Intelligent vehicle auxiliary driving and supervision method

Abstract

The invention provides an intelligent vehicle auxiliary driving and supervision method. The method comprises the steps that a longitudinal distance detection element and a transverse distance detection element are controlled to conduct obstacle detection on the advancing direction of a vehicle, and the relative movement trend of the vehicle and an obstacle is speculated; determining the collision probability of the vehicle and the obstacle, formulating a corresponding auxiliary obstacle avoidance scheme for the vehicle, transmitting the auxiliary obstacle avoidance scheme to a display screen for display, deducing the real-time driving risk of the vehicle according to the real-time obstacle avoidance information of the vehicle, analyzing a plurality of obstacle avoidance defects in the obstacle avoidance process, generating a risk report when the vehicle arrives at the destination, and displaying the risk report. According to the invention, a driver is assisted to identify and judge whether a small obstacle on a road surface collides with a vehicle, corresponding obstacle avoidance assistance is performed, and obstacle avoidance resuming is performed after obstacle avoidance is completed, so that the driver can be assisted to complete obstacle avoidance work and smoothly arrive at a destination, and the driver can have a good driving habit through long-term matching and correction.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle auxiliary obstacle avoidance, and particularly relates to an intelligent vehicle auxiliary driving and supervision method. Background Art

[0002] With the rapid development of technology, more and more families have purchased commuter cars, which has improved happiness and the quality of life. However, this has also led to an increasing number of vehicles on the road. To avoid collisions with other vehicles or road obstacles, resulting in casualties or economic losses, drivers are required to concentrate highly and constantly observe the surrounding environment while driving. This causes some drivers to be mentally tense for a long time, which is harmful to their bodies. In severe cases, it will affect the driver's reaction ability, causing problems such as dizziness and slow reaction. Moreover, the driver's long-tense nerves are likely to overlook small obstacles on the road surface, or mistake small obstacles on the road surface for dangerous obstacles due to dizziness, unconsciously performing braking actions that affect the progress of the following vehicle, and even causing accidents. Therefore, there is an urgent need for a technology that can assist drivers in identifying and judging whether small obstacles on the road surface will collide with the vehicle.

[0003] Therefore, the present invention provides an intelligent vehicle auxiliary driving and supervision method. Summary of the Invention

[0004] An intelligent vehicle auxiliary driving and supervision method of the present invention can assist a driver in identifying and judging whether a small obstacle on the road surface will collide with the vehicle, and make corresponding obstacle avoidance assistance and conduct an obstacle avoidance review after completing the obstacle avoidance. It can not only assist the driver in completing the obstacle avoidance work and reaching the destination smoothly, but also enable the driver to develop a good driving habit through long-term calibration.

[0005] The present invention provides an intelligent vehicle auxiliary driving and supervision method, including:

[0006] Step 1: When the vehicle is driving, control the longitudinal distance detection element and the lateral distance detection element to detect obstacles in the forward direction of the vehicle;

[0007] Step 2: When an obstacle is detected, infer the relative motion trend between the vehicle and the obstacle, simulate the intended forward route of the vehicle, and determine the collision probability between the vehicle and the obstacle;

[0008] Step 3: Based on the collision probability, formulate a corresponding auxiliary obstacle avoidance plan for the vehicle and transmit it to the display screen of the vehicle for display;

[0009] Step 4: Derive the real-time driving risk of the vehicle based on the real-time obstacle avoidance information of the vehicle, analyze several shortcomings in the current obstacle avoidance process, and generate and display a risk report when the vehicle reaches the destination.

[0010] In an implementable manner,

[0011] Step 1 includes:

[0012] Step 11: When the vehicle is moving, obtain the parallel detection information collected by the longitudinal distance detection element of the vehicle and the vertical detection information collected by the lateral distance detection element, perform an overlapping process on the parallel detection information and the vertical detection information to obtain several detection intersection information;

[0013] Step 12: Construct a detection grid of the vehicle according to the positional relationship between different detection intersection information, identify the image contours included in each sub-grid in the detection grid, construct several detection contours of the detection grid, and use AI to respectively identify the item attributes corresponding to each detection contour;

[0014] Step 13: Screen the target detection contours belonging to the obstacle attribute, locate the target contours in the detection grid, and when the obstacle corresponding to the target contour is in the same direction as the forward direction of the vehicle, perform a first mark on the obstacle, otherwise perform a second mark on the obstacle.

