Method for controlling braking force of vehicle based on behavior data of driver
By combining cameras and sensors to collect data in the vehicle, calculating the hazard coefficient for real-time braking operations, the problem of misbraking and excessive braking force is solved, the driving experience and practice efficiency is improved, and a safer braking solution is provided.
Patent Information
- Application Number
- CN202411229788.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the prior art, the vehicle braking system is prone to problems such as erroneous brakes or excessive braking force, which leads to a decrease in the driving experience of students and affects the practice progress, and causes losses to the vehicle brake device.
By installing a camera in the car to collect driver behavior data and object data around the vehicle, combining image recognition algorithms and sensor data, the hazard coefficient is calculated, and the brake system is dispatched in real time for emergency or point brake braking.
Reduce the impact of misbraking and excessive braking force, improves the safety and accuracy of braking, and improves the driving experience and practice efficiency of students.
Smart Images

Figure CN119078759A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of automatic driving, and in particular to a method for controlling the braking force of a vehicle. Background Art
[0002] Driving a vehicle requires certain driving skills. If a person who lacks such skills drives a vehicle at will, a traffic accident may occur, so the driver needs to receive corresponding skills training. With the development of society, the number of people obtaining a driver's license is increasing, and safety is an important topic in the process of obtaining a driver's license. When students practice in the initial stage of training, they are not proficient in vehicle control and have weak spatial perception, which leads to dangerous situations such as collisions. At present, there is technology that can detect obstacle data and brake, but false braking often occurs, which reduces the driving experience of students and affects the progress of the entire driving test.
[0003] The current solution is to detect surrounding obstacle data through radar and positioning devices installed on the vehicle body and perform safe braking. However, the actual results of safe braking often result in misidentification, for example: false braking caused by a malfunction or temporary abnormality of the radar or positioning device, or the trainee being close to an obstacle and mistakenly believing that the trainee will crash into the obstacle and brake. This not only causes the trainee's driving experience to deteriorate, but frequent false braking will directly affect the trainee's practice progress and cause certain damage to the vehicle's braking device.
[0004] Therefore, the prior art urgently needs a vehicle braking control method that is safe and has a low false alarm rate. Summary of the invention
[0005] In order to solve one of the problems in the prior art, the present invention provides a method for controlling vehicle braking force based on driver behavior data, comprising the following steps:
[0006] S1. Take photos of the driver's driving behavior through the camera installed in the car;
[0007] S2. Upload the collected driver behavior photos to the server, perform image recognition algorithm calculations, and annotate the calculation results;
[0008] S3, taking photos of objects around the vehicle through the camera installed on the vehicle body;
[0009] S4, uploading the collected photos of objects around the vehicle to the server, performing image recognition algorithm calculation, and marking the calculation results;
[0010] S5. The sensors installed on the vehicle collect vehicle data and upload it to the server;
[0011] S6. The result obtained by the image recognition algorithm is combined with the data uploaded by the sensor to perform algorithm calculation to calculate the current driving risk factor, which is marked with numbers. Different numbers represent different braking forces and voice broadcasts.
[0012] S7. The identified risk factor is sent to the brake system in real time, and the brake system performs braking operations according to the risk factor.
[0013] Furthermore, the image recognition algorithm in step S2 determines one or more of the student's head posture during driving, and the student's steering angle and / or strength;
[0014] Furthermore, the head posture specifically refers to whether the head is looking forward, left or right.
[0015] Further, in step S4: one or more of the distance and orientation of vehicles and / or obstacles and / or people around the vehicle and the vehicle are determined by an image recognition algorithm;
[0016] Furthermore, the sensors in step S5 include one or more of a GPS locator, a gear sensor, a radar sensor, a steering wheel sensor, a clutch sensor, a brake sensor, a throttle sensor, and an OBD information extraction device, wherein the GPS locator, the gear sensor, the radar sensor, the steering wheel sensor, the clutch sensor, the brake sensor, the throttle sensor, and the OBD information extraction device respectively collect the GPS coordinates of the subject location, the gear information of the vehicle, the distance to the obstacle, the steering angle, the clutch position information, the brake position information, the throttle position information, and the current vehicle speed value.
[0017] Furthermore, the danger system is 0, which means emergency braking and the vehicle cannot continue to drive; the danger system is 1, which means deep braking and the vehicle can continue to drive; the danger system is 2, which means light braking; the danger system is 3, which means no braking is required.
