Road vehicle virtual track control method and system and road vehicle

Abstract

The invention provides a road vehicle virtual track control method and system and a road vehicle, the road vehicle is provided with a visual sensor and a magnetic sensor, a virtual track is provided with a magnetic nail, and the road vehicle runs on the virtual track; the method comprises the steps that before a road vehicle starts to run, a first distance, obtained based on a visual sensor, of the road vehicle deviating from the track center of a virtual track is determined in advance, and a second distance, obtained based on a magnetic sensor and a magnetic nail, of the road vehicle deviating from the track center of the virtual track is determined; based on the first distance and the second distance, determining the lane line identification accuracy of the visual sensor on the virtual track; and under the condition that the lane line identification accuracy meets a preset requirement, controlling the driving operation of the road vehicle on the virtual track based on a visual sensor. The accuracy of lane line detection can be improved, so that the unmanned running process of the road vehicle on the virtual track can be reasonably controlled.

Description

Technical Field

[0001] The present invention relates to the technical field of virtual track control, and in particular to a road vehicle virtual track control method, system and road vehicle. Background Art

[0002] Autonomous driving technology is a topic of widespread concern in the current industry and academia. In order to reduce the burden on drivers and improve vehicle safety during driving, the autonomous driving system needs to ensure that the vehicle always stays within the lane line. The realization of this goal depends on the vehicle's ability to accurately perceive the lane line. At present, the tracking systems of most cars rely on pure visual cameras to capture road lane line information and control based on this.

[0003] However, lane line detection based on visual images has problems such as unstable detection and susceptibility to external interference.

[0004] Therefore, finding a road vehicle virtual track control method that can improve the accuracy of lane line detection has become a current research hotspot. Summary of the invention

[0005] The present invention provides a road vehicle virtual track control method, system and road vehicle, which can improve the accuracy of lane line detection, so as to reasonably control the unmanned driving operation process of the road vehicle on the virtual track.

[0006] The present invention provides a method for controlling a virtual track of a road vehicle, wherein the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track; the method comprises: before the road vehicle starts to travel, pre-determining a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and determining a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nails; determining the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance; and controlling the travel of the road vehicle on the virtual track based on the visual sensor when the lane line recognition accuracy of the virtual track meets preset requirements.

[0007] According to a road vehicle virtual track control method provided by the present invention, the driving operation of the road vehicle on the virtual track is controlled based on the visual sensor, specifically comprising: based on the visual sensor, collecting a first preceding road image of the road vehicle on the preceding road of the virtual track; based on the first preceding road image, determining a first preceding left lane line point set and a first preceding right lane line point set corresponding to the first preceding road image; based on the first preceding left lane line point set and the first preceding right lane line point set, performing a driving preview control on the road vehicle along the extension direction of the virtual track, so that the road vehicle travels in the middle position of the virtual track.

[0008] According to a road vehicle virtual track control method provided by the present invention, before determining a first front left lane line point set and a first front right lane line point set corresponding to the first front road image based on the first front road image, the method further includes: at each preset time interval, obtaining a first distance of the road vehicle deviating from the track center of the virtual track based on the visual sensor, and obtaining a second distance of the road vehicle deviating from the track center of the virtual track based on the magnetic sensor and the magnetic nail; determining a first front left lane line point set and a first front right lane line point set corresponding to the first front road image based on the first front road image specifically includes: determining a first front left lane line point set and a first front right lane line point set corresponding to the first front road image based on the first front road image when it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor meets a preset requirement.

[0009] According to a road vehicle virtual track control method provided by the present invention, after obtaining a first distance of the road vehicle deviating from the track center of the virtual track based on the visual sensor, and obtaining a second distance of the road vehicle deviating from the track center of the virtual track based on the magnetic sensor and the magnetic nail, the method further includes: in a case where it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements, issuing an alarm reminder, wherein the alarm reminder is used to prompt a user that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements.

[0010] According to a road vehicle virtual track control method provided by the present invention, the visual sensor is arranged at the center position of the road vehicle; based on the visual sensor, a first distance of the road vehicle deviating from the track center of the virtual track is obtained, which is implemented in the following manner: based on the visual sensor, a second preceding road image of the road vehicle on the preceding road of the virtual track is respectively collected; based on the second preceding road image, a second preceding left lane route point set and a second preceding right lane route point set corresponding to the second preceding road image are determined; the abscissa of the second preceding left lane route point and the abscissa of the second preceding right lane route point with the same ordinate are selected, wherein the second preceding left lane route point is a lane route point in the second preceding left lane route point set; the second preceding right lane route point is a lane route point in the second preceding right lane route point set; based on the abscissa of the second preceding left lane route point and the abscissa of the second preceding right lane route point, the first distance of the road vehicle deviating from the track center of the virtual track is determined.