[0015] In an implementable manner,

[0016] It further includes:

[0017] When there is no obstacle in the forward direction of the vehicle, give a cautious lane change reminder to the driver according to the second mark.

[0018] In an implementable manner,

[0019] Step 2 includes:

[0020] Step 21: When there is an obstacle in the forward direction of the vehicle, identify the obstacle movement characteristics of the obstacle, collect the current driving data of the vehicle to construct the vehicle movement characteristics of the vehicle, and construct the relative movement trend between the vehicle and the obstacle according to the obstacle movement characteristics and the vehicle movement characteristics;

[0021] Step 22: Lock the driving position of the vehicle according to the current driving data corresponding to the vehicle at different times, determine the current lane and current road conditions of the vehicle to derive the intended forward route of the vehicle, and determine the collision position between the vehicle and the obstacle according to the relative movement trend and mark it in the preset space;

[0022] Step 23: Construct a corresponding virtual vehicle according to the appearance parameters of the vehicle, control the virtual vehicle in the preset space to simulate the intended forward route, determine the distance change characteristics between the vehicle and the obstacle, and generate the collision probability between the vehicle and the obstacle according to a number of distance values included in the distance change characteristics.

[0023] In an implementable manner,

[0024] It further includes:

[0025] Obtain the short-term operation information of the driver on the vehicle, evaluate the rationality of the intended forward route according to the short-term operation information, and when the intended forward route is unreasonable, adjust the intended forward route of the vehicle according to the short-term operation information.

[0026] In an implementable manner,

[0027] The said step 3 includes:

[0028] Step 31: When the collision probability is higher than the specified probability, determine a number of suspected collision positions between the vehicle and the obstacle, determine the remaining obstacle avoidance duration of the vehicle according to the current lane and current road conditions of the vehicle, and determine the remaining obstacle avoidance distance and the position to be avoided of the vehicle according to the suspected collision positions;

[0029] Step 32: Determine the adjustable range of the vehicle according to the road condition information, simulate the vehicle to perform iterative adjustment within the adjustable range, obtain a number of preliminary obstacle avoidance plans for the vehicle, and use the remaining obstacle avoidance duration to train each preliminary obstacle avoidance plan respectively to obtain the obstacle avoidance effectiveness corresponding to each preliminary obstacle avoidance plan;

[0030] Step 33: Screen the target preliminary obstacle avoidance plan with the highest obstacle avoidance effectiveness, construct the auxiliary obstacle avoidance plan of the vehicle according to the plan training process corresponding to the target preliminary obstacle avoidance plan, and transmit the auxiliary obstacle avoidance plan to the display screen of the vehicle for display.

[0031] In an implementable manner,

[0032] It further includes:

[0033] Obtain the real-time relative position between the obstacle and the vehicle and transmit it to the display screen for display.

[0034] In an implementable manner,

[0035] The said step 4 includes:

[0036] Step 41: Construct the real-time obstacle avoidance information of the vehicle according to the driver's real-time obstacle avoidance operation, perform frame-by-frame processing on the real-time obstacle avoidance information to obtain the remaining avoidance distance between the vehicle and the obstacle at each moment, and determine the reasonable avoidance distance between the vehicle and the obstacle at each moment according to the auxiliary obstacle avoidance scheme;

[0037] Step 42: When the remaining avoidance distance is less than the reasonable avoidance distance, assist the driver in correcting the real-time obstacle avoidance operation, and at the same time record it as an obstacle avoidance shortcoming, and end the auxiliary obstacle avoidance work after the vehicle completes obstacle avoidance;

[0038] Step 43: When the vehicle reaches the destination, determine the driver's bad obstacle avoidance habits and bad obstacle avoidance operations according to several obstacle avoidance shortcomings existing in the vehicle's driving process this time, generate a risk report for this driving and display it.

[0039] In an implementable manner,

[0040] It also includes:

[0041] During the process of assisting the driver in obstacle avoidance, generate real-time obstacle avoidance reminder voice and play it;

[0042] When the remaining avoidance distance is less than the reasonable avoidance distance, generate a danger alarm voice and play it.

