Vehicle start-stop control method and device, storage medium, equipment and vehicle

Abstract

The application provides a vehicle start-stop control method and device, a storage medium, equipment and a vehicle, and relates to the technical field of unmanned driving. The method comprises the following steps: in response to a vehicle start-stop control instruction, passenger motion state data and sitting posture stability state data of each passenger in a vehicle to be controlled are acquired in real time; according to the passenger motion state data, posture recognition is performed on each passenger in the vehicle to be controlled to obtain a passenger posture recognition result; based on the passenger posture recognition result, action prediction is performed on each passenger in the vehicle to be controlled to obtain a passenger action prediction result; and based on the passenger action prediction result and the sitting posture stability state data, the speed of the vehicle to be controlled is controlled to perform start-stop control on the vehicle to be controlled. Through the application, the passenger posture is analyzed in real time, and an immediate response is made according to the change, so that the delay that may occur during manual operation is reduced, the response speed and start-stop efficiency of the vehicle are improved, and automatic start-stop control of the vehicle is realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned driving, and in particular to a vehicle start-stop control method and device, a storage medium, an equipment and a vehicle. BACKGROUND

[0002] In most traditional sightseeing vehicle systems, start-stop control is manually operated by a driver or an in-vehicle staff, usually through a button, a remote control or an in-vehicle operation panel to start or stop the vehicle. In the early application of unmanned sightseeing vehicles, the manual start-stop system is still used in some relatively simple environments, such as scenic parks, museums, zoos and other places. These environments usually require the vehicle to stop at different stations to facilitate passengers to get on and off the vehicle.

[0003] For the operator, the manual start-stop method is relatively simple, and does not require complex algorithms and sensors to monitor the passenger state, but only needs to judge the passenger's getting on and off the vehicle according to the vision and control the vehicle start-stop as needed. However, the manual start-stop system depends on the reaction speed of the operator, and usually when the passenger stands up to get off or get on the vehicle, the operator needs to control the vehicle start-stop through artificial observation and manual operation. This manual response may cause delay, especially in the case of frequent passenger changes or high vehicle speed, it is difficult to respond in time, which may cause safety hazards. SUMMARY

[0004] The technical problem to be solved by the present application is to provide a vehicle start-stop control method, device, storage medium, equipment and vehicle to solve the above technical problems.

[0005] The technical solution of the present application to solve the above technical problems is as follows: a vehicle start-stop control method, comprising: in response to a vehicle start-stop control instruction, acquiring passenger motion state data and sitting posture stability state data of each passenger in a to-be-controlled vehicle in real time; performing posture recognition on each passenger in the to-be-controlled vehicle according to the passenger motion state data to obtain a passenger posture recognition result; performing action prediction on each passenger in the to-be-controlled vehicle based on the passenger posture recognition result to obtain a passenger action prediction result, the passenger action prediction result being used to represent an action intention of each passenger in the to-be-controlled vehicle at a next time step corresponding to a current time; and controlling a speed of the to-be-controlled vehicle based on the passenger action prediction result and the sitting posture stability state data to perform start-stop control on the to-be-controlled vehicle.

[0006] The beneficial effects of the present application are: the present application carries out posture recognition on each passenger in the vehicle to be controlled by obtaining passenger motion state data corresponding to each passenger, and makes action prediction based on the posture recognition result. Finally, based on the passenger action prediction result and the obtained sitting posture stability state data, the start and stop of the vehicle are controlled. Through the present application, the passenger posture can be analyzed in real time and the response can be made according to the change, the automatic start and stop control of the vehicle is realized, and the response speed and start and stop efficiency of the vehicle are improved.

[0007] Based on the above technical solutions, the present application can also be improved as follows.

[0008] Further, the posture recognition on each passenger in the vehicle to be controlled according to the passenger motion state data to obtain a passenger posture recognition result comprises: obtaining a three-dimensional posture graph corresponding to each passenger in the vehicle to be controlled according to the passenger motion state data; inputting the three-dimensional posture graph corresponding to each passenger in the vehicle to be controlled into a trained action classification model respectively to obtain the passenger posture recognition result, the passenger posture recognition result comprising an action category corresponding to each passenger in the vehicle to be controlled at the current time.