[0011] According to a road vehicle virtual track control method provided by the present invention, a second distance of the road vehicle deviating from the track center of the virtual track is obtained based on the magnetic sensor and the magnetic nail, which is implemented in the following manner: calling the magnetic sensor set at the center position of the road vehicle to detect the magnetic nail position information of the magnetic nail; based on the magnetic nail position information, determining the second distance of the road vehicle deviating from the track center of the virtual track.

[0012] According to a road vehicle virtual track control method provided by the present invention, the determining the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance specifically includes: obtaining an average error based on the difference between the first distance and the second distance; when the average error is less than an error threshold and the first distance is less than a distance threshold, determining that the lane line recognition accuracy of the virtual track by the visual sensor meets preset requirements; when the average error is less than the error threshold and the first distance is greater than the distance threshold, recalibrating the lane line recognition of the virtual track by the visual sensor; when the average error is greater than the error threshold, determining that the lane line recognition accuracy of the virtual track by the visual sensor does not meet the preset requirements.

[0013] According to a road vehicle virtual track control method provided by the present invention, when the accuracy of lane line recognition of the virtual track by the visual sensor meets preset requirements, before controlling the driving operation of the road vehicle on the virtual track based on the visual sensor, the method further includes: calling the visual sensor to determine the track scene before entering the virtual track; when the track scene is a preset track scene, based on the magnetic nails set on the virtual track, controlling the driving operation of the road vehicle before entering the virtual track, wherein the preset track scene includes at least a bifurcated road track scene and a track scene without lane line markings.

[0014] The present invention also provides a road vehicle virtual track control system, wherein the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track; the system comprises: a determination module, used to predetermine a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and to determine a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nails before the road vehicle starts traveling; a processing module, used to determine the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance; and a control module, used to control the driving operation of the road vehicle on the virtual track based on the visual sensor when the lane line recognition accuracy of the virtual track by the visual sensor meets preset requirements.

[0015] The present invention also provides a road vehicle, comprising: a vehicle body, and a processor, wherein the processor is used to execute a road vehicle virtual track control method.

[0016] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned methods for controlling a virtual track of a road vehicle is implemented.

[0017] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the road vehicle virtual track control method as described in any one of the above is implemented.

[0018] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the road vehicle virtual track control method as described above is implemented.

[0019] The present invention provides a road vehicle virtual track control method, system and road vehicle, wherein the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with a magnetic nail, and the road vehicle travels on the virtual track; the method comprises: before the road vehicle starts to travel, pre-determine a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and determine a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; based on the first distance and the second distance, determine the lane line recognition accuracy of the virtual track by the visual sensor; when the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements, control the travel of the road vehicle on the virtual track based on the visual sensor. The lane line recognition accuracy of the virtual track by the visual sensor can be self-checked by the first distance and the second distance, and when the lane line recognition accuracy meets the preset requirements, control the travel of the road vehicle on the virtual track based on the visual sensor, thereby improving the accuracy of lane line detection, and thus realizing reasonable control of the unmanned driving operation process of the road vehicle on the virtual track. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0021] Figure 1 It is one of the flow charts of the road vehicle virtual track control method provided by the present invention.

[0022] Figure 2 It is a schematic diagram of a flow chart of controlling the running of a road vehicle on a virtual track based on a visual sensor provided by the present invention.

[0023] Figure 3 It is a schematic diagram of a process of obtaining a first distance of a road vehicle deviating from a track center of a virtual track based on a visual sensor provided by the present invention.

[0024] Figure 4 It is a schematic diagram of a flow chart of determining the lane line recognition accuracy of a virtual track by a visual sensor based on a first distance and a second distance provided by the present invention.

[0025] Figure 5 This is the second flow chart of the road vehicle virtual track control method provided by the present invention.

[0026] Figure 6It is a schematic diagram of an application scenario of the virtual track provided by the present invention.

[0027] Figure 7 It is a structural schematic diagram of a road vehicle virtual track control system provided by the present invention.

[0028] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. 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.

[0030] Virtual track is a track system that does not require the laying of physical tracks. It relies on specific technical means (such as image recognition, satellite navigation, etc.) to guide trains. Virtual track has the advantages of low construction cost and strong flexibility, and can be widely used in various new rail transit systems.

[0031] The road vehicle virtual track control method provided by the present invention can realize the verification of visual detection output (corresponding to visual sensor), thereby improving the reliability of controlling the driving of road vehicles on virtual tracks based on visual sensors and enhancing the safety of use. In addition, the road vehicle virtual track control method provided by the present invention can also solve the problems of no markings, marking forks (corresponding to preset track scenes), etc., thereby expanding the use scenarios, especially for situations with specific routes such as urban buses.

[0032] Figure 1 It is one of the flow charts of the road vehicle virtual track control method provided by the present invention.

[0033] The following will be combined Figure 1 The process of the road vehicle virtual track control method provided by the present invention is described.

