most matched power consumption control state level. For another example, the predicted running proportion of the sensor is 40%, which has the same closeness to 20% and 60%. At this time, in order to ensure the reliable execution of autonomous driving, power consumption control state level 3 can be selected, so that as many sensors as possible can be turned on to ensure the normal execution of autonomous driving, and the power consumption is saved to a certain extent.

[0087] Step 108: based on the driving mode and the running sensor identifier in the found power consumption control state level, respectively determining the target driving mode and the target sensor, controlling the target vehicle to run the target sensor, and performing autonomous driving control in the target driving mode.

[0088] Since each power consumption control state level has a corresponding driving mode and sensor identifier, after the matched power consumption control state level is determined, the target driving mode can be determined according to the driving mode under the power consumption control state level, and the target sensor can be determined according to the sensor identifier. Then, the target vehicle is controlled to turn on and run the target sensor, and autonomous driving control is performed in the target driving mode.

[0089] Optionally, in the scheme of the present application, after the target vehicle is controlled to run the target sensor and perform autonomous driving control in the target driving mode by using the above scheme, since the road scene is not fixed and can change over time, that is, the target vehicle is currently in a highway section, and the next time it may drive out of the highway and into an urban road. Therefore, the road information of the target vehicle in the current driving environment can also be periodically detected; and when the detected road information changes, the above steps 102-108 are repeatedly executed.

[0090] In other words, if a change in road information is detected, the target vehicle reacquires the latest road information and vehicle information in the current driving environment, extracts road scene features and vehicle posture control features based on the latest road information and vehicle information, respectively, uses the trained proportion prediction model to predict the latest demand proportion of the target vehicle for sensors in the current road scene, finds a matching latest power consumption control state level from the pre-set power consumption control state level library according to the predicted latest demand proportion, and controls the target vehicle to switch from the current power consumption control state level to the latest power consumption control state level. In this way, the target vehicle can adjust the power consumption control state level in a timely manner according to the change in the road scene, so that the target vehicle always runs a reasonable number of sensors to perform automatic driving control, thereby saving the power consumption of the whole vehicle.

[0091] Further, in the scheme of the present application, the whole vehicle control data and the automatic driving control data can also be received periodically and parsed, and it is determined whether the power consumption control state level of the target vehicle in the current driving environment is matched according to the parsing result. If not, the power consumption control state level is exited, and the direct control mode of the whole vehicle control system and the automatic driving system is triggered. This way can evaluate whether the controlled state of the current target vehicle and the power consumption control state level of the automatic driving are reasonable, and if necessary, the power consumption control of the automatic driving is forced to exit, the whole vehicle control system and the automatic driving system are directly connected, and the target vehicle is controlled by the automatic driving of the power consumption management control authority.

[0092] It should be understood that the sensors involved in the present application can be image acquisition devices or temperature acquisition devices or other sensor devices installed or integrated on the target vehicle, such as cameras, laser radars, temperature sensors, millimeter wave radars, etc. The present application does not limit this.

[0093] Referring to Figure 2 Fig. 1 shows a power consumption control flow diagram of an automatic driving system provided by an embodiment of the present application.

[0094] Step 202: Collect automatic driving data sets of the same vehicle model in full-power multi-road scene.

[0095] Since different vehicle models are configured with different types and numbers of sensors, when implementing the power consumption control scheme, the same vehicle model of the automatic driving vehicle is sampled.

[0096] Step 204: Screen the data to determine the training data.

[0097] The sample data required for this model training is screened from the collected automatic driving data set.

[0098] Step 206: Extract the demand proportion of the whole vehicle for each sensor data in the automatic driving system.

[0099] Step 208: Extract the road scene classification and label.

[0100] The steps 206 and 208 are mainly used to determine the feature vectors participating in the model training and the sample labels from the sample data, specifically, the demand proportion of the sensor is extracted as the sample label, and the road scene is extracted as one of the feature vectors. Subsequently, the vehicle posture can also be extracted as another feature vector through step 212.

[0101] Step 210: Time coupling is performed through the road scene and the demand proportion of the sensor.

[0102] Step 212: Input the vehicle posture control historical data set.

[0103] This step is mainly used to extract the feature vector corresponding to the vehicle posture from the vehicle posture control historical data set, and input the feature vector together with the feature vector of the road scene described above into the model for training.