[0009] Further, the action prediction on each passenger in the vehicle to be controlled based on the passenger posture recognition result to obtain a passenger action prediction result comprises: in the case that the passenger posture recognition result includes a preset target action category, obtaining a three-dimensional posture graph sequence corresponding to each passenger in the vehicle to be controlled according to the passenger motion state data, the three-dimensional posture graph sequence comprising a plurality of three-dimensional posture graphs corresponding to the passenger; inputting the three-dimensional posture graph sequence corresponding to each passenger in the vehicle to be controlled into a trained action sequence analysis model respectively to obtain an action intention category result output by the action sequence analysis model; determining the passenger action prediction result according to the action intention category result.

[0010] Further, the speed control of the vehicle to be controlled based on the passenger action prediction result and the sitting posture stability state data to control the start and stop of the vehicle to be controlled comprises: obtaining a vehicle running state of the vehicle to be controlled in real time, the vehicle running state being a start state or a running state; determining a vehicle control strategy according to the passenger action prediction result and the sitting posture stability state data based on the vehicle running state; controlling the speed of the vehicle to be controlled according to the vehicle control strategy to control the start and stop of the vehicle to be controlled.

[0011] Further, the vehicle control strategy is determined based on the vehicle running state, the passenger action prediction result and the sitting posture stability state data, and includes: when the vehicle running state is a starting state, determining whether the action intention of each passenger in the vehicle to be controlled is to get on the vehicle and whether the sitting posture stability state data of each passenger in the vehicle to be controlled meets a preset sitting posture stability condition; in the case that the action intention of each passenger in the vehicle to be controlled is to get on the vehicle and the sitting posture stability state data of each passenger in the vehicle to be controlled meets the preset sitting posture stability condition, the vehicle control strategy includes controlling the vehicle to be controlled to accelerate, so as to control the vehicle to be controlled to start according to the vehicle control strategy.

[0012] Further, the vehicle control strategy is determined based on the vehicle running state, the passenger action prediction result and the sitting posture stability state data, and includes: when the vehicle running state is a starting state, determining whether the action intention of each passenger in the vehicle to be controlled is to get on the vehicle and whether the sitting posture stability state data of each passenger in the vehicle to be controlled meets a preset sitting posture stability condition; in the case that the action intention of each passenger in the vehicle to be controlled is to get on the vehicle and the sitting posture stability state data of each passenger in the vehicle to be controlled meets the preset sitting posture stability condition, the vehicle control strategy includes controlling the vehicle to be controlled to accelerate, so as to control the vehicle to be controlled to start according to the vehicle control strategy.

[0013] To solve the above technical problems, the application further provides a vehicle start-stop control device, which comprises:

[0014] A data acquisition module is configured to acquire passenger motion state data and sitting posture stability state data of each passenger in a vehicle to be controlled in real time in response to a vehicle start-stop control instruction.

[0015] An attitude recognition module is configured to recognize the attitude of each passenger in the vehicle to be controlled based on the passenger motion state data, and obtain a passenger attitude recognition result.

[0016] An action prediction module is configured to predict the action of each passenger in the vehicle to be controlled based on the passenger attitude recognition result, and obtain a passenger action prediction result, which represents the action intention of each passenger in the vehicle to be controlled at a next time step.

[0017] A vehicle control module is configured to control the speed of the vehicle to be controlled based on the passenger action prediction result and the sitting posture stability state data, so as to control the vehicle to be controlled to start and stop.

[0018] To solve the above technical problems, the application further provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute the vehicle start-stop control method.

[0019] To solve the above technical problems, the application further provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the vehicle start-stop control method.

[0020] To solve the above technical problems, the application further provides a vehicle comprising the vehicle start-stop control device. BRIEF DESCRIPTION OF DRAWINGS

[0021] Figure 1 Flowchart of the vehicle start-stop control method of the application;

[0022] Figure 2 Schematic diagram of the vehicle start-stop control device of the application. DETAILED DESCRIPTION

[0023] The principles and features of the application are described below, and the examples are used to explain the application and not to limit the scope of the application.

[0024] With the development of unmanned technology, manual start-stop systems are gradually unsuitable for large-scale and efficient operation requirements. In related technologies, the application scenarios of unmanned sightseeing vehicles gradually expand from single parks to larger scenarios, such as large-scale tourist pickup and drop-off, transportation between multiple parking sites, etc., and manual start-stop is not efficient enough.

[0025] As described above, the manual start-stop system commonly used in the prior art has the following disadvantages:

[0026] 1. In high-frequency start-stop operations, it is difficult for operators to maintain concentration for a long time, which can cause fatigue and affect work efficiency and safety. Especially during peak hours or long-term operation, the safety and accuracy of manual operation will decrease.