[0043] In an implementable manner,

[0044] It also includes:

[0045] Obtain the first element parameter corresponding to the longitudinal distance detection element and the second element parameter corresponding to the lateral distance detection element within a specified period;

[0046] Analyze the first remaining life of the longitudinal distance detection element according to the first element parameter, and reverse the second remaining life of the lateral detection element according to the second element parameter;

[0047] When the first remaining life is less than the specified life duration, or the second remaining life is less than the specified life duration, generate a component replacement suggestion and transmit it to the display screen for display.

[0048] The achievable beneficial effects of the above technical solution are as follows: In order to better assist the driver in avoiding small obstacles, longitudinal distance detection components and lateral distance detection components are installed on the vehicle. The sensitivity of the distance detection components is used to detect the obstacles around the vehicle. Therefore, when the vehicle is driving, it is controlled to detect obstacles. When an obstacle is detected, the relative motion trend between the vehicle and the obstacle is inferred. Then, by simulating the intended forward route of the vehicle, the collision probability between the vehicle and the obstacle is analyzed, so as to formulate an auxiliary obstacle avoidance plan to assist the driver in obstacle avoidance work. In order to ensure the quality of obstacle avoidance and avoid obstacle avoidance failure caused by external emergencies or improper operation of the driver, during the process of obstacle avoidance, the real-time driving risk of the vehicle is deduced based on the real-time obstacle avoidance information of the vehicle, and corresponding obstacle avoidance reminders are made. Finally, after successfully achieving obstacle avoidance and reaching the destination, the obstacle avoidance experience during this driving process is reviewed to analyze the driver's obstacle avoidance determination, so as to construct a corresponding risk report. Since some obstacles are too small to affect the driving of the vehicle and can be driven directly, or the obstacle is exactly at the wheel position and the steering wheel can be slightly moved to avoid the obstacle, or the height of the obstacle is difficult to judge and the driver is not sure whether there will be a collision with the vehicle, but in this way, it can assist the driver in better handling the troubles brought by small obstacles during driving, assist the driver in avoiding small obstacles, and after completing the avoidance work, the driver can review in time. The driver can analyze the drawbacks in this driving process through the generated risk report, and can also improve the driver's driving level through continuous strengthening, reducing the probability of accidents.

[0049] Other features and advantages of the present invention will be described in the following specification, and, in part, will be obvious from the specification, or will be understood by implementing the present invention. The objectives and other advantages of the present invention can be realized and obtained by the structures specifically pointed out in the written specification and the drawings.

[0050] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0051] The drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention. In the drawings:

[0052] Figure 1 It is a schematic diagram of the working process of an intelligent vehicle assisted driving and supervision method in an embodiment of the present invention;

[0053] Figure 2 It is a schematic diagram of the working process of step 3 of an intelligent vehicle assisted driving and supervision method in an embodiment of the present invention. Detailed Embodiments

[0054] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention and are not used to limit the present invention.

[0055] Embodiment 1

[0056] This embodiment provides an intelligent vehicle assisted driving and supervision method, as Figure 1 shown, including:

[0057] Step 1: When the vehicle is moving, control the longitudinal distance detection element and the lateral distance detection element to detect obstacles in the forward direction of the vehicle;

[0058] Step 2: When an obstacle is detected, infer the relative motion trend between the vehicle and the obstacle, simulate the intended forward route of the vehicle, and determine the collision probability between the vehicle and the obstacle;

[0059] Step 3: Based on the collision probability, formulate a corresponding auxiliary obstacle avoidance plan for the vehicle and transmit it to the display screen of the vehicle for display;

[0060] Step 4: Deduce the real-time driving risk of the vehicle according to the real-time obstacle avoidance information of the vehicle, analyze several shortcomings of the current obstacle avoidance process, and generate and display a risk report when the vehicle reaches the destination.

[0061] In this example, the longitudinal distance detection element refers to an element used to measure the distance of an object in the horizontal direction of the vehicle, and the lateral distance detection element refers to an element used to measure the distance of an object in the vertical direction of the vehicle;

[0062] In this example, the relative motion trend refers to the motion performance between the vehicle and the obstacle when the vehicle or the obstacle moves;

[0063] In this example, the intended forward route refers to the route that the vehicle is about to move forward. In addition to the method of determining the intended forward route given in the text, the vehicle navigation can also be used to assist in determining the intended forward route;

[0064] In this example, the real-time driving risk refers to the risk of collision with an obstacle according to the current operation of the driver.

