Automatic Trajectory Correction Method and System for Driverless Vehicles

Abstract

The present application relates to an automatic trajectory correction method and system for an unmanned vehicle. The method includes: Step A: Determine whether the unmanned vehicle deviates from the preset route. When the unmanned vehicle deviates from the preset route, execute Step B; Step B: Obtain the current actual attitude angle and / or driving trajectory of the unmanned vehicle; Obtain the driving distances of the left and right wheels of the unmanned vehicle, and simulate the corresponding simulated attitude angle and / or simulated trajectory of the unmanned vehicle under the driving distances. Compare whether the simulated attitude angle is consistent with the actual attitude angle, and / or compare whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle is consistent with the actual attitude angle, and / or the simulated trajectory is consistent with the driving trajectory, it is determined that there is a wheel failure, and execute Step C; Step C: Correct the wheels. By identifying the type of failure through the above method, accurate correction can be made to the unmanned vehicle, enabling the unmanned vehicle to return to the preset route in a timely manner.

Description

Technical Field

[0001] The present invention relates to the field of autonomous vehicles, and in particular, to an automatic trajectory correction method and system for autonomous vehicles. Background Art

[0002] With the continuous development of technology and the continuous improvement of living standards, many jobs tend to be automated, and the use of autonomous vehicles is becoming more and more common. For the control of autonomous vehicles, under normal circumstances, an autonomous vehicle will travel along a preset route at a preset heading angle according to a set program. However, during the driving process of an autonomous vehicle, there are often some unpredictable faults that cause the autonomous vehicle to deviate from the preset route and it is difficult to achieve the expected effect. Therefore, once the autonomous vehicle deviates from the preset heading, it needs to be corrected in time to return to the preset route for normal driving. However, due to the many factors that cause the autonomous vehicle to deviate from the preset route, without on-site manual detection, it is difficult for the autonomous vehicle to identify the type of fault and unable to take appropriate corrective measures. Summary of the Invention

[0003] Based on this, the present application proposes an automatic trajectory correction method and system for autonomous vehicles, which can enable the autonomous vehicle to automatically identify the type of fault and make correct corrections in a timely manner.

[0004] An automatic trajectory correction method for an autonomous vehicle includes:

[0005] Step A: Determine whether the autonomous vehicle deviates from the preset route. When the autonomous vehicle deviates from the preset route, execute Step B;

[0006] Step B: Obtain the current actual attitude angle and / or driving trajectory of the autonomous vehicle; obtain the driving distances of the left and right wheels of the autonomous vehicle, and simulate the corresponding simulated attitude angle and / or simulated trajectory of the autonomous vehicle under the driving distances. Compare whether the simulated attitude angle is consistent with the actual attitude angle, and / or compare whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle is consistent with the actual attitude angle, and / or the simulated trajectory is consistent with the driving trajectory, it is determined that there is a wheel fault, and execute Step C;

[0007] Step C: Correct the wheels.

[0008] In one embodiment, Step C includes:

[0009] Step C1: Control the autonomous vehicle to return to the preset route and mark the return position, restart the wheel program, and determine whether the autonomous vehicle deviates from the preset route again from the return position. When the autonomous vehicle deviates from the preset route again at the return position, it is determined that there is a deviation angle in the wheel installation, and execute Step C2;

[0010] Step C2: Obtain the driving trajectory of the driverless vehicle after restarting the wheel program, calculate the deviation angle based on the driving trajectory, adjust the wheel program, subtract the deviation angle from the set wheel steering angle in the wheel program, and control the driverless vehicle to return to the preset route.

[0011] In one embodiment, the return position is the initial position where the driverless vehicle deviates from the preset route.