[0027] 2. Long-time manual operation can cause driver fatigue, especially in busy stations or scenic areas, drivers may not be able to monitor the actions of each passenger in real time due to fatigue, causing delays in vehicle start or stop, and affecting passenger experience.

[0028] 3. Each unmanned sightseeing vehicle needs to be equipped with a driver or operator to be responsible for the start, acceleration, deceleration, and stop of the vehicle. For large-scale applications, the cost of hiring and training a large number of operators will increase significantly, especially in scenarios such as scenic areas, airports, and parks where multiple sightseeing vehicles need to operate.

[0029] 4. When the driver is tired, distracted or busy with other matters, he may misjudge the passenger's actions, resulting in incorrect operation, such as starting or stopping the vehicle too early or too late, affecting the safety and comfort of passengers.

[0030] 5. Due to the layout or angle limitations of the vehicle, the driver may not be able to fully observe all passengers, especially when there are multiple passengers or the seating layout is complex. There are blind spots in the field of vision, resulting in missing the opportunity for passengers to stand up or sit down.

[0031] In view of this, the present embodiment provides a vehicle start-stop control method, device, storage medium, equipment and vehicle to solve the above technical problems.

[0032] Example 1

[0033] like Figure 1 As shown, this embodiment provides a vehicle start-stop control method, including:

[0034] S101 , in response to a vehicle start / stop control instruction, obtaining passenger motion state data and sitting posture stability state data of each passenger in the vehicle to be controlled in real time.

[0035] A vehicle start-stop control command is a command issued to a vehicle to be controlled to control it to enter an automatic start-stop control state. This can occur after the vehicle is in a stable and safe state of travel, with the vehicle start-stop control command issued to the vehicle's start-stop control system. Alternatively, based on the vehicle's location, the vehicle enters an automatic start-stop control state at a pre-set or real-time determined safe section of road suitable for automatic start-stop control, with the vehicle start-stop control command issued to the vehicle's start-stop control system.

[0036] The passenger's motion state data and sitting posture stability data are both dynamic data acquired in real time. In this embodiment, the passenger motion state data is a depth image captured by a depth camera. A depth camera, such as a Kinect camera, is installed in the vehicle to be controlled to capture the motion state of the passengers inside the vehicle. The sitting posture stability data is a pressure value. A pressure sensor is installed in each seat of the vehicle to be controlled, and the pressure value reflects whether the passenger is sitting firmly.

[0037] S102 : performing posture recognition on each passenger in the vehicle to be controlled based on the passenger motion state data to obtain a passenger posture recognition result.

[0038] Optionally, in an embodiment, the passenger posture recognition based on the passenger motion state data to obtain a passenger posture recognition result comprises: obtaining a three-dimensional posture graph corresponding to each passenger in the vehicle to be controlled based on the passenger motion state data; and inputting the three-dimensional posture graph corresponding to each passenger in the vehicle to be controlled into a trained action classification model respectively to obtain the passenger posture recognition result, wherein the passenger posture recognition result comprises an action category corresponding to each passenger in the vehicle to be controlled at the current time.

[0039] The depth camera can capture depth information in three-dimensional space, and through these information combined with pose estimation algorithm, a three-dimensional posture graph can be generated. Based on existing image processing technology, a three-dimensional posture graph containing all people can be generated, or a separate three-dimensional posture graph for each person can be generated. In this embodiment, a three-dimensional posture graph corresponding to each passenger respectively needs to be generated for a frame of depth image captured by the depth camera. The three-dimensional posture graph is composed of a series of key points (such as shoulders, elbows, wrists, hips, knees and ankles, etc.) and lines connecting these points, which is an image representing the posture of the human body key points.

[0040] For generating a three-dimensional posture graph based on a depth image, a pose detection model can also be constructed to achieve this. Specifically, first, the training data is collected, and the training data is a plurality of depth images. The training data can be obtained by simulating the behavior of passengers in an experimental environment and taking pictures, or a public pose detection dataset such as COCOKeypoints, MPI IDataset, etc. can be used. Depth images under multiple angles and multiple lighting conditions are collected to form training data. For each image, human key points are labeled, including head, shoulder, elbow, knee, etc. The labeled training data and the coordinates of the labeled key points are input into a convolutional neural network (CNN) for training to obtain a pose detection model. The trained pose detection model can extract image features (shape, position, motion state and behavior pattern of the human body, etc.) based on the depth image, perform human key point detection at the feature layer, and output the coordinates of each key point in the image to form a three-dimensional posture graph.