[0065] Working principle and beneficial effects of the above technical solution: In order to better assist the driver in avoiding small obstacles, longitudinal distance detection components and lateral distance detection components are installed on the vehicle. The sensitivity of the distance detection components is used to detect obstacles around the vehicle. Therefore, when the vehicle is driving, it is controlled to detect obstacles. When an obstacle is detected, the relative motion trend between the vehicle and the obstacle is inferred. Then, by simulating the intended forward route of the vehicle, the collision probability between the vehicle and the obstacle is analyzed, and an auxiliary obstacle avoidance plan is formulated to assist the driver in avoiding obstacles. In order to ensure the quality of obstacle avoidance and avoid the failure of obstacle avoidance caused by external emergencies or improper operation of the driver, during the process of obstacle avoidance, the real-time driving risk of the vehicle is deduced based on the real-time obstacle avoidance information of the vehicle, and corresponding obstacle avoidance reminders are made. Finally, after successfully avoiding the obstacle and reaching the destination, the obstacle avoidance experience during this driving process is reviewed to analyze the driver's obstacle avoidance determination, and a corresponding risk report is constructed. Since some obstacles are too small to affect the driving of the vehicle and can be driven directly, or the obstacle is exactly at the wheel position and the steering wheel can be slightly moved to avoid the obstacle, or the height of the obstacle is difficult to judge and the driver is not sure whether there will be a collision with the vehicle, but in this way, the driver can be assisted to better handle the troubles brought by small obstacles during driving, assist the driver in avoiding small obstacles, and after completing the avoidance work, the driver can review in time. The driver can analyze the drawbacks in this driving process through the generated risk report, and can also improve the driver's driving level and reduce the probability of accidents through continuous strengthening.

[0066] Embodiment 2

[0067] Based on Embodiment 1, for the intelligent vehicle assisted driving and supervision method, Step 1 includes:

[0068] Step 11: When the vehicle is driving, obtain the parallel detection information collected by the longitudinal distance detection component of the vehicle and the vertical detection information collected by the lateral distance detection component, and perform overlapping processing on the parallel detection information and the vertical detection information to obtain a number of detection intersection information;

[0069] Step 12: Construct a detection grid of the vehicle according to the positional relationship between different detection intersection information, identify the image contours included in each sub-grid in the detection grid, construct a number of detection contours of the detection grid, and use AI to respectively identify the item attributes corresponding to each detection contour;

[0070] Step 13: Screen the target detection contours belonging to the obstacle attribute, locate the target contour in the detection grid, and when the obstacle corresponding to the target contour is in the same direction as the forward direction of the vehicle, make a first mark on the obstacle, otherwise make a second mark on the obstacle.

[0071] In this example, the detected intersection information represents the identical information between the parallel detection information and the vertical detection information when they detect the same position.

[0072] In this example, the detection grid represents the result of arranging the detected intersection information according to the spatial position.

[0073] In this example, the image contour represents the contour presented by the items contained in a sub-grid.

[0074] In this example, the item attribute represents the attribute of whether the detected item belongs to an obstacle.

[0075] In this example, the first marker and the second marker are used to distinguish between the obstacles located in the vehicle's forward direction and those not located in the vehicle's forward direction.

[0076] The working principle and beneficial effects of the above technical solution: During the vehicle's driving process, the detection information at different angles collected by the longitudinal distance detection element and the parallel distance detection element is overlapped to obtain the vehicle's detected intersection information, thereby constructing the vehicle's detection grid. The powerful function of AI technology is used to identify the attributes of the items contained in each sub-grid, and thus the target detection contour belonging to the obstacle can be determined. Then, the obstacles in the vehicle's driving direction and those not in the vehicle's driving direction are marked differently. Since the vehicle is driven by a person and the driver can adjust the vehicle's forward direction at any time according to needs, when analyzing the obstacles, both the obstacles in the vehicle's forward direction and those not in the forward direction are identified, avoiding the vehicle colliding with the obstacles due to the driver suddenly changing the forward direction, and improving the intelligence of the assisted driving work.