[0012] In one embodiment, step A includes:

[0013] Obtain the current actual attitude angle of the driverless vehicle and / or the driving trajectory of the driverless vehicle, compare whether the deviation between the actual attitude angle of the driverless vehicle and the preset course angle is within a preset angle range, and / or compare whether the deviation between the driving trajectory of the driverless vehicle and the preset route is within a preset distance range. When the deviation between the actual attitude angle of the driverless vehicle and the preset course angle is not within the preset angle range, and / or the deviation between the driving trajectory of the driverless vehicle and the preset route is not within the preset distance range, it is determined that the driverless vehicle deviates from the preset route.

[0014] In one embodiment, in step B, when the simulated attitude angle and the actual attitude angle are inconsistent, and / or the simulated trajectory and the driving trajectory are inconsistent, execute step D;

[0015] Step D: Obtain the road surface conditions around the driverless vehicle through the road surface detection device installed on the driverless vehicle, and determine whether there are road surface obstacles.

[0016] A driverless vehicle trajectory automatic correction system includes:

[0017] A judgment module, used to judge whether the driverless vehicle deviates from the preset route. When the driverless vehicle deviates from the preset route, trigger the analysis module;

[0018] An analysis module, used to obtain the current actual attitude angle and / or driving trajectory of the driverless vehicle, and the driving distances of the left and right wheels of the driverless vehicle. Simulate the corresponding simulated attitude angle and / or simulated trajectory of the driverless vehicle under the driving distances, compare whether the simulated attitude angle is consistent with the actual attitude angle, and / or compare whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle and the actual attitude angle are consistent, and / or the simulated trajectory and the driving trajectory are consistent, it is determined that there is a wheel failure, and trigger the correction module;

[0019] A correction module, used to correct the wheels.

[0020] In one embodiment, the correction module includes:

[0021] A restart unit, which is used to control the unmanned vehicle to return to the preset route and mark the return position, restart the wheel program, and determine whether the unmanned vehicle deviates from the preset route again from the return position. When the unmanned vehicle deviates from the preset route again at the return position, it is determined that there is a deviation angle in the wheel installation, and the angle compensation unit is triggered;

[0022] An angle compensation unit, which is used to obtain the driving trajectory of the unmanned vehicle after restarting the wheel program, calculate the deviation angle according to the driving trajectory, adjust the wheel program, subtract the deviation angle from the set wheel steering angle in the wheel program, and control the unmanned vehicle to return to the preset route.

[0023] In one embodiment, it further includes:

[0024] A road surface detection device, which is installed on the unmanned vehicle and is used to obtain the road surface conditions around the unmanned vehicle and determine whether there are road surface obstacles;

[0025] The analysis module is further used to trigger the road surface detection device when the simulated attitude angle is inconsistent with the actual attitude angle, or the simulated trajectory is inconsistent with the driving trajectory.

[0026] In one embodiment, it further includes:

[0027] A monitoring platform, which is used to mark the state of the unmanned vehicle:

[0028] When the unmanned vehicle is driving normally on the preset route, it is marked as the normal state;

[0029] When the unmanned vehicle is in the automatic correction state, it is marked as the correction state;

[0030] When the unmanned vehicle still deviates from the preset route or there are road surface obstacles after automatic correction, it is marked as the fault state.

[0031] In one embodiment, the unmanned vehicle is equipped with a gyroscope and / or a positioning device. The gyroscope is used to detect the current actual attitude angle of the unmanned vehicle, and the positioning device is used to detect the driving trajectory of the unmanned vehicle. The judgment module is used to obtain the current actual attitude angle of the unmanned vehicle and / or the driving trajectory of the unmanned vehicle according to the detection data of the gyroscope and / or the positioning device, compare whether the deviation between the actual attitude angle of the unmanned vehicle and the preset heading angle is within the preset angle range, and / or whether the deviation between the driving trajectory of the unmanned vehicle and the preset route is within the preset distance range. When the deviation between the actual attitude angle of the unmanned vehicle and the preset heading angle is not within the preset angle range, and / or the deviation between the driving trajectory of the unmanned vehicle and the preset route is not within the preset distance range, it is determined that the unmanned vehicle deviates from the preset route.