[0034] In an exemplary embodiment of the present invention, a road vehicle is provided with a visual sensor and a magnetic sensor, a virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track. In one example, the road vehicle may be a rubber-wheeled train. The rubber-wheeled train may be a train that uses rubber wheels as a running mechanism, and has higher flexibility and adaptability than a traditional steel wheel and steel rail train. The rubber-wheeled train may also deviate from conventional tracks and travel on roads.

[0035] In one embodiment, in combination Figure 1 It can be seen that the road vehicle virtual track control method may include steps 110 to 130, and each step will be introduced below.

[0036] In step 110, before the road vehicle starts driving, a first distance of the road vehicle deviating from the track center of the virtual track based on the visual sensor is determined in advance, and a second distance of the road vehicle deviating from the track center of the virtual track based on the magnetic sensor and the magnetic nail is determined in advance.

[0037] In step 120 , based on the first distance and the second distance, the lane line recognition accuracy of the virtual track performed by the visual sensor is determined.

[0038] In one embodiment, before the road vehicle starts to travel, that is, before the road vehicle officially runs, the accuracy of the lane line recognition of the virtual track by the visual sensor can be self-checked first. When the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements, the driving of the road vehicle on the virtual track can be controlled based on the visual sensor, which can provide control reliability.

[0039] In another embodiment, a first distance of a road vehicle deviating from the track center of a virtual track based on a visual sensor may be predetermined, and a second distance of a road vehicle deviating from the track center of a virtual track based on a magnetic sensor and a magnetic nail may be predetermined. It is understood that the first distance may represent the distance of a vehicle deviating from the center of a lane determined by visual detection (corresponding to a visual sensor). The first distance may represent the distance of a vehicle deviating from the center of a lane determined by magnetic nail detection (corresponding to a magnetic sensor and a magnetic nail).

[0040] In yet another embodiment, a self-check process may be performed based on the first distance and the second distance, so as to determine the accuracy of lane line recognition of the virtual track by the visual sensor.

[0041] In step 130, when the lane line recognition accuracy of the virtual track performed by the visual sensor meets the preset requirements, the driving operation of the road vehicle on the virtual track is controlled based on the visual sensor.

[0042] In one embodiment, when the lane line recognition accuracy of the virtual track performed by the visual sensor meets the preset requirements, the driving of the road vehicle on the virtual track can be controlled based on the visual sensor. The preset requirements can be determined according to actual conditions, and are not specifically limited in this embodiment.

[0043] In another embodiment, since the driving operation of the road vehicle on the virtual track is controlled based on the visual sensor, it is possible to adjust the driving operation of the road vehicle on the virtual track through the feedback content of the visual sensor without the need for human participation, thereby realizing reasonable control of the unmanned driving operation process of the road vehicle on the virtual track.

[0044] The present invention provides a road vehicle virtual track control method, wherein the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with a magnetic nail, and the road vehicle travels on the virtual track; the method comprises: before the road vehicle starts to travel, predetermine a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and determine a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; based on the first distance and the second distance, determine the lane line recognition accuracy of the virtual track by the visual sensor; when the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements, control the travel of the road vehicle on the virtual track based on the visual sensor. The lane line recognition accuracy of the virtual track by the visual sensor can be self-checked by the first distance and the second distance, and when the lane line recognition accuracy meets the preset requirements, control the travel of the road vehicle on the virtual track based on the visual sensor, thereby improving the accuracy of lane line detection, thereby realizing reasonable control of the unmanned driving operation process of the road vehicle on the virtual track.

[0045] Figure 2 It is a schematic diagram of a flow chart of controlling the running of a road vehicle on a virtual track based on a visual sensor provided by the present invention.

[0046] The following will be combined Figure 2 The process of controlling the driving operation of a road vehicle on a virtual track based on a visual sensor is described.

[0047] In an exemplary embodiment of the present invention, Figure 2 It can be seen that controlling the driving of a road vehicle on a virtual track based on a visual sensor may include steps 210 to 230, and each step will be introduced below.

[0048] In step 210 , a first preceding road image of the road vehicle on the preceding road of the virtual track is collected based on a visual sensor.

[0049] In step 220 , based on the first preceding road image, a first preceding left lane line point set and a first preceding right lane line point set corresponding to the first preceding road image are determined.

[0050] In step 230, based on the first preceding left lane line point set and the first preceding right lane line point set, the road vehicle is controlled to travel in the middle position of the virtual track along the extension direction of the virtual track.

[0051] In one embodiment, during the running of the rail vehicle on the virtual track, a first preceding road image of the road vehicle on the preceding road of the virtual track may be collected based on a visual sensor. Further, based on the first preceding road image, a first preceding left lane line point set and a first preceding right lane line point set corresponding to the first preceding road image are determined. It is to be understood that the first preceding left lane line point set and the first preceding right lane line point set may respectively include position coordinate information of each point of the first preceding left lane line point and the first preceding right lane line point.