[0018] Furthermore, the specific logic of the image recognition algorithm in step S6 is:
[0019] When the image detects that the driver has not looked forward for a long time, the image detects that there is an obstacle in front of the car, and the sensor detects that the car is moving, the risk factor is judged to be 0;
[0020] When the image detects that the driver is looking forward, the image detects that the driver is turning the steering wheel, the image detects that the obstacle ahead is close, the sensor does not detect the brake pedal data, and the sensor detects that the vehicle speed is too fast, the risk factor is judged to be 1;
[0021] When the image detects that the driver is looking forward, the image detects that the driver is turning, the image detects that the obstacle ahead is far away and the vehicle speed is fast, and the sensor does not detect brake pedal data, the risk factor is judged to be 2;
[0022] When the image detects that the driver is looking forward and the image detects that the steering wheel angle is positive and the image detects no obstacles around or the distance is far and the sensor detects that the vehicle speed is slow and the sensor detects that the accelerator is stepped on hard, the risk factor is judged to be 3.
[0023] The method provided by the present invention for controlling the braking force of a vehicle based on driver behavior data performs algorithmic calculations through image recognition technology combined with practice data collected by sensors, determines the risk factor, and then performs corresponding emergency braking or point braking, which solves the technical problems existing in the prior art and reduces the impact of false braking or excessive braking force on trainees' practice. The safe braking scheme is more complete, making up for the shortcomings of safe braking brought by only sensors and positioning, solving the impact of false braking and excessive braking depth on trainees' driving experience, and making driving training faster and more efficient. BRIEF DESCRIPTION OF THE DRAWINGS
[0024] In order to more clearly illustrate the technical solutions in the specific implementation manner of the present invention, the drawings required for use in the specific implementation manner or the description of the prior art will be briefly introduced below.
[0025] Figure 1 It is a flow chart of the method disclosed in the embodiment of the first aspect of the present invention.
[0026] Figure 2 It is a specific flow chart of the method disclosed in the embodiment of the first aspect of the present invention. DETAILED DESCRIPTION
[0027] The structure and operation of the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the accompanying drawings are provided only for a better understanding of the present invention and should not be construed as limiting the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0028] In the description of the present invention, it should be noted that, if the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, if the terms "first" and "second" appear, they are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0029] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0030] Example 1
[0031] Combination Figure 1 to Figure 2 The present invention provides a method for controlling vehicle braking force based on driver behavior data, comprising the following steps:
[0032] S1. Take photos of the driver's driving behavior through the camera installed in the car;
[0033] S2. Upload the collected driver behavior photos to the server, perform image recognition algorithm calculations, and annotate the calculation results;
[0034] S3, taking photos of objects around the vehicle through the camera installed on the vehicle body;
[0035] S4, uploading the collected photos of objects around the vehicle to the server, performing image recognition algorithm calculation, and marking the calculation results;
[0036] S5. The sensors installed on the vehicle collect vehicle data and upload it to the server;
[0037] S6. The result obtained by the image recognition algorithm is combined with the data uploaded by the sensor to perform algorithm calculation to calculate the current driving risk factor, which is marked with numbers. Different numbers represent different braking forces and voice broadcasts.
[0038] S7. The identified risk factor is sent to the brake system in real time, and the brake system performs braking operations according to the risk factor.
[0039] Specifically, the image recognition algorithm in step S2 determines one or more of the student's head posture during driving and the student's steering angle and / or strength;
[0040] Specifically, head posture refers to whether the head is looking forward, left or right.
[0041] Specifically, in step S4: one or more of the distance and orientation of vehicles and / or obstacles and / or people around the vehicle and the vehicle are determined by an image recognition algorithm;
[0042] Specifically, the sensors in step S5 include one or more of a GPS locator, a gear sensor, a radar sensor, a steering wheel sensor, a clutch sensor, a brake sensor, a throttle sensor, and an OBD information extraction device, wherein the GPS locator, the gear sensor, the radar sensor, the steering wheel sensor, the clutch sensor, the brake sensor, the throttle sensor, and the OBD information extraction device respectively collect the GPS coordinates of the subject location, the gear information of the vehicle, the distance to the obstacle, the steering angle, the clutch position information, the brake position information, the throttle position information, and the current vehicle speed value.
[0043] Specifically, a danger system of 0 represents emergency braking and the vehicle cannot continue to drive; a danger system of 1 represents deep braking and the vehicle can continue to drive; a danger system of 2 represents light braking; and a danger system of 3 represents no braking required.
[0044] Specifically, the specific logic of the image recognition algorithm in step S6 is:
[0045] When the image detects that the driver has not looked forward for a long time, the image detects that there is an obstacle in front of the car, and the sensor detects that the car is moving, the risk factor is judged to be 0;
[0046] When the image detects that the driver is looking forward, the image detects that the driver is turning the steering wheel, the image detects that the obstacle ahead is close, the sensor does not detect the brake pedal data, and the sensor detects that the vehicle speed is too fast, the risk factor is judged to be 1;
[0047] When the image detects that the driver is looking forward, the image detects that the driver is turning, the image detects that the obstacle ahead is far away and the vehicle speed is fast, and the sensor does not detect brake pedal data, the risk factor is judged to be 2;
[0048] When the image detects that the driver is looking forward and the image detects that the steering wheel angle is positive and the image detects no obstacles around or the distance is far and the sensor detects that the vehicle speed is slow and the sensor detects that the accelerator is stepped on hard, the risk factor is judged to be 3.