[0032] The above-mentioned automatic trajectory correction method and system for a driverless vehicle. When the driverless vehicle recognizes that it deviates from the preset route, it first simulates the simulated attitude angle and / or simulated trajectory that the driverless vehicle should have under the driving distance through the driving distance of the wheels, and then compares whether the simulated attitude angle is consistent with the actual attitude angle, and / or, compares whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle is consistent with the actual attitude angle, and / or, the simulated trajectory is consistent with the driving trajectory, it indicates that the deviation from the route is caused by a wheel failure. Therefore, the wheels can be corrected specifically, and after the wheels are corrected, the driverless vehicle can return to normal. If the result of the above simulation is inconsistent with the actual situation, it indicates that there are other types of obstacles, and even if the wheels are corrected, the driverless vehicle cannot return to normal, and other tools need to be assisted for further inspection. Brief Description of the Drawings

[0033] Figure 1 It is a flowchart of the steps of the automatic trajectory correction method for a driverless vehicle in an embodiment of the present application;

[0034] Figure 2 It is a step decomposition diagram of step S300 in an embodiment of the present application;

[0035] Figure 3 It is a flowchart of the steps of the automatic trajectory correction method for a driverless vehicle in another embodiment of the present application;

[0036] Figure 4a It is a driving state diagram of a driverless vehicle in an embodiment of the present application;

[0037] Figure 4b It is a trajectory diagram of a driverless vehicle deviating from the preset route and making a circular motion in an embodiment of the present application;

[0038] Figure 5 It is a structural block diagram of the automatic trajectory correction system for a driverless vehicle in an embodiment of the present application;

[0039] Figure 6 It is a decomposition diagram of the analysis module in an embodiment of the present application;

[0040] Figure 7 It is a structural block diagram of the automatic trajectory correction system for a driverless vehicle in another embodiment of the present application;

[0041] Figure 8 It is a structural block diagram of the automatic trajectory correction system for a driverless vehicle in yet another embodiment of the present application. Detailed Embodiments

[0042] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Preferred embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which the present invention belongs. The terms used in the description of the present invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0044] As Figure 1 described, the method for automatically correcting the trajectory of an unmanned vehicle includes the following steps:

[0045] Step S100: Determine whether the unmanned vehicle deviates from the preset route. When the unmanned vehicle deviates from the preset route, execute step S200.

[0046] As Figure 4a shown, the preset route AB is planned in advance, and the unmanned vehicle is moved to the preset route AB. The preset heading angle of the unmanned vehicle is set in advance, so that the unmanned vehicle travels from point A to point B on the preset route AB. Among them, the heading angle can specifically be the angle between a fixed reference direction. At this time, both the preset route and the preset heading angle are known data.

[0047] During the driving process, it is necessary to continuously determine whether the unmanned vehicle deviates from the preset route AB. As Figure 4a shown, when the unmanned vehicle moves to point C, the driving starts to deviate from the preset route and travels to point D outside the preset route AB. At this time, CD is the actual driving trajectory deviating from the preset route.

[0048] In one embodiment, determining whether the unmanned vehicle deviates from the preset route can be by comparing whether the deviation between the driving trajectory of the unmanned vehicle and the preset route is within a preset distance range, and the preset distance range is known data set in advance. For example, as Figure 4a shown, it can be compared whether the distance between the driving trajectory CD and the preset route AB is within the preset distance range. If it exceeds the preset distance range, it is determined that the unmanned vehicle has deviated from the preset route AB. Specifically, the driving trajectory of the unmanned vehicle can be monitored by a positioning device, and the positioning device can specifically be a GPS (Global Positioning System).