[0077] Embodiment 3

[0078] Based on Embodiment 2, the intelligent vehicle assisted driving and supervision method further includes:

[0079] When there is no obstacle in the vehicle's forward direction, a cautious lane change reminder is given to the driver according to the second marker.

[0080] The working principle and beneficial effects of the above technical solution: Different reminders are given to the driver according to the actual situation of the obstacle distribution, reducing the probability of collision accidents.

[0081] Embodiment 4

[0082] Based on Embodiment 1, in the intelligent vehicle assisted driving and supervision method, step 2 includes:

[0083] Step 21: When there is an obstacle in the forward direction of the vehicle, identify the obstacle movement characteristics of the obstacle, collect the current driving data of the vehicle to construct the vehicle movement characteristics of the vehicle, and construct the relative movement trend between the vehicle and the obstacle according to the obstacle movement characteristics and the vehicle movement characteristics;

[0084] Step 22: Lock the driving position of the vehicle according to the current driving data corresponding to the vehicle at different times, determine the current lane and current road conditions of the vehicle to deduce the intended forward route of the vehicle, and determine the collision position between the vehicle and the obstacle according to the relative movement trend and mark it in the preset space;

[0085] Step 23: Construct a corresponding virtual vehicle according to the appearance parameters of the vehicle, control the virtual vehicle in the preset space to simulate the intended forward route, determine the distance change characteristics between the vehicle and the obstacle, and generate the collision probability between the vehicle and the obstacle according to a number of distance values included in the distance change characteristics.

[0086] In this example, the obstacle movement characteristics represent the characteristics generated when the obstacle moves;

[0087] In this example, the vehicle movement characteristics represent the characteristics generated when the vehicle is driving, including its driving direction and driving speed;

[0088] In this example, the driving position locking represents the process of positioning the driving position of the vehicle;

[0089] In this example, the preset space represents a three-dimensional space constructed by the X direction, Y direction, and Z direction;

[0090] In this example, the distance change characteristics represent the change situation of the minimum distance between the vehicle and the obstacle during the driving process of the vehicle.

[0091] The working principle and beneficial effects of the above technical solution: If there is an obstacle in the forward direction of the vehicle, by analyzing the relative movement trend between the vehicle and the obstacle, combined with the current driving data corresponding to the vehicle at different times to lock the position of the vehicle, and then deduce the intended forward route of the vehicle, and then determine the collision probability between the vehicle and the obstacle by means of simulation in the preset space. In this way, it can be analyzed in advance whether the vehicle will collide when driving in the established direction, reduce the number of times the vehicle avoids small obstacles, and improve driving safety.

[0092] Embodiment 5

[0093] Based on Embodiment 4, the intelligent vehicle assisted driving and supervision method further includes:

[0094] Obtain the short-term operation information of the driver on the vehicle, evaluate the rationality of the intended forward route according to the short-term operation information, and when the intended forward route is unreasonable, adjust the intended forward route of the vehicle according to the short-term operation information.

[0095] In this example, the short-term operation information represents the operations performed by the driver to control the vehicle within 2 seconds.

[0096] In this example, the rationality evaluation represents the process of judging whether the short-term operation information matches the intended forward route and the degree of matching.

[0097] The working principle and beneficial effects of the above technical solution: When the driving demand made by the driver is different from the intended forward route, the intended forward route of the vehicle is adjusted in a timely manner according to the short-term operation information of the driver to ensure effective obstacle avoidance in the follow-up.

[0098] Embodiment 6

[0099] Based on Embodiment 1, the intelligent vehicle assisted driving and supervision method, as Figure 2 shown, Step 3 includes:

[0100] Step 31: When the collision probability is higher than the specified probability, determine several suspected collision positions between the vehicle and the obstacle, determine the remaining obstacle avoidance duration of the vehicle according to the current lane and current road conditions of the vehicle, and determine the remaining obstacle avoidance distance and the position to be avoided of the vehicle according to the suspected collision positions;

[0101] Step 32: Determine the adjustable range of the vehicle according to the road condition information, simulate the vehicle to perform iterative adjustment within the adjustable range, obtain several preliminary obstacle avoidance plans for the vehicle, and use the remaining obstacle avoidance duration to perform plan training on each preliminary obstacle avoidance plan to obtain the obstacle avoidance effectiveness corresponding to each preliminary obstacle avoidance plan;

[0102] Step 33: Screen the target preliminary obstacle avoidance plan with the highest obstacle avoidance effectiveness, construct the auxiliary obstacle avoidance plan of the vehicle according to the plan training process corresponding to the target preliminary obstacle avoidance plan, and transmit the auxiliary obstacle avoidance plan to the display screen of the vehicle for display.

