Electronic map grid determination method and control system

Abstract

The invention provides an electronic map grid determination method and a control system. The method comprises the following steps: acquiring respective precision values of a plurality of sensors related to displacement in the intelligent trolley and a plurality of random position deviation values of a plurality of error sources; and determining the range of the grid size of the driving electronic map based on the plurality of random position deviation values of the plurality of error sources and the precision values of the plurality of sensors. According to the method, the total fluctuation range of the error value is constrained in the grid size, and redundancy is reserved to cope with error increase caused by environment change and prevent the error range from overflowing the grid, so that the complexity of data processing can be simplified, and the data processing efficiency and reliability can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent navigation, in particular to a method for determining the grid of an electronic map and a control system. BACKGROUND

[0002] Intelligent Guided Vehicle (IGV for short) is an unmanned transport device used in automated ports and smart factories, which realizes autonomous navigation and obstacle avoidance through Beidou navigation system, laser radar, visual SLAM technology, etc. It has high flexibility, intelligent navigation and excellent performance. IGV usually walks according to the navigation information provided by the two-dimensional code belt or matrix two-dimensional code.

[0003] At present, in order to deal with the interference of complex environment (such as ground wet caused by back-to-south days) on IGV driving, a driving electronic map is used to provide auxiliary driving information for IGV, so as to quickly and effectively pass through the complex environment. The driving electronic map is a grid electronic map. The driving electronic map includes an ideal kinematic model, which is a series of normal data obtained when the intelligent car drives on the navigation path in an ideal state, so as to improve the accurate management of IGV driving.

[0004] However, if the grid is too small, the calculation amount will be too large; if the grid is too large, the correction accuracy will be reduced.

[0005] Therefore, the present application provides a method for determining the grid of an electronic map to solve the above technical problems. SUMMARY

[0006] The purpose of the present application is to provide a method for determining the grid of an electronic map and a control system, which can solve at least one of the above technical problems. The specific scheme is as follows: According to the specific embodiment of the present application, in a first aspect, the present application provides a method for determining the grid of an electronic map, comprising: obtaining the accuracy value of each of a plurality of sensors related to displacement in an intelligent car and a plurality of random position deviation values of each of a plurality of error sources; determining the range of the grid size of the driving electronic map based on the plurality of random position deviation values of each of the plurality of error sources and the accuracy value of each of the plurality of sensors.

[0007] Optionally, the method for determining the grid size of the driving electronic map based on the plurality of random position deviation values of each of the plurality of error sources and the accuracy value of each of the plurality of sensors comprises: obtaining the error standard deviation based on the plurality of random position deviation values of each of the plurality of error sources; obtaining a lower limit value of the grid size based on the error standard deviation; obtaining an upper limit value of the grid size based on the error standard deviation and the accuracy value of each of the plurality of sensors.

[0008] Optionally, the obtaining of the lower limit value of the grid size based on the error standard deviation comprises: determining a lower limit error fluctuation range of the grid size based on a minimum error coverage probability of the error standard deviation; determining the lower limit value of the grid size based on the lower limit error fluctuation range of the grid size.

[0009] Optionally, the lower limit error fluctuation range is [- σ , + σ ], wherein, σ denotes the error standard deviation.

[0010] Optionally, the obtaining of the upper limit value of the grid size based on the error standard deviation and the accuracy value of each of the plurality of sensors comprises: determining a minimum accuracy value based on the accuracy value of each of the plurality of sensors; obtaining a first experience value based on a preset accuracy integer multiple of the maximum accuracy value, and obtaining a second experience value based on a maximum error coverage probability of the error standard deviation, wherein the maximum error coverage probability is greater than the minimum error coverage probability; determining the upper limit value of the grid size based on a maximum value of the first experience value and the second experience value.

[0011] Optionally, the preset accuracy integer multiple is equal to 5.

[0012] Optionally, the upper limit value of the grid size is equal to 5 σ , wherein, σ denotes the error standard deviation.

[0013] Optionally, the method further comprises: when the navigation path of the driving electronic map is represented as a dry straight section, dividing the grid by using the upper limit value of the grid size; when the navigation path of the driving electronic map is represented as a curved section or a wet and slippery section, dividing the grid by using the lower limit value of the grid size.

[0014] Optionally, the plurality of error sources include the intelligent car and the sensors.

[0015] According to the specific embodiment of the present application, in a second aspect, the present application provides a control system for controlling an intelligent car, comprising: The group control device stores a driving electronic map, and determines the range of the grid size of the driving electronic map according to the method described above; The host computer controls the smart car to travel according to the driving electronic map.