[0049] In another embodiment, to determine whether the driverless vehicle deviates from the preset route, it can also be by comparing whether the deviation between the current actual attitude angle of the driverless vehicle and the preset heading angle is within a preset angle range, and the preset angle range is known data set in advance. For example, as Figure 4a shown, the deviation between the current actual attitude angle of the driverless vehicle and the preset heading angle is the angle θ. It can be compared whether the angle θ is within the preset angle range. If it exceeds the preset angle range, it is determined that the driverless vehicle has deviated from the preset route AB. Specifically, the deviation angle θ between the current actual attitude angle of the driverless vehicle and the preset heading angle can be monitored by a gyroscope.

[0050] In other embodiments, it can also be to simultaneously compare whether the deviation between the driving trajectory of the driverless vehicle and the preset route is within a preset distance range, and compare whether the deviation between the current actual attitude angle of the driverless vehicle and the preset heading angle is within a preset angle range. If the distance between the driving trajectory and the preset route exceeds the preset distance range, and the deviation between the actual attitude angle and the preset heading angle exceeds the preset angle range, it is determined that the driverless vehicle has deviated from the preset route.

[0051] Step S200: Obtain the current actual attitude angle and / or driving trajectory of the driverless vehicle; obtain the driving distances of the left and right wheels of the driverless vehicle, and simulate the corresponding simulated attitude angle and / or simulated trajectory of the driverless vehicle under the driving distances. Compare whether the simulated attitude angle is consistent with the actual attitude angle, and / or compare whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle is consistent with the actual attitude angle, and / or the simulated trajectory is consistent with the driving trajectory, it is determined that there is a wheel failure, and step C is executed.

[0052] In this step, it is necessary to obtain the driving distance of the wheel, and based on this driving distance of the wheel, simulate the simulated attitude angle and / or simulated trajectory corresponding to this driving distance for the driverless vehicle. Among them, the driving distance of the wheel is equal to the number of revolutions of the wheel multiplied by the outer circumference of the wheel. If the reason for the driverless vehicle deviating from its course is only due to wheel problems, such as the wheel being skewed or the wheel program malfunctioning, at this time, the simulated attitude angle simulated based on the driving distance of the wheel should be consistent with the actual attitude angle, and the simulated trajectory simulated should be consistent with the actual driving trajectory. In one embodiment, it is possible to only compare whether the simulated attitude angle is consistent with the actual attitude angle. If they are consistent, it indicates a wheel failure. In another embodiment, it is also possible to only compare whether the simulated trajectory is consistent with the actual driving trajectory. If they are consistent, it indicates a wheel failure. Of course, it is also possible to simultaneously compare whether the simulated attitude angle is consistent with the actual attitude angle and compare whether the simulated trajectory is consistent with the actual driving trajectory. If all are consistent, it indicates a wheel failure. In the above embodiments, if the judgment result is inconsistent, it indicates that there are other reasons causing the driverless vehicle to deviate from the preset route, and correcting the wheels cannot make the driverless vehicle resume normal driving, and further judgment is required. Specifically, the driving distance of the corresponding wheel can be monitored by an odometer installed on the wheel.

[0053] Step S300: Correct the wheel.

[0054] Through the above step S200, it can be determined that the type of failure causing the driverless vehicle to deviate from its route is a wheel failure. Therefore, it is only necessary to specifically correct the wheel.

[0055] Specifically, wheel failures are divided into two types. The first type of wheel failure is a wheel program error, that is, the preset course angle written in the wheel program is tampered with. For example, in the initial state, the preset course angle written in the wheel program is 0°, and during driving, the preset course angle in the wheel program is tampered with to 5°, resulting in the driverless vehicle deviating from its route. The second type of wheel failure is that the wheel is skewed, that is, there is a deviation angle in the wheel installation. For example, the wheel steering angle written in the wheel program is correct, but due to the incorrect installation position of the wheel, such as the wheel being skewed to the right. For example, the wheel steering angle written in the wheel program is 0°, that is, the driverless vehicle keeps going straight, but due to the wheel being skewed to the right, such as the deviation angle to the right being 1°. At this time, according to the program instruction, the driverless vehicle should go straight, but in fact, due to the wheel being skewed, the movement trajectory of the driverless vehicle is as Figure 4b shown as a circle. Therefore, for the correction of the wheel, it is to correct the wheel program and the wheel installation angle.