[0041] For training of the action classification model: first, data collection is performed, and images of passenger posture behaviors simulated in an experimental environment are collected by a depth camera, including images under multiple angles and multiple lighting conditions. The training data used for training of the posture detection model described above can also be used. The coordinates of each key point in each image are output to form a three-dimensional posture graph for model training. Each image is labeled to indicate the action category corresponding to the human body in the image. The labeled images are used to train a convolutional neural network to obtain an action classification model. Each image is input to a CNN feature extractor, the CNN extracts spatial features of the posture skeleton, and a fully connected layer outputs an action category.

[0042] The action category represents a category for dividing the posture actions of the passengers, and the action category includes a sitting action, a sitting posture, a standing action, a leaning action, a standing posture, etc., which can be set according to actual conditions.

[0043] S103, based on the passenger posture recognition result, predicting the action of each passenger in the vehicle to be controlled to obtain a passenger action prediction result, the passenger action prediction result being used to represent the action intention of each passenger in the vehicle to be controlled at a next time step.

[0044] Optionally, in an embodiment, based on the passenger posture recognition result, the action of each passenger in the vehicle to be controlled is predicted to obtain a passenger action prediction result, including: in the case where the passenger posture recognition result includes a preset target action category, obtaining a three-dimensional posture graph sequence corresponding to each passenger in the vehicle to be controlled according to the passenger motion state data, the three-dimensional posture graph sequence including multiple frames of three-dimensional posture graphs corresponding to the passenger; inputting the three-dimensional posture graph sequence corresponding to each passenger in the vehicle to be controlled into a trained action sequence analysis model respectively to obtain an action intention category result output by the action sequence analysis model; and determining a passenger action prediction result according to the action intention category result.

[0045] In this embodiment, the preset target action category includes a sitting action, a sitting posture, and a standing action. The sitting action represents the action of a passenger changing from a standing posture to a sitting posture, the sitting posture represents the action of a passenger keeping a sitting posture unchanged, and the standing action represents the action of a passenger changing from a sitting posture to a standing posture.

[0046] According to the passenger motion state data obtained in real time, multiple frames of continuous depth images can be obtained. Through the above method, a three-dimensional posture graph of a passenger is generated according to the depth images. Therefore, a three-dimensional posture graph sequence can be obtained through multiple frames of continuous depth images.

[0047] The action intention category result includes an action intention category corresponding to each passenger in the vehicle to be controlled, and the action intention category includes keeping sitting, walking to a door, walking to another seat, keeping standing, etc., which can be set according to actual conditions. According to the action intention category of each passenger, a corresponding action intention of each passenger is determined. The action intention includes taking a vehicle, getting off a vehicle, changing a seat, etc. When the action intention category is keeping sitting, the corresponding action intention is taking a vehicle, and when the action intention category is walking to a door, the corresponding action intention is getting off a vehicle, which can be adjusted according to actual conditions.

[0048] Specifically, the action sequence analysis model is composed of a CNN and a long short-term memory (LSTM). For training of the action sequence analysis model: videos simulating passenger posture behaviors are collected, three-dimensional posture maps corresponding to each frame of image in each video are generated, and three-dimensional posture map sequences used for model training are obtained. Each three-dimensional posture map sequence is labeled to mark the action intention category of the human body in each three-dimensional posture map sequence. The model is trained through the labeled three-dimensional posture map sequences to obtain the action sequence analysis model.

[0049] After the three-dimensional posture map sequence is input into the action sequence analysis model, the CNN extracts features of each frame of image (uses a convolution kernel to slide on the image to extract features of a local region, such as an edge, a corner point, a contour, etc.). The LSTM captures time sequence information between frames (controls the flow of information through three gates, namely an input gate, a forgetting gate, and an output gate). The LSTM accumulates dynamic change information between frames to generate a global representation of a time sequence. For example, when a passenger stands up, leg key points move up frame by frame, and the LSTM will capture this trend and encode it as a hidden state. Finally, a classification head is connected to output a predicted action intention category.

[0050] In S104, the speed of the vehicle to be controlled is controlled based on the passenger action prediction result and the sitting posture stability state data to control the start and stop of the vehicle to be controlled.