[0103] In this example, the specified probability is 45%.

[0104] In this example, the suspected collision position represents the result of a collision between a position on the vehicle and a position on the obstacle.

[0105] In this example, the position to be avoided represents the position where a collision occurs in the vehicle.

[0106] In this example, the adjustable range means that the vehicle can adjust its position within this range without colliding with surrounding objects;

[0107] In this example, iterative adjustment means making multiple short-distance adjustments within the adjustable range;

[0108] In this example, the obstacle avoidance effectiveness represents the probability of completing a preliminary obstacle avoidance plan within the remaining obstacle avoidance time.

[0109] The working principle and beneficial effects of the above technical solution: When the vehicle is likely to collide with an obstacle, first determine the suspected collision position between the vehicle and the obstacle and the adjustable range of the vehicle, so as to determine the remaining obstacle avoidance distance and the position to be avoided by the vehicle. At the same time, analyze the remaining obstacle avoidance time of the vehicle according to the current lane where the vehicle is located and the current road conditions, and make iterative adjustments within the adjustable range through simulation to obtain a preliminary obstacle avoidance plan for the vehicle. In order to achieve effective obstacle avoidance, use the remaining obstacle avoidance time to train the preliminary obstacle avoidance plan to obtain the obstacle avoidance effectiveness of each preliminary obstacle avoidance plan, and then the target obstacle avoidance plan with the highest obstacle avoidance effectiveness can be selected, and then execute the plan training process of the target obstacle avoidance plan, thereby generating an auxiliary obstacle avoidance plan for the vehicle. In this way, the obstacle avoidance plan can be analyzed and trained in a short time to obtain the most effective obstacle avoidance plan, assisting the driver to complete obstacle avoidance in a short time and improving the driving safety of the driver.

[0110] Embodiment 7

[0111] Based on Embodiment 6, the intelligent vehicle assisted driving and supervision method further includes:

[0112] Obtain the real-time relative position between the obstacle and the vehicle and transmit it to the display screen for display.

[0113] The working principle and beneficial effects of the above technical solution: Real-time display of the real-time relative position between the vehicle and the obstacle provides a reference for the driver to avoid obstacles.

[0114] Embodiment 8

[0115] Based on Embodiment 1, in the intelligent vehicle assisted driving and supervision method, step 4 includes:

[0116] Step 41: Construct the real-time obstacle avoidance information of the vehicle according to the driver's real-time obstacle avoidance operation, perform frame-by-frame processing on the real-time obstacle avoidance information to obtain the remaining avoidance distance between the vehicle and the obstacle at each moment, and determine the reasonable avoidance distance between the vehicle and the obstacle at each moment according to the auxiliary obstacle avoidance plan;

[0117] Step 42: When the remaining avoidance distance is less than the reasonable avoidance distance, assist the driver to correct the real-time obstacle avoidance operation, and record it as an obstacle avoidance defect at the same time. After the vehicle completes obstacle avoidance, end the assisted obstacle avoidance work;

[0118] Step 43: When the vehicle reaches the destination, determine the driver's bad obstacle avoidance habits and bad obstacle avoidance operations based on several obstacle avoidance defects existing in the current driving process of the vehicle, generate a risk report for this driving and display it.

[0119] In this example, frame-by-frame processing represents the result of dividing the real-time obstacle avoidance information in units of one second in chronological order;

[0120] In this example, the reasonable avoidance distance represents the avoidance distance presented at the current moment when performing obstacle avoidance according to the assisted obstacle avoidance scheme.