[0052] In another embodiment, longitudinal preview control can be performed based on the first preceding left lane line point set and the first preceding right lane line point set, that is, based on the position coordinate information of each point of the first preceding left lane line point and the first preceding right lane line point identified and fed back by the visual sensor, that is, preview control of the road vehicle's driving operation can be performed along the extension direction of the virtual track, so that the road vehicle can travel in the middle position of the virtual track. In this embodiment, since the visual sensor is a self-checking visual sensor, the reliability of control can be improved by controlling the driving operation of the road vehicle on the virtual track based on the visual sensor.

[0053] In an exemplary embodiment of the present invention, continuing with the above Figure 2 Taking the above embodiment as an example, before determining the first front left lane line point set and the first front right lane line point set corresponding to the first front road image based on the first front road image, the road vehicle virtual track control method may further include the following steps: At each preset time interval, a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; Wherein, based on the first front road image, determining the first front left lane line point set and the first front right lane line point set corresponding to the first front road image can be implemented in the following manner: When it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor meets the preset requirements, based on the first front road image, a first front left lane line point set and a first front right lane line point set corresponding to the first front road image are determined.

[0054] In one embodiment, during the driving of a road vehicle, the visual sensor can be recalibrated at preset time intervals based on a first distance of the road vehicle deviating from the track center of the virtual track obtained by the visual sensor, and a second distance of the road vehicle deviating from the track center of the virtual track obtained by the magnetic sensor and the magnetic nail.

[0055] In another embodiment, when it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor meets preset requirements, that is, when the lane line recognition verification of the virtual track performed by the visual sensor passes, it is possible to continue to determine the first front left lane line point set and the first front right lane line point set corresponding to the first front road image based on the first front road image, thereby laying a foundation for controlling the automatic driving operation of road vehicles.

[0056] In another exemplary embodiment of the present invention, the above-mentioned embodiment is continued to be used as an example for explanation. After the first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor and the second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail, the road vehicle virtual track control method may further include the following steps: When it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements, an alarm reminder is issued, wherein the alarm reminder is used to prompt the user that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements.

[0057] In one embodiment, when it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements, that is, when the visual sensor self-check fails, an alarm reminder can be issued. The alarm reminder is used to prompt the user that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements. In another example, when it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements, that is, when the visual sensor self-check fails, the automatic driving operation program of the road vehicle can also be exited, and the user can operate the road vehicle to drive.

[0058] Figure 3 It is a schematic diagram of a process of obtaining a first distance of a road vehicle deviating from a track center of a virtual track based on a visual sensor provided by the present invention.

[0059] The following will be combined Figure 3 The process of obtaining a first distance of a road vehicle deviating from a track center of a virtual track based on a visual sensor is described.

[0060] In an exemplary embodiment of the present invention, the visual sensor can be arranged at the center of the road vehicle; Figure 3 It can be known that obtaining the first distance of the road vehicle deviating from the track center of the virtual track based on the visual sensor may include steps 310 to 340, and each step will be introduced below.

[0061] In step 310 , second preceding road images of the road vehicle on the preceding road of the virtual track are respectively collected based on the visual sensor.

[0062] In step 320 , based on the second preceding road image, a second preceding left lane line point set and a second preceding right lane line point set corresponding to the second preceding road image are determined.

[0063] In one embodiment, the visual sensor and the magnetic sensor can be set at the center of the road vehicle; the magnetic nail can be set at the track center of the virtual track. It should be noted that for actual applications that do not meet this assumption, the assumption can be met through calibration and coordinate conversion processes. A self-vehicle coordinate system can be established with the center of the rear axle of the vehicle as the origin, the forward direction of the vehicle as the positive x-coordinate, and the left side of the vehicle as the positive y-coordinate.

[0064] In another embodiment, the second front road image of the road vehicle on the front road of the virtual track can be collected based on the visual sensor. Further, based on the second front road image, the second front left lane line point set and the second front right lane line point set corresponding to the second front road image are determined. Among them, the second front left lane line point set and the second front right lane line point set can respectively include the position coordinate information of each point of the second front left lane line point and the second front right lane line point. In the application process, the coordinate information of the lane line (corresponding to the second front left lane line and the second front right lane line) can be output in a list form. Among them, the output result can include the left lane line point set (corresponding to the second front left lane line point set) {[x1, y1], [x2, y2], ..., [xm, ym]}, the coefficients [al, bl, cl] obtained by fitting the left lane line, and y = al x^2 + bl x + cl to describe the relationship between the horizontal coordinates and the vertical coordinates of each road point in the front left lane line. The right lane line point set (corresponding to the second right lane line point set in front) {[x1, y1], [x2, y2], …, [xn, yn]}, the coefficients obtained by fitting the left lane line [ar, br, cr], and y = ar x^2 + br x + cr to describe the relationship between the horizontal and vertical coordinates of each point in the right lane line in front.