[0104] Step 214: A prediction model is obtained by training a long short-term memory network (LSTM) and an optimal control strategy.

[0105] Step 216: Obtain the vehicle posture and the road scene under the current driving scene.

[0106] This step can extract the feature vector to be predicted under the current driving scene from the obtained vehicle posture and road scene.

[0107] Step 218: Input the prediction model for prediction to obtain the demand proportion of the sensor under the current scene.

[0108] Step 220: Find the state level matching the demand proportion of the sensor from the power consumption control state level library.

[0109] Step 222: Execute the automatic driving using the driving mode corresponding to the matched state level and the sensor identifier.

[0110] Thus, under the condition of ensuring the safety of the automatic driving vehicle, the energy consumption is managed in stages by controlling the running number and on-off state of the sensor, computing platform, and auxiliary cooling device under different working condition modes, thereby reducing the energy consumption. Moreover, when determining the running number of the sensor, the LSTM model is predicted by the machine learning algorithm, which significantly improves the estimation accuracy of the running number of the sensor, thereby improving the safety of the automatic driving and saving energy consumption.

[0111] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0112] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0113] Figure 3 This application shows a structural block diagram of a power consumption control device for an autonomous driving system according to an embodiment of the present application, such as... Figure 3 As shown. The power consumption control device 300 of the autonomous driving system in this embodiment may include an acquisition module 301, a prediction module 302, a search module 303, and a control module 304. The acquisition module 301 is used to acquire road information and vehicle information of the target vehicle in the current driving environment; the prediction module 302 is used to extract road scene features from the road information and vehicle attitude control features from the vehicle information, and based on the road scene features and vehicle attitude control features, use a trained percentage prediction model to predict the percentage of sensor demand of the target vehicle in the current road scene; the search module 303 is used to search for a matching power consumption control state level from a preset power consumption control state level library according to the predicted demand percentage; wherein the preset power consumption control state level library stores multiple power consumption control state levels, each power consumption control state level is configured with a driving mode, a demand percentage, and an operable sensor identifier; the control module 304 is used to determine the target driving mode and the target sensor based on the driving mode and operable sensor identifier in the searched power consumption control state level, control the target vehicle to operate the target sensor, and perform autonomous driving control in the target driving mode.

[0114] It should be noted that some or all of the power consumption control device of the autonomous driving system in this embodiment can be an application located on the local terminal, or it can be a plugin or software development kit (SDK) or other functional unit set in the application located on the local terminal, or it can be a processing engine located on the network-side server, or it can be a distributed system located on the network side, such as a processing engine or distributed system in the autonomous driving platform on the network side. This embodiment does not impose any particular limitations on this.

[0115] It can be understood that the application can be a native application (nativeApp) installed on the local terminal, or can also be a web application (webApp) of a browser on the local terminal, and the present embodiment does not limit this.

[0116] Optionally, in a possible implementation of the present embodiment, the obtaining module 301 can be specifically configured to input the road scene features and the vehicle attitude control features into a trained proportion prediction model respectively, and predict the demand proportion of the target vehicle for the sensor in the current road scene; wherein the trained proportion prediction model is a multi-modal prediction model.

[0117] Optionally, in a possible implementation of the present embodiment, the proportion prediction model is trained by the following method:

[0118] Obtain automatic driving historical data of a sample vehicle of the same model as the target vehicle when the sample vehicle runs at full power in multiple road scenes; filter a sample data set for training from the automatic driving historical data; wherein the sample data set contains multiple sample data and a sample label corresponding to each sample data, and each sample data at least contains road scene features and vehicle attitude control features; the sample label is the running proportion of multiple sensors on the sample vehicle; input multiple sample data composed of road scene features and vehicle attitude control features and sample labels in the sample data set into a preset neural network model for training; repeatedly adjust the parameters of the model based on the optimal control strategy to obtain a converged proportion prediction model.