[0051] Optionally, in the embodiments, the control of the speed of the vehicle to be controlled based on the passenger action prediction result and the sitting posture stability state data to control the start and stop of the vehicle to be controlled includes: acquiring a vehicle running state of the vehicle to be controlled in real time, the vehicle running state being a start state or a running state; determining a vehicle control strategy according to the passenger action prediction result and the sitting posture stability state data based on the vehicle running state; and controlling the speed of the vehicle to be controlled according to the vehicle control strategy to control the start and stop of the vehicle to be controlled.

[0052] Specifically, the to-be-started state represents that the to-be-controlled vehicle is in a state of waiting for starting, and the running state represents that the to-be-controlled vehicle is in a running state.

[0053] Optionally, in the embodiment, the vehicle control strategy is determined according to the passenger action prediction result and the sitting posture stability state data based on the vehicle running state, including: when the vehicle running state is the to-be-started state, determining whether the action intention of each passenger in the to-be-controlled vehicle is to get on the vehicle and whether the sitting posture stability state data of each passenger in the to-be-controlled vehicle meets the preset sitting posture stability condition; in the case that the action intention of each passenger in the to-be-controlled vehicle is to get on the vehicle and the sitting posture stability state data of each passenger in the to-be-controlled vehicle meets the preset sitting posture stability condition, the vehicle control strategy includes controlling the to-be-controlled vehicle to accelerate, so as to control the to-be-controlled vehicle to start according to the vehicle control strategy.

[0054] When the to-be-controlled vehicle is in the to-be-started state, it needs to be determined to start, and when all passengers in the vehicle are seated and stable, the vehicle can be controlled to start. Whether the passengers are seated and stable needs to be judged in combination with the action intention and the sitting posture stability state data of the passengers.

[0055] The preset sitting posture stability condition can be a pressure threshold. When the sitting posture stability state data corresponding to the passenger, that is, the pressure value corresponding to the passenger is greater than or equal to the pressure threshold, it is determined that the sitting posture stability state data corresponding to the passenger meets the preset sitting posture stability condition; otherwise, it is determined that the sitting posture stability state data corresponding to the passenger does not meet the preset sitting posture stability condition. The pressure threshold is a pre-set value, which can be set according to experience, experimental data, etc.

[0056] Therefore, by comprehensively considering the action intention and the pressure value, it can be determined whether the passengers are seated and maintain a stable sitting posture. Only when all passengers in the vehicle are seated and stable on the seats, the vehicle can be controlled to start and smoothly accelerate according to the road conditions (for example, whether there is an obstacle in front of the vehicle, the distance to the front vehicle, etc.); otherwise, the vehicle is controlled to remain stationary, and it is continuously determined whether the passengers are seated and stable.

[0057] Optionally, in an embodiment, the vehicle control strategy is determined based on the vehicle operating state, the passenger action prediction result and the sitting posture stability state data, including: when the vehicle operating state is a driving state, determining whether the action intention of one or more passengers in the vehicle to be controlled is to get off, and whether the sitting posture stability state data of the one or more passengers meets the preset seat leaving condition; in the case that the action intention of one or more passengers in the vehicle to be controlled is to get off, and the sitting posture stability state data of the one or more passengers meets the preset seat leaving condition, the vehicle control strategy includes controlling the vehicle to be controlled to decelerate, determine the parking position and the parking time, so as to control the vehicle to be controlled to park according to the vehicle control strategy.

[0058] When the vehicle to be controlled is in a driving state, parking determination is needed. When there are passengers in the vehicle who want to get off, the vehicle can be controlled to decelerate and stop in the target parking area, so that the passengers who want to get off can get off. When there are passengers in the vehicle whose action intention is to get off and whose sitting posture stability state data meets the preset seat leaving condition, the vehicle to be controlled is controlled to park and stop in the target parking area. Moreover, the degree of brake control can be calculated according to the sign of the parking area and the current vehicle speed. During parking, the system reaction time and the additional time required by the passenger behavior need to be considered to ensure that the vehicle can be safely parked within the parking range.

[0059] The preset seat leaving condition can be a pressure threshold. When the sitting posture stability state data corresponding to the passenger, i.e., the pressure value corresponding to the passenger, is less than the pressure threshold, it is determined that the sitting posture stability state data corresponding to the passenger meets the preset seat leaving condition; otherwise, it is determined that the sitting posture stability state data corresponding to the passenger does not meet the preset seat leaving condition. Generally, the pressure threshold of the seat leaving condition is the same as the pressure threshold of the sitting posture stability condition.