[0056] In one embodiment, the wheel can be corrected through the following sub-steps:

[0057] Step S310: Control the driverless vehicle to return to the preset route and mark the return position, restart the wheel program, and determine whether the driverless vehicle deviates from the preset route again from the return position. When the driverless vehicle deviates from the preset route again at the return position, it is determined that there is a deviation angle in the wheel installation, and step S320 is executed.

[0058] When a wheel correction instruction is received, control the driverless vehicle to return to the preset route and mark the return position of the driverless vehicle on the preset route, restart the wheel program, and initialize the wheel program parameters. If there is a wheel program failure in the above-mentioned failure, after restarting the wheel program, the program can be restored to normal. After restarting the program, the driverless vehicle continues to move forward from the return position. At this time, it is necessary to continue to monitor whether the driverless vehicle will still deviate from the preset route. If the driving of the driverless vehicle returns to normal after restarting the wheel program, it means that the above-mentioned wheel failure is only a wheel program failure, and the correction is completed, and the driverless vehicle continues to move forward; if the driverless vehicle still deviates from the preset route after restarting the wheel program, it means that there are other failures in the above-mentioned wheel failure, and step S320 needs to be executed for further correction. Further, the above return position can be the initial position where the driverless vehicle deviates from the preset route. For example Figure 1 As shown, when the driverless vehicle deviates from point C, during the correction process of this step, the return position is also point C, so that the reason for the deviation of the driverless vehicle at point C can be analyzed more accurately.

[0059] Step S320: Obtain the driving trajectory of the driverless vehicle after restarting the wheel program, calculate the deviation angle according to the driving trajectory, adjust the wheel program, subtract the deviation angle from the set wheel steering angle in the wheel program, and control the driverless vehicle to return to the preset route.

[0060] When restarting the wheel program cannot fully restore the driverless vehicle, it is necessary to consider whether the wheels are skewed. Therefore, in step S320, the driverless vehicle automatically detects whether the wheels are skewed and corrects them according to the degree of skewness. When the wheels are skewed, the driverless vehicle moves in a circular motion, such as Figure 4bAs shown, the circular trajectory of the driverless vehicle during circular motion can be obtained through the positioning device, and the radius of the circle can be calculated. Based on the radius of the circle, the actual steering angle of the wheels can be simulated. Assuming the initially set steering angle is α1 and the actual steering angle is α2, the difference between the actual steering angle and the steering angle set in the wheel program can be calculated to obtain the deviation angle Δα = α2 - α1. Then, the set steering angle can be revised, and the steering angle in the program after revision is α3 = α1 - Δα. After correcting the steering angle set in the wheel program, the actual driving angle of the driverless vehicle conforms to the preset course angle. For example, the steering angle set in the wheel program is 0°, and α1 = 0°, that is, the driverless vehicle keeps going straight. However, since the wheel is skewed 1° to the right, that is, Δα = 1°, the driverless vehicle always makes a circular motion to the right. By correcting the steering angle in the program, a new steering angle α3 = α1 - Δα = -1° is obtained, that is, the steering angle set in the program is compensated 1° to the left, so that the driverless vehicle actually goes straight.

[0061] In other embodiments, the wheels can also be corrected in other ways, as long as the wheel program and the wheel installation angle are restored to normal.

[0062] In one embodiment, in step S200, when the simulated attitude angle is inconsistent with the actual attitude angle, and / or the simulated trajectory is inconsistent with the driving trajectory, then jump to execute the following step S400;

[0063] Step S400: Obtain the road surface conditions around the driverless vehicle through the road surface detection device installed on the driverless vehicle, and determine whether there are road surface obstacles.