[0119] Optionally, in a possible implementation of the present embodiment, the power consumption control device of the automatic driving system further comprises a detection module and a switching module; wherein,

[0120] The detection module can be specifically configured to periodically detect road information of the target vehicle in the current driving environment;

[0121] The obtaining module 301 is further configured to re-obtain the latest road information and vehicle information of the target vehicle in the current driving environment if it is detected that the road information changes, and the prediction module 302 is further configured to extract road scene features and vehicle attitude control features based on the latest road information and vehicle information respectively, and use the trained proportion prediction model to predict the latest demand proportion of the target vehicle for the sensor in the current road scene;

[0122] The finding module 303 is further configured to find a matched latest power consumption control state level from the preset power consumption control state level library according to the predicted latest demand proportion;

[0123] The switching module is specifically configured to control the target vehicle to switch from a current power consumption control state level to a latest power consumption control state level.

[0124] Optionally, in one possible implementation of the embodiment, the power consumption control device of the automatic driving system further includes an analysis module, an evaluation module and an exit module, wherein,

[0125] The analysis module is specifically configured to periodically receive and analyze whole-vehicle control data and automatic driving control data.

[0126] The evaluation module is specifically configured to evaluate whether the power consumption control state level of the target vehicle in the current driving environment matches according to the analysis result.

[0127] The exit module is specifically configured to exit the power consumption control state level and trigger the entry into the direct control mode of the whole-vehicle control system and the automatic driving system if the power consumption control state level does not match.

[0128] In the embodiment, road information and vehicle information of the target vehicle in the current driving environment can be obtained, road scene features are extracted from the road information, vehicle posture control features are extracted from the vehicle information, and a demand proportion prediction model trained is used to predict the demand proportion of sensors of the target vehicle in the current road scene based on the road scene features and the vehicle posture control features. Then, a matching power consumption control state level is searched from a preset power consumption control state classification library according to the predicted demand proportion. Then, a target driving mode and a target sensor are determined based on the driving mode and the executable sensor identifier in the searched power consumption control state level, the target vehicle is controlled to run the target sensor, and automatic driving control is performed in the target driving mode. Thus, under the condition of ensuring the safety of automatic driving of the vehicle, the running number and the on-off state of the sensors, the computing power platforms and the auxiliary heat dissipation devices in different working condition modes are controlled to realize the hierarchical management of energy consumption and reduce the energy consumption.

[0129] Referring to Figure 4 FIG. 1 shows a structure schematic diagram of a power consumption control system of an automatic driving system provided by the embodiment of the application. The power consumption control system can include an automatic driving power consumption control device 401, an automatic driving control system 402, a whole-vehicle control system 403, a vehicle cloud control platform 404 and an automatic driving sensor system 405.

[0130] The automatic driving power consumption control device 401 can be divided into the following functional modules according to different functions: a state detection module, a signal transmission module, a scene analysis module, a mode switching module and a safety redundancy module. The state detection module is used to detect the current driving mode of the vehicle and the working state and fault state of the sensor included in the automatic driving control system. The driving module includes the automatic driving mode, the remote takeover mode and the manual operation mode. The signal transmission module is used to complete the interactive transmission of information with the vehicle control system and the automatic driving control system. The scene analysis module is used to obtain a relatively reliable automatic driving classification state by using a neural network algorithm state estimation model according to the current road environment, sensor data, automatic driving state, vehicle historical data and the like. The mode switching module is used to switch different mode working states according to the automatic driving classification state obtained by the scene analysis module, and to ensure the safety and smoothness of switching between different states. The safety redundancy module is used to analyze the automatic driving state data and the vehicle driving state data, to evaluate whether the current vehicle controlled state and the automatic driving classification state of the analysis module are reasonable, and to forcibly exit the automatic driving classification state control when necessary, so as to realize the direct connection of the vehicle control system and the automatic driving system and to bypass the energy consumption management control authority.

[0131] The automatic driving control system 402 can include level master modules for executing different power consumption control state levels and a power management master module. In addition, it can also include other necessary modules required for automatic driving, which will not be described here. Taking the example that the power consumption control state level library stores four levels, the level master module can further include: a power consumption control state level 1 master module, a power consumption control state level 2 master module, a power consumption control state level 3 master module and a power consumption control state level 4 master module. The automatic driving control system 402 can switch between different level master modules according to the decision of the automatic driving power consumption control device 401, so as to adapt to the driving mode under a reasonable level and to perform safe and energy-saving automatic driving control on the sensor.