[0060] A depth camera and a pressure sensor are installed in the vehicle, and an embedded computing platform is installed. The image data collected by the depth camera and the pressure value collected by the pressure sensor are processed in real time by the embedded computing platform, and the start, acceleration, deceleration or parking of the vehicle is controlled by the above method.

[0061] Through this method, automatic start and stop control of the vehicle is achieved. It can analyze the passenger's posture in real time and respond immediately to changes, reducing the delay that may occur during manual operation and improving the vehicle's response speed and start-stop efficiency. It can accurately control the start and stop of the vehicle based on the passenger's movement intentions and sitting posture stability data, avoiding discomfort to passengers caused by sudden starts or stops. In addition, the camera and sensor can fully scan all passengers in the car without being restricted by the field of view, and there will be no blind spots that the driver cannot observe. This method is particularly important for the large-scale application of sightseeing vehicles in high-traffic areas such as popular attractions and airports. It can continuously provide consistent start-stop services and ensure operational efficiency. Even in large-scale applications where multiple vehicles are running at the same time, there is no need to increase staffing, saving a lot of human resources and related expenses. A one-time investment in automation equipment can meet the control needs of large quantities of sightseeing vehicles.

[0062] Example 2

[0063] like Figure 2 As shown, this embodiment provides a vehicle start-stop control device 200, including:

[0064] The data acquisition module 201 is used to obtain the passenger motion state data and sitting posture stability state data of each passenger in the vehicle to be controlled in real time in response to the vehicle start-stop control command;

[0065] A posture recognition module 202 is configured to perform posture recognition on each passenger in the vehicle to be controlled based on the passenger motion state data to obtain a passenger posture recognition result;

[0066] The motion prediction module 203 is configured to perform motion prediction for each passenger in the vehicle to be controlled based on the passenger posture recognition result, and obtain a passenger motion prediction result, wherein the passenger motion prediction result is used to represent the motion intention of each passenger in the vehicle to be controlled at the next time step at the current moment;

[0067] The vehicle control module 204 is configured to control the speed of the vehicle to be controlled based on the passenger motion prediction result and the sitting posture stability state data, so as to perform start-stop control on the vehicle to be controlled.

[0068] Optionally, in an embodiment, the gesture recognition module 202 includes:

[0069] an image generating unit, configured to obtain a three-dimensional posture image corresponding to each passenger in the vehicle to be controlled based on the passenger motion state data;

[0070] The posture recognition unit is configured to input a three-dimensional posture graph corresponding to each passenger in the to-be-controlled vehicle into a trained action classification model to obtain a passenger posture recognition result, and the passenger posture recognition result includes an action category corresponding to each passenger in the to-be-controlled vehicle at a current time.

[0071] Optionally, in some embodiments, the action prediction module 203 includes:

[0072] The image processing unit is configured to, when the passenger posture recognition result includes a preset target action category, acquire a three-dimensional posture graph sequence corresponding to each passenger in the to-be-controlled vehicle according to the passenger motion state data, and the three-dimensional posture graph sequence includes a plurality of three-dimensional posture graphs corresponding to the passenger.

[0073] The action prediction unit is configured to input the three-dimensional posture graph sequence corresponding to each passenger in the to-be-controlled vehicle into a trained action sequence analysis model to obtain an action intention category result output by the action sequence analysis model.

[0074] The result generation unit is configured to determine a passenger action prediction result according to the action intention category result.

[0075] Optionally, in some embodiments, the vehicle control module 204 includes:

[0076] The state acquisition unit is configured to acquire a vehicle running state of the to-be-controlled vehicle in real time, and the vehicle running state is a to-be-started state or a driving state.

[0077] The strategy acquisition unit is configured to determine a vehicle control strategy according to the passenger action prediction result and the sitting posture stability state data based on the vehicle running state.

[0078] The vehicle control unit is configured to control a speed of the to-be-controlled vehicle according to the vehicle control strategy to perform start-stop control on the to-be-controlled vehicle.

[0079] Optionally, in some embodiments, the strategy acquisition unit includes:

[0080] The first judgment subunit is configured to, when the vehicle running state is the to-be-started state, determine whether an action intention corresponding to each passenger in the to-be-controlled vehicle is to take the vehicle and whether the sitting posture stability state data corresponding to each passenger in the to-be-controlled vehicle satisfies a preset sitting posture stability condition.