[0065] In step 330, select the abscissa of the second front left lane line point and the abscissa of the second front right lane line point having the same ordinate, where the second front left lane line point is the lane line point in the second front left lane line point set; the second front right lane line point is the lane line point in the second front right lane line point set.

[0066] In step 340, based on the abscissa of the second front left lane line point and the abscissa of the second front right lane line point, determine the first distance of the road vehicle from the center of the virtual track.

[0067] In another embodiment, based on the output result of the vision sensor, respectively select the first N points in the left lane line point set and the first N points in the right lane line point set (0 < N < min(m, n)). It can be understood that if the vehicle is strictly driving in the center of the lane, for the points in the left and right lane line point sets obtained by vision detection, when the ordinates are the same, the abscissas x of the left and right lane points should be a pair of opposite numbers. In the application process, based on the abscissa of the second front left lane line point and the abscissa of the second front right lane line point, determine the first distance of the road vehicle from the center of the virtual track, that is, select the average value e1 of the sum of the abscissas of the above 2N points, which represents the distance of the vehicle detected by vision from the center of the lane. It can be understood that the first distance can be e1.

[0068] It should be noted that when the front lane is more curved and has a larger curvature, select fewer lane line points N; when the front lane is straight and has a smaller curvature, select more lane line points N.

[0069] In an exemplary embodiment of the present invention, based on the magnetic sensor and the magnetic nail to obtain the second distance of the road vehicle from the center of the virtual track, the following steps may be included: Call the magnetic sensor set at the center position of the road vehicle to detect the magnetic nail position information of the magnetic nail; Based on the magnetic nail position information, determine the second distance of the road vehicle from the center of the virtual track.

[0070] In one embodiment, if the vehicle is strictly driving in the center of the lane, the magnetic nail position detection should be at the center of the magnetic sensor. Denote the distance of the magnetic nail position detection from the center of the magnetic sensor as e2, which represents the distance of the vehicle detected by the magnetic nail from the center of the lane. In the application process, based on the magnetic nail position information, determine the second distance of the road vehicle from the center of the virtual track, where the second distance can be e2.

[0071] Figure 4 It is a schematic flow chart of the present invention for determining the lane line recognition accuracy of the virtual track by the vision sensor based on the first distance and the second distance.

[0072] The following will be combined Figure 4 The process of determining the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance is described.

[0073] In an exemplary embodiment of the present invention, Figure 4 It can be seen that determining the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance may include steps 410 to 440, and each step will be introduced below.

[0074] In step 410, an average error is obtained based on the difference between the first distance and the second distance.

[0075] In one embodiment, it can be applied in the station start-up scenario, that is, before the road vehicle starts to run. In this scenario, by setting clear lane lines and dense ground magnetic nails, e1 and e2 can be compared and their average error E can be obtained by difference.

[0076] In step 420, when the average error is less than the error threshold and the first distance is less than the distance threshold, it is determined that the lane line recognition accuracy of the virtual track performed by the visual sensor meets the preset requirement.

[0077] In step 430 , when the average error is less than the error threshold and the first distance is greater than the distance threshold, the lane line recognition of the virtual track of the visual sensor is recalibrated.

[0078] In step 440 , when the average error is greater than the error threshold, it is determined that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirement.

[0079] In one embodiment, the average error E should be within a set smaller error limit Th1. If it is satisfied, the system is considered normal. That is, when the average error is less than the error threshold (corresponding to the smaller error limit Th1) and the first distance e1 is less than the distance threshold Th2, it is determined that the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements.

[0080] In another embodiment, when the average error is less than the error threshold and the first distance is greater than the distance threshold, it indicates that the accuracy of the calibration based on the visual sensor is not high. In the application process, the visual sensor needs to be recalibrated for lane line recognition of the virtual track. In one example, the self-calibration and re-self-checking process can be implemented by subtracting the average error from the result of the visual detection (corresponding to the visual sensor).

[0081] In yet another embodiment, when the average error is greater than the error threshold, it indicates that the self-test of the visual sensor has failed, that is, it is determined that the lane line recognition accuracy of the virtual track by the visual sensor does not meet the preset requirements.

[0082] Figure 5 This is the second flow chart of the road vehicle virtual track control method provided by the present invention.

[0083] The following will be combined Figure 5 The process of another road vehicle virtual track control method is described.

[0084] In an exemplary embodiment of the present invention, Figure 5 It can be seen that the road vehicle virtual track control method may include steps 510 to 550, wherein steps 510 to 520 are the same as or similar to steps 110 to 120, and step 550 is the same as or similar to step 130. Please refer to the foregoing description for its specific implementation and beneficial effects, which will not be repeated in this embodiment. Steps 530 and 540 will be introduced respectively below.

[0085] In step 530, a visual sensor is called to determine the track scene before entering the virtual track.

[0086] In step 540, when the track scene is a preset track scene, the driving operation of the road vehicle before entering the virtual track is controlled based on the magnetic nails set on the virtual track, wherein the preset track scene at least includes a forked road track scene and a track scene without lane line markings.