[0132] In the power consumption control state level 1, the state monitoring module detects that the vehicle is in the remote takeover mode and the manual operation mode, and the automatic driving system platform and the sensor are in the power-on standby state. In this mode, the power consumption is the lowest.

[0133] In the power consumption control state level 2, the state detection module detects that the vehicle is in the automatic driving mode. At this time, the automatic driving system computing unit platform is in the calibrated low-power mode (20% of full power) and works, the sensor only has the front binocular camera and the front millimeter wave radar working, and other sensors are in the standby sleep state, so as to realize the automatic driving ability of automatic following and autonomous cruise.

[0134] In the power consumption control state level 3, the state detection mode detects that the vehicle is currently in the automatic driving mode, at this time, the automatic driving system computing unit is working at the marked medium power consumption (60% of the full power consumption), only the front double laser radar and the front monocular camera work, and other sensors are in standby sleep state, realizing the automatic driving ability based on automatic following and autonomous cruise, and further realizing the obstacle avoidance lane changing function.

[0135] In the power consumption control state level 4, the state detection mode detects that the vehicle is currently in the automatic driving mode, at this time, the automatic driving system computing unit is working at the marked full power consumption, and all sensors are in working state, realizing all high-order automatic driving functions.

[0136] In addition, the vehicle cloud control platform 404 can be a vehicle networking platform, configured to receive a service request of the vehicle and issue a corresponding vehicle service to the vehicle. The automatic driving sensor system 405 can include multiple independent or related sensors, which are collectively regarded as an automatic driving sensor system and provide automatic driving services for the vehicle.

[0137] An embodiment of the present application provides a computer readable storage medium, wherein at least one instruction is stored in the storage medium, and the at least one instruction is loaded and executed by a processor to implement the power consumption control method of the automatic driving system.

[0138] An embodiment of the present application provides an electronic device, comprising a processor and a memory, wherein at least one instruction is stored in the memory, and the instruction is loaded and executed by the processor to implement the power consumption control method of the automatic driving system.

[0139] An embodiment of the present application provides a computer program product, characterized in that comprising a computer program, wherein the computer program is executed by a processor to implement the power consumption control method of the automatic driving system.

[0140] An embodiment of the present application provides an automatic driving vehicle, comprising the electronic device.

[0141] In the technical solution of the present application, the collection, storage, use, processing, transmission, provision and disclosure of user personal information meet the relevant legal regulations and do not violate public order and good customs.

[0142] Figure 5A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smartphones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the present application described and / or claimed in this document to the embodiments presented herein.

[0143] As shown in Figure 5 The electronic device 500 includes a computing unit 501 that can perform various appropriate actions and processes in accordance with a computer program stored in a read-only memory (ROM) 502 or a computer program loaded into a random access memory (RAM) 503 from a storage unit 508. Various programs and data required for the operation of the electronic device 500 can also be stored in the RAM 503. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0144] Various components in the electronic device 500 are connected to the I / O interface 505, including an input unit 506, such as a keyboard, a mouse, etc.; an output unit 507, such as various types of displays, speakers, etc.; the storage unit 508, such as a magnetic disk, an optical disk, etc.; and a communication unit 509, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0145] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as power control methods for autonomous driving systems. For example, in some embodiments, the power control methods for autonomous driving systems can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the power control methods for autonomous driving systems described above can be performed. Alternatively, in other embodiments, the computing unit 501 can be configured to perform power control methods for autonomous driving systems by any other suitable means (e.g., by means of firmware).

[0146] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0147] The program code used to implement the methods of this application may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing device, such that when executed by the processor or controller, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0148] In the context of this application, a machine-readable medium can be a tangible medium that can contain or store program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable storage medium can include, but are not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0149] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0150] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0151] The computer system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server can arise by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0152] It should be understood that the various forms of flow shown above can be re-ordered, added to, or have steps deleted, for example. The steps recited in the present disclosure can be performed in parallel, in series, or in a different order, as long as the desired results of the present disclosure are achieved, and are not limited herein.

[0153] The specific embodiments discussed hereinabove are illustrative of various aspects of the present application. Alterations, modifications, combinations, sub-combinations, and the like are intended to be included within the scope of the present application. Accordingly, although specific embodiments have been described herein, these are not intended to limit the scope of the present application, as claimed.