[0081] The first strategy obtaining sub-unit is configured to, in a case where the action intention corresponding to each passenger in the vehicle to be controlled is to take the vehicle and the sitting posture stable state data corresponding to each passenger in the vehicle to be controlled satisfies a preset sitting posture stable condition, the vehicle control strategy comprises controlling the vehicle to be controlled to accelerate, so as to control the vehicle to be controlled to start according to the vehicle control strategy.

[0082] Optionally, in an embodiment, the strategy obtaining unit comprises:

[0083] The second judgment sub-unit is configured to, when the vehicle running state is a driving state, determine whether the action intention corresponding to one or more passengers in the vehicle to be controlled is to get off the vehicle and whether the sitting posture stable state data corresponding to the one or more passengers satisfies a preset off-seat condition.

[0084] The second strategy obtaining sub-unit is configured to, in a case where the action intention corresponding to one or more passengers in the vehicle to be controlled is to get off the vehicle and the sitting posture stable state data corresponding to the one or more passengers satisfies a preset off-seat condition, the vehicle control strategy comprises controlling the vehicle to be controlled to decelerate, determining a parking position and a parking time, so as to control the vehicle to be controlled to park according to the vehicle control strategy.

[0085] Embodiment three

[0086] The embodiment provides a non-transitory computer readable storage medium storing computer instructions for causing a computer to execute the vehicle start-stop control method in the embodiment one.

[0087] Embodiment four

[0088] The embodiment provides an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the vehicle start-stop control method in the embodiment one when executing the computer program.

[0089] Embodiment five

[0090] The embodiment provides a vehicle comprising the vehicle start-stop control device in the embodiment two.

[0091] In the description of the specification, the description of the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are contained in at least one embodiment or example of the present application. In the specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any suitable manner in any one or more embodiments or examples. In addition, the person skilled in the art can combine and combine the different embodiments or examples described in the specification and the features of the different embodiments or examples without contradiction.

[0092] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and the person skilled in the art can make changes, modifications, replacements and variations to the above-described embodiments within the scope of the present application.

Claims

1. A vehicle start-stop control method characterized by comprising: The method comprises: obtaining passenger motion state data and seat posture stability state data of each passenger in the vehicle to be controlled in real time in response to a vehicle start-stop control instruction, wherein the seat posture stability state data is a pressure value output by a pressure sensor installed in a seat of the vehicle to be controlled; performing posture recognition on each passenger in the vehicle to be controlled according to the passenger motion state data to obtain a passenger posture recognition result; performing action prediction on each passenger in the vehicle to be controlled based on the passenger posture recognition result to obtain a passenger action prediction result, wherein the passenger action prediction result is used to represent an action intention of each passenger in the vehicle to be controlled at a next time step corresponding to a current time; controlling a speed of the vehicle to be controlled based on the passenger action prediction result and the seat posture stability state data to perform start-stop control on the vehicle to be controlled; the controlling of the speed of the vehicle to be controlled based on the passenger action prediction result and the seat posture stability state data to perform start-stop control on the vehicle to be controlled comprises: obtaining a vehicle running state of the vehicle to be controlled in real time, wherein the vehicle running state is a start-ready state or a driving state; determining a vehicle control strategy based on the vehicle running state, the passenger action prediction result and the seat posture stability state data; controlling the speed of the vehicle to be controlled according to the vehicle control strategy to perform start-stop control on the vehicle to be controlled; the determining of the vehicle control strategy based on the vehicle running state, the passenger action prediction result and the seat posture stability state data comprises: when the vehicle running state is the start-ready state, determining whether an action intention of each passenger in the vehicle to be controlled is to get on the vehicle and whether a seat posture stability state data corresponding to each passenger in the vehicle to be controlled satisfies a preset seat posture stability condition; when the action intention of each passenger in the vehicle to be controlled is to get on the vehicle and the seat posture stability state data corresponding to each passenger in the vehicle to be controlled satisfies the preset seat posture stability condition, the vehicle control strategy comprises controlling the vehicle to be controlled to accelerate so as to perform start control on the vehicle to be controlled according to the vehicle control strategy; the determining of the vehicle control strategy based on the vehicle running state, the passenger action prediction result and the seat posture stability state data comprises: when the vehicle running state is the driving state, determining whether an action intention of one or more passengers in the vehicle to be controlled is to get off the vehicle and whether a seat posture stability state data corresponding to the one or more passengers satisfies a preset seat leaving condition; when the action intention of the one or more passengers in the vehicle to be controlled is to get off the vehicle and the seat posture stability state data corresponding to the one or more passengers satisfies the preset seat leaving condition, the vehicle control strategy comprises controlling the vehicle to be controlled to decelerate, determining a parking position and a parking time so as to perform parking control on the vehicle to be controlled according to the vehicle control strategy.