[0087] Figure 6 This is a schematic diagram of an application scenario of the virtual track provided by the present invention. Figure 6 Examples are described.

[0088] In one embodiment, a visual sensor may be called to determine a track scene before entering a virtual track; further, when the track scene is a preset track scene, the driving operation of a road vehicle before entering the virtual track may be controlled based on magnetic nails set on the virtual track, wherein the preset track scene may include at least a forked road track scene and a track scene without lane line markings.

[0089] In the application process, combined with Figure 6 It can be seen that Figure 6 The black dots in the figure represent magnetic pins, and the dotted lines represent lane lines. Figure 6For the bifurcated road section in the middle, clear lane lines can be set, and denser magnetic nails can be set in front of the road bifurcation, and deviate in the direction of the desired road. For example, at the lane entrance that bifurcates to the right, the magnetic nails are set to deviate from the center of the lane by 5cm, 10cm, 15cm, 20cm...50cm in sequence; after receiving continuous data from the magnetic sensor, the algorithm recognizes this pattern and drives in the direction of the magnetic nail deviation. Among them, the magnetic nail can also be implemented by encoding and identifying the N and S poles of the magnetic nail, or by directly reading the coded information through the magnetic nail with RFID.

[0090] In another embodiment, at an unmarked line intersection (corresponding to Figure 6 For the unmarked line section in the middle of the intersection, relatively dense magnetic nails are set before and in the intersection. The magnetic nails are all located in the center of the desired lane. The algorithm recognizes this pattern and drives towards the center of the magnetic nails.

[0091] Furthermore, after entering the virtual track guided by magnetic nails, the driving of the road vehicle on the virtual track can be controlled based on the visual sensor when the lane line recognition accuracy of the virtual track meets the preset requirements, so as to ensure that the road vehicle drives in the center of the virtual track, thereby realizing reasonable control of the unmanned driving operation process of the road vehicle on the virtual track.

[0092] According to the foregoing description, the road vehicle virtual track control method provided by the present invention, the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with a magnetic nail, and the road vehicle travels on the virtual track; the method includes: before the road vehicle starts to travel, pre-determine a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and determine a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; based on the first distance and the second distance, determine the lane line recognition accuracy of the virtual track by the visual sensor; when the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements, control the driving operation of the road vehicle on the virtual track based on the visual sensor. The lane line recognition accuracy of the virtual track can be self-checked by the visual sensor through the first distance and the second distance, and when the lane line recognition accuracy meets the preset requirements, control the driving operation of the road vehicle on the virtual track based on the visual sensor, thereby improving the accuracy of lane line detection, and thus realizing reasonable control of the unmanned driving operation process of the road vehicle on the virtual track.

[0093] The road vehicle virtual track control system provided by the present invention is described below. The road vehicle virtual track control system described below and the road vehicle virtual track control method described above can be referred to each other.

[0094] Figure 7 It is a structural schematic diagram of a road vehicle virtual track control system provided by the present invention.

[0095] The following will be combined Figure 7 The structure of the road vehicle virtual track control system is described.

[0096] In an exemplary embodiment of the present invention, the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic spikes, and the road vehicle travels on the virtual track. Figure 7 It can be seen that the road vehicle virtual track control system may include a determination module 710, a processing module 720 and a control module 730, and each module will be introduced below.

[0097] The determination module 710 may be configured to, before the road vehicle starts driving, predetermine a first distance that the road vehicle deviates from the track center of the virtual track based on the visual sensor, and determine a second distance that the road vehicle deviates from the track center of the virtual track based on the magnetic sensor and the magnetic nail; The processing module 720 may be configured to determine the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance; The control module 730 may be configured to control the driving of the road vehicle on the virtual track based on the visual sensor when the lane line recognition accuracy of the virtual track performed by the visual sensor meets a preset requirement.

[0098] In an exemplary embodiment of the present invention, the control module 730 may control the driving of the road vehicle on the virtual track based on the visual sensor in the following manner: Based on the visual sensor, collecting a first preceding road image of the road vehicle on the preceding road of the virtual track; Based on the first front road image, determining a first front left lane line point set and a first front right lane line point set corresponding to the first front road image; Based on the first preceding left lane line point set and the first preceding right lane line point set, the road vehicle is subjected to a driving preview control along an extension direction of the virtual track, so that the road vehicle travels at a middle position of the virtual track.

[0099] In an exemplary embodiment of the present invention, the control module 730 may also be configured to: At intervals of a preset time, a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; The control module 730 may also determine the first front left lane line point set and the first front right lane line point set corresponding to the first front road image based on the first front road image in the following manner: When it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor meets preset requirements, based on the first front road image, a first front left lane line point set and a first front right lane line point set corresponding to the first front road image are determined.