[0121] The working principle and beneficial effects of the above technical solution: During obstacle avoidance, the real-time obstacle avoidance information of the vehicle is processed frame by frame to determine the remaining avoidance distance between the vehicle and the obstacle. At the same time, according to the assisted obstacle avoidance scheme, the reasonable avoidance distance between the vehicle and the obstacle is deduced. If the remaining avoidance distance is less than the reasonable avoidance distance, then assist the driver to correct the obstacle avoidance, and regard this position as an obstacle avoidance determination. When the vehicle reaches the destination and stops stably after turning off the engine, analyze the bad obstacle avoidance habits and bad obstacle avoidance operations during this driving process, generate a risk report for this driving. In this way, it can not only remedy emergencies during vehicle driving, but also conduct a review later to determine the driver's bad habits and bad operations, which can help the driver change bad habits and bad operations and continuously improve the driver's driving skills.

[0122] Embodiment 9

[0123] Based on Embodiment 8, the intelligent vehicle assisted driving and supervision method further includes:

[0124] During the process of assisting the driver to avoid obstacles, generate and play a real-time obstacle avoidance reminder voice;

[0125] When the remaining avoidance distance is less than the reasonable avoidance distance, generate and play a danger alarm voice.

[0126] The working principle and beneficial effects of the above technical solution: Different voice reminders are made for different situations during obstacle avoidance, which can better help the driver complete the obstacle avoidance work.

[0127] Embodiment 10

[0128] Based on Embodiment 1, the intelligent vehicle assisted driving and supervision method further includes:

[0129] Obtain the first component parameter corresponding to the longitudinal distance detection component and the second component parameter corresponding to the lateral distance detection component within a specified period;

[0130] Analyze the first remaining life of the longitudinal distance detection component according to the first component parameter, and analyze the second remaining life of the lateral detection component according to the second component parameter;

[0131] When the first remaining life is less than the specified life duration, or the second remaining life is less than the specified life duration, generate a component replacement suggestion and transmit it to the display screen for display.

[0132] In this example, the specified period is 180 days, and the specified life duration is 30 days.

[0133] The working principle and beneficial effects of the above technical solution: Analyze the remaining life of the longitudinal distance detection component and the lateral distance detection component by analyzing their component parameters. When the remaining life is insufficient, generate a component replacement suggestion to remind the driver to replace the component in time to avoid component damage affecting the obstacle avoidance quality.

[0134] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. An intelligent vehicle assisted driving and supervision method, characterized in that: include: Step 1: When the vehicle is traveling, the longitudinal distance detection element and the lateral distance detection element are controlled to detect obstacles in the forward direction of the vehicle; Step 2: When an obstacle is detected, the relative motion trend between the vehicle and the obstacle is estimated, the intended route of the vehicle is simulated, and the collision probability between the vehicle and the obstacle is determined; Step 3: formulating a corresponding auxiliary obstacle avoidance plan for the vehicle based on the collision probability, and transmitting the plan to the display screen of the vehicle for display; Step 4: derive the real-time driving risk of the vehicle based on the real-time obstacle avoidance information of the vehicle, analyze several obstacle avoidance shortcomings of this obstacle avoidance process, and generate and display a risk report when the vehicle arrives at the destination.

2. An intelligent vehicle assisted driving and supervision method as claimed in claim 1, characterized in that: The step 1 comprises: Step 11: when the vehicle is traveling, obtaining parallel detection information collected by the longitudinal distance detection element of the vehicle and vertical detection information collected by the lateral distance detection element, and overlapping the parallel detection information and the vertical detection information to obtain a plurality of detection intersection information; Step 12: constructing a detection grid of the vehicle according to the positional relationship between different detection intersection information, identifying the image contour contained in each sub-grid in the detection grid, constructing a plurality of detection contours of the detection grid, and using AI to respectively identify the object attributes corresponding to each detection contour; Step 13: Filter the target detection contour belonging to the obstacle attribute, locate the target contour in the detection grid, and when the obstacle corresponding to the target contour is consistent with the forward direction of the vehicle, perform a first mark on the obstacle, otherwise perform a second mark on the obstacle.

3. An intelligent vehicle assisted driving and supervision method as claimed in claim 2, characterized in that: Also includes: When there is no obstacle in the forward direction of the vehicle, the driver is reminded to change lanes carefully according to the second mark.