2. The vehicle start-stop control method according to claim 1, characterized by, The passenger posture recognition result includes a corresponding action category of each passenger in the to-be-controlled vehicle at a current time. The passenger posture recognition result includes a corresponding action category of each passenger in the to-be-controlled vehicle at a current time. The passenger posture recognition result includes a corresponding action category of each passenger in the to-be-controlled vehicle at a current time.

3. The vehicle start-stop control method according to claim 1, characterized by, The passenger posture recognition result includes a corresponding action category of each passenger in the to-be-controlled vehicle at a current time. The passenger posture recognition result includes a corresponding action category of each passenger in the to-be-controlled vehicle at a current time. The data acquisition module is configured to acquire passenger motion state data and sitting posture stability state data of each passenger in a to-be-controlled vehicle in real time in response to a vehicle start-stop control instruction; the sitting posture stability state data is a pressure value output by a pressure sensor installed in a seat of the to-be-controlled vehicle; The posture recognition module is configured to perform posture recognition on each passenger in the to-be-controlled vehicle according to the passenger motion state data, to obtain a passenger posture recognition result.

4. A vehicle start-stop control device characterized by comprising: The action prediction module is configured to perform action prediction on each passenger in the to-be-controlled vehicle based on the passenger posture recognition result, to obtain a passenger action prediction result, which represents an action intention of each passenger in the to-be-controlled vehicle at a next time step at a current time. The vehicle control module is configured to control a speed of the to-be-controlled vehicle based on the passenger action prediction result and the sitting posture stability state data, to perform start-stop control on the to-be-controlled vehicle. The vehicle control module includes: The state acquisition unit is configured to acquire a vehicle running state of the to-be-controlled vehicle in real time, the vehicle running state being a to-be-started state or a driving state. The strategy acquisition unit is configured to determine a vehicle control strategy based on the vehicle running state, the passenger action prediction result, and the sitting posture stability state data. The vehicle control unit is configured to control the speed of the to-be-controlled vehicle according to the vehicle control strategy, to perform start-stop control on the to-be-controlled vehicle. The strategy acquisition unit includes: The first judgment subunit is configured to determine whether an action intention of each passenger in the to-be-controlled vehicle is to take the vehicle and whether the sitting posture stability state data of each passenger in the to-be-controlled vehicle satisfies a preset sitting posture stability condition when the vehicle running state is the to-be-started state. ​ ​ ​ The first strategy obtaining subunit is configured to, when the action intention corresponding to each passenger in the to-be-controlled vehicle is to take the vehicle, and the sitting posture stable state data corresponding to each passenger in the to-be-controlled vehicle satisfies a preset sitting posture stable condition, the vehicle control strategy comprises controlling the to-be-controlled vehicle to accelerate, so as to control the to-be-controlled vehicle to start according to the vehicle control strategy. The strategy obtaining unit comprises: The second judgment subunit is configured to, when the vehicle running state is a driving state, determine whether the action intention corresponding to one or more passengers in the to-be-controlled vehicle is to get off the vehicle, and whether the sitting posture stable state data corresponding to the one or more passengers satisfies a preset leaving seat condition; The second strategy obtaining subunit is configured to, when the action intention corresponding to one or more passengers in the to-be-controlled vehicle is to get off the vehicle, and the sitting posture stable state data corresponding to the one or more passengers satisfies the preset leaving seat condition, the vehicle control strategy comprises controlling the to-be-controlled vehicle to decelerate, determining a parking position and a parking time, so as to control the to-be-controlled vehicle to park according to the vehicle control strategy.

5. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are configured to cause a computer to execute the vehicle start-stop control method according to any one of claims 1 to 3.

6. An electronic device, comprising: The vehicle start-stop control device comprises a memory, a processor, and computer programs stored in the memory and executable on the processor, and the processor executes the computer programs to implement the vehicle start-stop control method according to any one of claims 1 to 3.

7. A vehicle characterized by comprising: The vehicle start-stop control device according to claim 4.

Images