[0064] During the process of judging the fault category in step S200, if the judgment result indicates that there are other faults other than wheel faults, even if step S300 is executed, it cannot be restored to normal and further identification is required. Usually, for the faults that cause the driverless vehicle to deviate from the preset route, in addition to wheel faults, there may also be road surface obstacles. For example, the driverless vehicle hits a road surface obstacle and is lifted and drifts. In step S400, specifically, the road surface conditions around the driverless vehicle are obtained through the road surface detection device installed on the driverless vehicle, and it is judged whether there are road surface obstacles at the position where the route deviation occurs. This road surface detection device can specifically be a camera. Once it is determined that there are road surface obstacles, human intervention is required to remove the road surface obstacles, or re-plan the preset route, or the route can also be automatically adjusted so that the driverless vehicle can avoid the obstacles and return to the preset route to continue moving forward.

[0065] In the above-mentioned automatic correction method for the trajectory of an unmanned vehicle, when the unmanned vehicle recognizes that it has deviated from the preset route, it first simulates the simulated driving process that the unmanned vehicle should have under the driving distance through the driving distance of the wheels, and compares the simulated driving process with the actual driving process. When the two are consistent, it means that the deviation from the route is caused by a wheel failure. Therefore, the wheels can be corrected in a targeted manner, and after the wheels are corrected, the unmanned vehicle can be restored to normal. If the results of the above simulation are inconsistent with the actual situation, it means that there are other types of obstacles. Even if the wheels are corrected, the unmanned vehicle cannot be restored to normal, and other tools are needed for further inspection.

[0066] The present application also relates to the following unmanned vehicle trajectory automatic correction system.

[0067] like Figure 5 As shown, the unmanned vehicle trajectory automatic correction system includes a judgment module 100, an analysis module 200 and a correction module 300 which are communicatively connected in sequence.

[0068] The judgment module 100 is used to judge whether the unmanned vehicle deviates from the preset route. When the unmanned vehicle deviates from the preset route, the analysis module 200 is triggered.

[0069] The analysis module 200 is used to obtain the current actual attitude angle and / or driving trajectory of the unmanned vehicle and the driving distance of the left and right wheels of the unmanned vehicle, simulate the simulated attitude angle and / or simulated trajectory corresponding to the driving distance according to the driving distance, compare whether the simulated attitude angle is consistent with the actual attitude angle, and / or compare whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle is consistent with the actual attitude angle, and / or the simulated trajectory is consistent with the driving trajectory, it is determined to be a wheel fault and the correction module 300 is triggered.

[0070] The correction module 300 is used to correct the wheel.

[0071] In one embodiment, if Figure 6 As shown, the correction module 300 includes a restart unit 310 and an angle compensation unit 320 .

[0072] Among them, the restart unit 310 is used to control the unmanned vehicle to return to the preset route and mark the return position, restart the wheel program, and determine whether the unmanned vehicle deviates from the preset route again from the return position. When the unmanned vehicle deviates from the preset route again at the return position, it is determined that there is a deviation angle in the wheel installation and the angle compensation unit 320 is triggered.

[0073] The angle compensation unit 320 is used to obtain the driving trajectory of the unmanned vehicle after restarting the wheel program, calculate the deviation angle according to the driving trajectory, adjust the wheel program, subtract the deviation angle from the wheel steering angle set in the wheel program, and control the unmanned vehicle to return to the preset route.

[0074] In one embodiment, as Figure 7 shown, the above system further includes a road surface detection device 400 installed on the driverless vehicle. The road surface detection device 400 is used to obtain the road surface conditions around the driverless vehicle and determine whether there are road surface obstacles. Specifically, the road surface detection device 400 can be a camera. The above analysis module 200 is communicatively connected to the road surface detection device 400 and is used to trigger the road surface detection device 400 when the simulated attitude angle is inconsistent with the actual attitude angle, or the simulated trajectory is inconsistent with the driving trajectory.