[0100] In an exemplary embodiment of the present invention, the control module 730 may also be configured to: When it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements, an alarm reminder is issued, wherein the alarm reminder is used to prompt a user that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements.

[0101] In an exemplary embodiment of the present invention, the visual sensor is disposed at the center of the road vehicle; the processing module 720 may obtain the first distance of the road vehicle from the track center of the virtual track based on the visual sensor in the following manner: Based on the visual sensor, respectively collect the second preceding road image of the road vehicle on the preceding road of the virtual track; Based on the second front road image, determining a second front left lane line point set and a second front right lane line point set corresponding to the second front road image; Selecting the abscissa of a second preceding left lane route point and the abscissa of a second preceding right lane route point having the same ordinate, wherein the second preceding left lane route point is a lane route point in the second preceding left lane route point set; and the second preceding right lane route point is a lane route point in the second preceding right lane route point set; Based on the abscissa of the second preceding left lane route point and the abscissa of the second preceding right lane route point, a first distance by which the road vehicle deviates from a track center of the virtual track is determined.

[0102] In an exemplary embodiment of the present invention, the processing module 720 may obtain the second distance of the road vehicle from the track center of the virtual track based on the magnetic sensor and the magnetic nail in the following manner: calling the magnetic sensor disposed at the center position of the road vehicle to detect magnetic nail position information of the magnetic nail; Based on the magnetic spike position information, a second distance that the road vehicle deviates from the track center of the virtual track is determined.

[0103] In an exemplary embodiment of the present invention, the processing module 720 may determine the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance in the following manner: Obtaining an average error based on a difference between the first distance and the second distance; When the average error is less than an error threshold and the first distance is less than a distance threshold, determining that the lane line recognition accuracy of the virtual track performed by the visual sensor meets a preset requirement; When the average error is less than an error threshold and the first distance is greater than a distance threshold, recalibrating the lane line recognition of the virtual track by the visual sensor; When the average error is greater than the error threshold, it is determined that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet a preset requirement.

[0104] In an exemplary embodiment of the present invention, the control module 730 may also be configured to: Invoking the visual sensor to determine the track scene before entering the virtual track; In the case where the track scene is a preset track scene, the driving operation of the road vehicle before entering the virtual track is controlled based on the magnetic nails set on the virtual track, wherein the preset track scene at least includes a forked road track scene and a track scene without lane line markings.

[0105] Based on the same inventive concept, the present invention also provides a road vehicle.

[0106] The structure of the road vehicle will be described below in conjunction with the following embodiments.

[0107] In an exemplary embodiment of the present invention, a road vehicle may include a vehicle body and a processor. The processor is used to execute the road vehicle virtual track control method described in any one of the above. Since the processor in the road vehicle can self-check the lane line recognition accuracy of the virtual track by the visual sensor through the first distance and the second distance, and control the driving operation of the road vehicle on the virtual track based on the visual sensor when the lane line recognition accuracy meets the preset requirements, the accuracy of lane line detection can be improved, thereby realizing reasonable control of the unmanned driving operation process of the road vehicle on the virtual track.

[0108] Figure 8 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 8 As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to execute a road vehicle virtual track control method, wherein the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track; the method includes: before the road vehicle starts to travel, pre-determine a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and determine a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; based on the first distance and the second distance, determine the lane line recognition accuracy of the virtual track by the visual sensor; when the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements, control the travel of the road vehicle on the virtual track based on the visual sensor.

[0109] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0110] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the road vehicle virtual track control method provided by the above methods, wherein the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track; the method includes: before the road vehicle starts driving, pre-determining a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and determining a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; based on the first distance and the second distance, determining the lane line recognition accuracy of the virtual track by the visual sensor; when the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements, controlling the driving operation of the road vehicle on the virtual track based on the visual sensor.

[0111] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented when the processor executes the road vehicle virtual track control method provided by the above methods, wherein the road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track; the method comprises: before the road vehicle starts driving, pre-determining a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and determining a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; based on the first distance and the second distance, determining the lane line recognition accuracy of the virtual track by the visual sensor; and when the lane line recognition accuracy of the virtual track by the visual sensor meets the preset requirements, controlling the driving operation of the road vehicle on the virtual track based on the visual sensor.

[0112] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0113] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0114] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A road vehicle virtual track control method, characterized in that: The road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track; the method comprises: Before the road vehicle starts running, predetermine a first distance of the road vehicle deviating from the track center of the virtual track based on the visual sensor, and predetermine a second distance of the road vehicle deviating from the track center of the virtual track based on the magnetic sensor and the magnetic nail; Based on the first distance and the second distance, determining the lane line recognition accuracy of the virtual track by the visual sensor; When the lane line recognition accuracy of the virtual track performed by the visual sensor meets preset requirements, the driving operation of the road vehicle on the virtual track is controlled based on the visual sensor.