4. The intelligent vehicle assisted driving and supervision method according to claim 1, characterized in that: The step 2 comprises: Step 21: when there is an obstacle in the forward direction of the vehicle, identifying the obstacle motion characteristics of the obstacle, collecting the current driving data of the vehicle to construct the vehicle motion characteristics of the vehicle, and constructing the relative motion trend between the vehicle and the obstacle according to the obstacle motion characteristics and the vehicle motion characteristics; Step 22: locking the driving position of the vehicle according to the current driving data corresponding to the vehicle at different times, determining the current lane of the vehicle and the current road conditions to deduce the intended route of the vehicle, and determining the collision position between the vehicle and the obstacle according to the relative motion trend and marking it in a preset space; Step 23: construct a corresponding virtual vehicle according to the appearance parameters of the vehicle, control the virtual vehicle in the preset space to simulate the intended route, determine the distance transformation characteristics between the vehicle and the obstacle, and generate the collision probability between the vehicle and the obstacle according to several distance values ​​included in the distance transformation characteristics.

5. An intelligent vehicle assisted driving and supervision method as claimed in claim 4, characterized in that: Also includes: The short-term operation information of the driver on the vehicle is obtained, and the rationality of the intended route is evaluated according to the short-term operation information. When the intended route is unreasonable, the intended route of the vehicle is adjusted according to the short-term operation information.

6. The intelligent vehicle assisted driving and supervision method according to claim 1, characterized in that: The step 3 comprises: Step 31: when the collision probability is higher than a specified probability, determining a number of suspected collision positions between the vehicle and the obstacle, determining the remaining obstacle avoidance time of the vehicle according to the current lane of the vehicle and the current road conditions, and determining the remaining obstacle avoidance distance and the obstacle avoidance position of the vehicle according to the suspected collision position; Step 32: determining the adjustable range of the vehicle according to the road condition information, simulating the vehicle to perform iterative adjustment within the adjustable range, obtaining several preliminary obstacle avoidance schemes of the vehicle, and using the remaining obstacle avoidance time to perform scheme training on each of the preliminary obstacle avoidance schemes, to obtain the obstacle avoidance effectiveness corresponding to each of the preliminary obstacle avoidance schemes; Step 33: Screening the target preliminary obstacle avoidance scheme with the highest obstacle avoidance effectiveness, constructing the auxiliary obstacle avoidance scheme of the vehicle according to the scheme training process corresponding to the target preliminary obstacle avoidance scheme, and transmitting the auxiliary obstacle avoidance scheme to the display screen of the vehicle for display.

7. An intelligent vehicle assisted driving and supervision method as claimed in claim 6, characterized in that: Also includes: The real-time relative position between the obstacle and the vehicle is obtained and transmitted to the display screen for display.

8. The intelligent vehicle assisted driving and supervision method as claimed in claim 1, characterized in that: The step 4 comprises: Step 41: constructing real-time obstacle avoidance information of the vehicle according to the real-time obstacle avoidance operation of the driver, performing frame processing on the real-time obstacle avoidance information to obtain the remaining avoidance distance between the vehicle and the obstacle at each moment, and determining a reasonable avoidance distance between the vehicle and the obstacle at each moment according to the auxiliary obstacle avoidance scheme; Step 42: When the remaining avoidance distance is less than the reasonable avoidance distance, assist the driver to correct the real-time obstacle avoidance operation, and record it as an obstacle avoidance defect, and end the obstacle avoidance assistance work after the vehicle completes the obstacle avoidance; Step 43: When the vehicle arrives at the destination, the driver's bad obstacle avoidance habits and bad obstacle avoidance operations are determined based on several obstacle avoidance shortcomings existing in the vehicle's current driving process, and a risk report for this driving is generated and displayed.

9. An intelligent vehicle assisted driving and supervision method as claimed in claim 8, characterized in that: Also includes: In the process of assisting the driver to avoid obstacles, generating and playing a real-time obstacle avoidance reminder voice; When the remaining avoidance distance is less than the reasonable avoidance distance, a danger warning voice is generated and played.

10. An intelligent vehicle assisted driving and supervision method as claimed in claim 1, characterized in that: Also includes: Acquire a first element parameter corresponding to the longitudinal distance detection element and a second element parameter corresponding to the transverse distance detection element within a prescribed period; Analyzing a first remaining life of the longitudinal distance detection element according to the first element parameter and analyzing a second remaining life of the transverse detection element according to the second element parameter instead of the reverse; When the first remaining life is less than a prescribed life span, or the second remaining life is less than a prescribed life span, a component replacement suggestion is generated and transmitted to the display screen for display.

Images