[0075] In one embodiment, as Figure 7 shown, the above system further includes a monitoring platform 500. The monitoring platform 500 is used to mark the state of the driverless vehicle: when the driverless vehicle is driving normally on the preset route, it is marked as the normal state; when the driverless vehicle is in the automatic correction state, it is marked as the correction state; when the driverless vehicle still deviates from the preset route or there are road surface obstacles after automatic correction, it is marked as the fault state.

[0076] In one embodiment, as Figure 8 shown, a gyroscope 610 and / or a positioning device 620 are installed on the driverless vehicle. The gyroscope 610 is used to detect the current actual attitude angle of the driverless vehicle, and the positioning device 620 is used to detect the driving trajectory of the driverless vehicle. The judgment module 100 is used to obtain the current actual attitude angle of the driverless vehicle and / or the driving trajectory of the driverless vehicle according to the detection data of the gyroscope 610 and / or the positioning device 620, and compare whether the deviation between the actual attitude angle of the driverless vehicle and the preset course angle is within the preset angle range, and / or whether the deviation between the driving trajectory of the driverless vehicle and the preset route is within the preset distance range. When the deviation between the actual attitude angle of the driverless vehicle and the preset course angle is not within the preset angle range, and / or the deviation between the driving trajectory of the driverless vehicle and the preset route is not within the preset distance range, it is determined that the driverless vehicle deviates from the preset route.

[0077] In one embodiment, continue to refer to Figure 8 , odometers 630 are installed on both the left and right wheels of the driverless vehicle. The odometers 630 are used to measure the driving distances of the corresponding wheels. The analysis module 200 is used to obtain the driving distances of the left and right wheels of the driverless vehicle according to the measurement data of the odometers 630, and obtain the current actual attitude angle of the driverless vehicle according to the detection data of the gyroscope 610, and / or obtain the driving trajectory of the driverless vehicle according to the detection data of the positioning device 620.

[0078] Specifically, the working process of the above system can refer to the detailed introduction in the above driverless vehicle trajectory automatic correction method, which will not be elaborated here.

[0079] The above embodiments merely illustrate several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. An automatic trajectory correction method for an unmanned vehicle, characterized in that, Including: Step A: Determine whether the driverless vehicle deviates from the preset route. When the driverless vehicle deviates from the preset route, execute Step B; Step B: Obtain the current actual attitude angle and / or driving trajectory of the driverless vehicle; obtain the driving distances of the left and right wheels of the driverless vehicle, simulate the corresponding simulated attitude angle and / or simulated trajectory of the driverless vehicle under the driving distances, compare whether the simulated attitude angle is consistent with the actual attitude angle, and / or compare whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle is consistent with the actual attitude angle, and / or the simulated trajectory is consistent with the driving trajectory, it is determined that there is a wheel failure, and execute Step C; Step C: Correct the wheels; The said Step C includes: Step C1: Control the driverless vehicle to return to the preset route and mark the return position, restart the wheel program, and determine whether the driverless vehicle deviates from the preset route again from the return position. When the driverless vehicle deviates from the preset route again at the return position, it is determined that there is a deviation angle in the wheel installation, and execute Step C2; Step C2: Obtain the driving trajectory of the driverless vehicle after restarting the wheel program, calculate the deviation angle according to the driving trajectory, adjust the wheel program, subtract the deviation angle from the set wheel steering angle in the wheel program, and control the driverless vehicle to return to the preset route.

2. The method according to claim 1, characterized in that, The said return position is the initial position where the driverless vehicle deviates from the preset route.