Claims

1. A method for power consumption control of an autonomous driving system, characterized by, The method comprises: obtaining road information and vehicle information of a target vehicle in a current driving environment; extracting road scene features from the road information and vehicle posture control features from the vehicle information, and using a trained proportion prediction model to predict the proportion of sensor demand of the target vehicle in the current road scene based on the road scene features and the vehicle posture control features; According to the predicted demand proportion, find a matched power consumption control state level from a preset power consumption control state level library; wherein the preset power consumption control state level library stores a plurality of power consumption control state levels, and each power consumption control state level is configured with a driving mode, a demand proportion and a runnable sensor identifier; Based on the driving mode and the runnable sensor identifier in the found power consumption control state level, determine the target driving mode and the target sensor respectively, control the target vehicle to run the target sensor, and control the automatic driving in the target driving mode.

2. The method of claim 1, wherein, Based on the road scene features and the vehicle posture control features, a trained proportion prediction model is used to predict the proportion of sensor demand of the target vehicle in the current road scene, which comprises: inputting the road scene features and the vehicle posture control features into the trained proportion prediction model respectively to predict the proportion of sensor demand of the target vehicle in the current road scene; wherein the trained proportion prediction model is a multi-modal prediction model.

3. The method of claim 2, wherein, The proportion prediction model is trained by the following way: obtain the automatic driving historical data of a sample vehicle of the same model as the target vehicle when running at full power in multiple road scenes; select a sample data set for training from the automatic driving historical data; wherein the sample data set contains multiple sample data and sample labels corresponding to each sample data, and each sample data at least contains road scene features and vehicle posture control features; the sample label is the running proportion of multiple sensors on the sample vehicle; input the multiple sample data composed of road scene features and vehicle posture control features and the sample labels in the sample data set into a preset neural network model for training; Based on the optimal control strategy, repeatedly adjust the parameters of the model to obtain a convergent proportion prediction model.

4. The method according to any one of claims 1 to 3, characterized in that, The method further comprises: periodically detecting the road information of the target vehicle in the current driving environment; if the road information is detected to change, reacquire the latest road information and vehicle information of the target vehicle in the current driving environment; and based on the latest road information and vehicle information, extract road scene features and vehicle posture control features respectively, and use the trained proportion prediction model to predict the latest demand proportion of sensors of the target vehicle in the current road scene; According to the predicted latest demand proportion, find a matched latest power consumption control state level from a preset power consumption control state level library; Control the target vehicle to switch from the current power consumption control state level to the latest power consumption control state level.

5. The method according to any one of claims 1 to 3, wherein The method further comprises: Periodically receive whole vehicle control data and automatic driving control data, and perform analysis; According to the analysis result, evaluate whether the power consumption control state level of the target vehicle in the current driving environment matches; If not, exit the power consumption control state level, and trigger entering the direct control mode of the whole vehicle control system and the automatic driving system.

6. A power consumption control device of an autonomous driving system, characterized by comprising: Comprise: An acquisition module for acquiring road information and vehicle information of a target vehicle in a current driving environment; A prediction module for extracting road scene features from the road information and vehicle posture control features from the vehicle information, and using a trained proportion prediction model to predict the demand proportion of sensors of the target vehicle in the current road scene based on the road scene features and the vehicle posture control features; A lookup module for looking up a matched power consumption control state level from a preset power consumption control state level library according to the predicted demand proportion; wherein the preset power consumption control state level library stores a plurality of power consumption control state levels, and each power consumption control state level is configured with a driving mode, a demand proportion, and a runnable sensor identifier; A control module for determining a target driving mode and a target sensor based on the driving mode and the runnable sensor identifier in the looked-up power consumption control state level, respectively, controlling the target vehicle to run the target sensor, and performing automatic driving control in the target driving mode.

7. An electronic device, comprising: Comprise: At least one processor; And A memory communicatively connected with the at least one processor; wherein The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1-5.

8. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to make the computer perform the method according to any one of claims 1-5.

9. A computer program product, characterised in that, Comprise a computer program, which, when executed by a processor, implements the method according to any one of claims 1-5.

10. An autonomous vehicle, comprising: Comprise the electronic device of claim 7.

Images