[0049] It is understandable that the above specific logic is only an example, and other specific logic can be set according to actual conditions and needs.
[0050] The present invention can achieve the following technical effects: by performing algorithm calculations with image recognition technology combined with the practice data collected by sensors, the risk factor is determined, and then corresponding emergency braking or point braking is performed, which solves the technical problems existing in the prior art and reduces the impact of false braking or excessive braking force on trainees' practice. The safe braking scheme is more complete, making up for the shortcomings of safe braking brought by sensors and positioning alone, solving the impact of false braking and excessive braking depth on trainees' driving experience, and making driving training faster and more efficient.
[0051] The above embodiments are only used to illustrate the present invention, wherein the structure, connection method and manufacturing process of each component may be changed. Any equivalent transformations and improvements based on this technical solution should not be excluded from the protection scope of the present invention.
Claims
1. A method for controlling vehicle braking force based on driver behavior data, characterized in that: The following steps are involved: S1. Take photos of the driver's driving behavior through the camera installed in the car; S2. Upload the collected driver behavior photos to the server, perform image recognition algorithm calculations, and annotate the calculation results; S3, taking photos of objects around the vehicle through the camera installed on the vehicle body; S4, uploading the collected photos of objects around the vehicle to the server, performing image recognition algorithm calculation, and marking the calculation results; S5. The sensors installed on the vehicle collect vehicle data and upload it to the server; S6. The result obtained by the image recognition algorithm is combined with the data uploaded by the sensor to perform algorithm calculation to calculate the current driving risk factor, which is marked with numbers. Different numbers represent different braking forces and voice broadcasts. S7. The identified risk factor is sent to the brake system in real time, and the brake system performs braking operations according to the risk factor.
2. The method according to claim 1, characterized in that: The image recognition algorithm in step S2 determines one or more of the student's head posture during driving and the student's steering angle and / or strength.
3. The method according to claim 2, characterized in that: Head posture specifically refers to whether the head is looking forward, left, or right.
4. The method according to claim 1, characterized in that: In step S4: one or more of the distance and direction between the vehicles and / or obstacles and / or people around the vehicle and the vehicle are determined by an image recognition algorithm.
5. The method according to claim 1, characterized in that: The sensors in step S5 include one or more of a GPS locator, a gear sensor, a radar sensor, a steering wheel sensor, a clutch sensor, a brake sensor, a throttle sensor, and an OBD information extraction device, wherein the GPS locator, the gear sensor, the radar sensor, the steering wheel sensor, the clutch sensor, the brake sensor, the throttle sensor, and the OBD information extraction device respectively collect GPS coordinates of the subject location, vehicle gear information, distance to obstacles, steering angle, clutch position information, brake position information, throttle position information, and current vehicle speed value.
6. The method according to claim 1, characterized in that: The danger system is 0, which means emergency braking and the vehicle cannot continue to drive; the danger system is 1, which means deep braking and the vehicle can continue to drive; the danger system is 2, which means light braking; the danger system is 3, which means no braking is required.
7. The method according to claim 6, characterized in that: the specific logic of the image recognition algorithm in step S6 is: When the image detects that the driver has not looked forward for a long time, the image detects that there is an obstacle in front of the car, and the sensor detects that the car is moving, the risk factor is judged to be 0; When the image detects that the driver is looking forward, the image detects that the driver is turning the steering wheel, the image detects that the obstacle ahead is close, the sensor does not detect the brake pedal data, and the sensor detects that the vehicle speed is too fast, the risk factor is judged to be 1; When the image detects that the driver is looking forward, the image detects that the driver is turning, the image detects that the obstacle ahead is far away and the vehicle speed is fast, and the sensor does not detect brake pedal data, the risk factor is judged to be 2; When the image detects that the driver is looking forward and the image detects that the steering wheel angle is positive and the image detects no obstacles around or the distance is far and the sensor detects that the vehicle speed is slow and the sensor detects that the accelerator is stepped on hard, the risk factor is judged to be 3.
Citation Information
Patent Citations
Driving danger coefficient assessment method and device based on multi-modal information
CN107180219A
Safety braking system applied to driver training coach car
CN113954795A
Dangerous driving management and control method and system based on multi-feature fusion
CN116572984A
Safe driving behavior detection method fusing multi-source data
CN117313034A
Dangerous status alarming device
JP1994215300A