3. The method according to claim 1, characterized in that, The said Step A includes: Obtain the current actual attitude angle and / or the driving trajectory of the driverless vehicle, compare whether the deviation between the actual attitude angle of the driverless vehicle and the preset heading angle is within the preset angle range, and / or compare whether the deviation between the driving trajectory of the driverless vehicle and the preset route is within the preset distance range. When the deviation between the actual attitude angle of the driverless vehicle and the preset heading angle is not within the preset angle range, and / or the deviation between the driving trajectory of the driverless vehicle and the preset route is not within the preset distance range, it is determined that the driverless vehicle deviates from the preset route.

4. The method according to claim 1, characterized in that, In the said Step B, when the simulated attitude angle is not consistent with the actual attitude angle, and / or the simulated trajectory is not consistent with the driving trajectory, execute Step D; Step D: Obtain the road surface condition around the driverless vehicle through the road surface detection device installed on the driverless vehicle, and determine whether there are road surface obstacles.

5. An automatic trajectory correction system for an unmanned vehicle, characterized in that, Including: A judgment module, used to judge whether the driverless vehicle deviates from the preset route. When the driverless vehicle deviates from the preset route, trigger the analysis module; An analysis module, used to obtain the current actual attitude angle and / or driving trajectory of the driverless vehicle, the driving distances of the left and right wheels of the driverless vehicle, simulate the corresponding simulated attitude angle and / or simulated trajectory of the driverless vehicle under the driving distances, compare whether the simulated attitude angle is consistent with the actual attitude angle, and / or compare whether the simulated trajectory is consistent with the driving trajectory. When the simulated attitude angle is consistent with the actual attitude angle, and / or the simulated trajectory is consistent with the driving trajectory, it is determined that there is a wheel failure, and trigger the correction module; A correction module, used to correct the wheels; The said correction module includes: A restart unit, which is used to control the unmanned vehicle to return to the preset route and mark the return position, restart the wheel program, and determine whether the unmanned vehicle deviates from the preset route again from the return position. When the unmanned vehicle deviates from the preset route again at the return position, it is determined that there is a deviation angle in the wheel installation, and the angle compensation unit is triggered; An angle compensation unit, which is used to obtain the driving trajectory of the unmanned vehicle after restarting the wheel program, calculate the deviation angle according to the driving trajectory, adjust the wheel program, subtract the deviation angle from the set wheel steering angle in the wheel program, and control the unmanned vehicle to return to the preset route.

6. The system according to claim 5, characterized in that, It further includes: A road surface detection device, which is installed on the unmanned vehicle and is used to obtain the road surface conditions around the unmanned vehicle and determine whether there are road surface obstacles; The analysis module is further used to trigger the road surface detection device when the simulated attitude angle is inconsistent with the actual attitude angle, or the simulated trajectory is inconsistent with the driving trajectory.

7. The system according to claim 5, characterized in that, It further includes: A monitoring platform, which is used to mark the state of the unmanned vehicle: When the unmanned vehicle is driving normally on the preset route, it is marked as the normal state; When the unmanned vehicle is in the automatic correction state, it is marked as the correction state; When the unmanned vehicle still deviates from the preset route or there are road surface obstacles after automatic correction, it is marked as the fault state.

8. The system according to claim 5, characterized in that, The unmanned vehicle is equipped with a gyroscope and / or a positioning device. The gyroscope is used to detect the current actual attitude angle of the unmanned vehicle, and the positioning device is used to detect the driving trajectory of the unmanned vehicle. The judgment module is used to obtain the current actual attitude angle of the unmanned vehicle and / or the driving trajectory of the unmanned vehicle according to the detection data of the gyroscope and / or the positioning device, and compare whether the deviation between the actual attitude angle of the unmanned vehicle and the preset heading angle is within the preset angle range, and / or whether the deviation between the driving trajectory of the unmanned vehicle and the preset route is within the preset distance range. When the deviation between the actual attitude angle of the unmanned vehicle and the preset heading angle is not within the preset angle range, and / or the deviation between the driving trajectory of the unmanned vehicle and the preset route is not within the preset distance range, it is determined that the unmanned vehicle deviates from the preset route.

Images