2. The road vehicle virtual track control method according to claim 1, characterized in that: The controlling the driving of the road vehicle on the virtual track based on the visual sensor specifically includes: Based on the visual sensor, collecting a first preceding road image of the road vehicle on the preceding road of the virtual track; Based on the first front road image, determining a first front left lane line point set and a first front right lane line point set corresponding to the first front road image; Based on the first preceding left lane line point set and the first preceding right lane line point set, the road vehicle is subjected to a driving preview control along an extension direction of the virtual track, so that the road vehicle travels at a middle position of the virtual track.

3. The road vehicle virtual track control method according to claim 2, characterized in that: Before determining, based on the first front road image, a first front left lane line point set and a first front right lane line point set corresponding to the first front road image, the method further includes: At intervals of a preset time, a first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor, and a second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; The determining, based on the first front road image, a first front left lane line point set and a first front right lane line point set corresponding to the first front road image specifically includes: When it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor meets preset requirements, based on the first front road image, a first front left lane line point set and a first front right lane line point set corresponding to the first front road image are determined.

4. The road vehicle virtual track control method according to claim 3, characterized in that: After the first distance of the road vehicle deviating from the track center of the virtual track obtained based on the visual sensor and the second distance of the road vehicle deviating from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail, the method further includes: When it is determined based on the first distance and the second distance that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements, an alarm reminder is issued, wherein the alarm reminder is used to prompt a user that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet the preset requirements.

5. The road vehicle virtual track control method according to any one of claims 1 to 4, characterized in that: The visual sensor is arranged at the center of the road vehicle; and obtaining a first distance of the road vehicle from the track center of the virtual track based on the visual sensor is implemented in the following manner: Based on the visual sensor, respectively collect the second preceding road image of the road vehicle on the preceding road of the virtual track; Based on the second front road image, determining a second front left lane line point set and a second front right lane line point set corresponding to the second front road image; Selecting the abscissa of a second preceding left lane route point and the abscissa of a second preceding right lane route point having the same ordinate, wherein the second preceding left lane route point is a lane route point in the second preceding left lane route point set; and the second preceding right lane route point is a lane route point in the second preceding right lane route point set; Based on the abscissa of the second preceding left lane route point and the abscissa of the second preceding right lane route point, a first distance by which the road vehicle deviates from a track center of the virtual track is determined.

6. The road vehicle virtual track control method according to any one of claims 1 to 4, characterized in that: The second distance of the road vehicle deviating from the track center of the virtual track is obtained based on the magnetic sensor and the magnetic nail, and is implemented in the following manner: calling the magnetic sensor disposed at the center position of the road vehicle to detect magnetic nail position information of the magnetic nail; Based on the magnetic spike position information, a second distance that the road vehicle deviates from the track center of the virtual track is determined.

7. The road vehicle virtual track control method according to any one of claims 1 to 4, characterized in that: The determining, based on the first distance and the second distance, the lane line recognition accuracy of the virtual track by the visual sensor specifically includes: Obtaining an average error based on a difference between the first distance and the second distance; When the average error is less than an error threshold and the first distance is less than a distance threshold, determining that the lane line recognition accuracy of the virtual track performed by the visual sensor meets a preset requirement; When the average error is less than an error threshold and the first distance is greater than a distance threshold, recalibrating the lane line recognition of the virtual track by the visual sensor; When the average error is greater than the error threshold, it is determined that the lane line recognition accuracy of the virtual track performed by the visual sensor does not meet a preset requirement.

8. The road vehicle virtual track control method according to claim 1, characterized in that: When the lane line recognition accuracy of the virtual track performed by the visual sensor meets the preset requirements, before controlling the driving operation of the road vehicle on the virtual track based on the visual sensor, the method further includes: Invoking the visual sensor to determine the track scene before entering the virtual track; In the case where the track scene is a preset track scene, the driving operation of the road vehicle before entering the virtual track is controlled based on the magnetic nails set on the virtual track, wherein the preset track scene at least includes a forked road track scene and a track scene without lane line markings.

9. A road vehicle virtual track control system, characterized in that: The road vehicle is provided with a visual sensor and a magnetic sensor, the virtual track is provided with magnetic nails, and the road vehicle travels on the virtual track; the system comprises: a determination module, configured to predetermine, before the road vehicle starts driving, a first distance by which the road vehicle deviates from the track center of the virtual track obtained based on the visual sensor, and a second distance by which the road vehicle deviates from the track center of the virtual track obtained based on the magnetic sensor and the magnetic nail; A processing module, configured to determine the lane line recognition accuracy of the virtual track by the visual sensor based on the first distance and the second distance; A control module is used to control the driving operation of the road vehicle on the virtual track based on the visual sensor when the lane line recognition accuracy of the virtual track performed by the visual sensor meets the preset requirements.

10. A road vehicle, wherein: The road vehicle comprises: The vehicle body, and A processor, wherein the processor is used to execute the road vehicle virtual track control method as described in any one of claims 1 to 8.

Images