[0016] Compared with the prior art, the above scheme of the embodiments of the present application has at least the following beneficial effects: The present application provides a method and a control system for determining the grid of an electronic map. The present application obtains the accuracy values of a plurality of sensors related to displacement in a smart car and a plurality of random position deviation values of a plurality of error sources; determines the range of the grid size of the driving electronic map based on the plurality of random position deviation values of the plurality of error sources and the accuracy values of the plurality of sensors. The total fluctuation range of the error values is constrained within the grid size, and redundancy is reserved to cope with the increase in error caused by environmental changes, avoiding the overflow of the error range out of the grid, thereby simplifying the complexity of data processing, improving the efficiency and reliability of data processing. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 A flowchart of a method for determining the grid of an electronic map according to an embodiment of the present application is shown; Figure 2 A device schematic block diagram of a control system according to an embodiment of the present application is shown; REFERENCE SIGNS: 11 - group control device, 12 - host computer, 13 - smart car. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be described in further detail below with reference to the drawings. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0019] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. "Multiple" generally includes at least two.

[0020] It should be understood that the term "and / or" used herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone. In addition, the character " / " in this paper generally represents that the front and rear associated objects are in an "or" relationship.

[0021] It should be understood that although the terms first, second, third, etc., may be used in the embodiments of this application, these descriptions should not be limited to these terms. These terms are only used to distinguish the descriptions. For example, first may also be referred to as second without departing from the scope of the embodiments of this application, and similarly, second may also be referred to as first.

[0022] Depending on the context, the words “if” or “suppose” as used here can be interpreted as “when” or “in response to determination” or “in response to detection.” Similarly, depending on the context, the phrases “if determination” or “if detection (of the stated condition or event)” can be interpreted as “when determination” or “in response to determination” or “when detection (of the stated condition or event)” or “in response to detection (of the stated condition or event).”

[0023] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that an article or device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such an article or device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the article or device that includes said element.

[0024] It should be noted that any symbols and / or numbers present in the specification that are not marked in the accompanying drawings are not reference numerals.

[0025] The optional embodiments of this application are described in detail below with reference to the accompanying drawings.

[0026] The embodiments provided in this application are embodiments of a method for determining an electronic map grid.

[0027] The following is combined Figure 1 The embodiments of this application will be described in detail.

[0028] Step S101: Obtain the accuracy values ​​of multiple sensors related to displacement inside the intelligent vehicle and the multiple random position deviation values ​​of various error sources.

[0029] The intelligent vehicle can be an Automated Guided Vehicle (AGV) or an Infinite Vehicle (IGV).

[0030] The multiple displacement-related sensors inside the intelligent vehicle can be understood as sensors that measure changes in position, such as inertial measurement units and wheel speed encoders.

[0031] An Inertial Measurement Unit (IMU) is a device that measures the three-axis attitude angles (or angular rates) and acceleration of an object. An IMU contains three single-axis accelerometers and three single-axis gyroscopes. The accelerometers detect the acceleration signals of the object along the three independent axes of the carrier's coordinate system, while the gyroscopes detect the angular velocity signals of the carrier relative to the navigation coordinate system. By measuring the object's angular velocity and acceleration in three-dimensional space, the object's position and attitude can be calculated.

[0032] The wheel speed encoder collects linear velocity, mileage, and angular velocity information of the intelligent vehicle's wheels. The accuracy of these data (linear velocity, mileage, and angular velocity) allows determination of the positional deviation within the sampling period.

[0033] The accuracy of a sensor is essentially represented by its error value.

[0034] In some specific embodiments, the multiple sources of error include the smart car and multiple displacement-related sensors within the smart car.

[0035] A driving electronic map is a gridded electronic map. It includes an ideal kinematic model, which is a series of normal data obtained when the intelligent vehicle travels along the navigation path in an ideal state.

[0036] An ideal state is a perfect state in which all conditions and outcomes are optimal. In this embodiment, the ideal state refers to the state where the intelligent vehicle is driving normally under normal ground conditions. The driving electronic map establishes an ideal kinematic model by recording the standard motion parameters (such as linear velocity, angular velocity, and turning radius) of the drive wheels within each grid during multiple normal driving cycles of the intelligent vehicle. If there is no environmental interference, the intelligent vehicle can drive normally along the navigation path. In this case, the intelligent vehicle does not need the driving electronic map to identify ground conditions, nor does it need to rely on the driving electronic map for assistance; it can drive autonomously. If the environment is abnormal, the intelligent vehicle needs to use the driving electronic map to identify ground conditions and, with its assistance, compensate for the driving commands, adjusting the drive wheel values ​​to safely and reliably pass through abnormal areas. Simultaneously, it provides the driving data and environmental data of safe passage to the driving electronic map, enabling the driving electronic map to improve its adaptability to the environment through self-learning and updating capabilities, and adding an online update mechanism. This allows subsequent vehicles to quickly identify ground anomalies, eliminate abnormal interference, and pass through the interfering environment as quickly as possible, thereby improving driving efficiency.

[0037] Once the system confirms that there are no anomalies on the ground over a long period of time, new reliable data can be integrated into the driving electronic map with certain weights (such as exponential smoothing), enabling the system to adapt to long-term, slow changes such as normal wear and tear on the ground.

[0038] Each grid in the driving electronic map stores environment-related data in its attribute information. For example, each grid's attribute information includes, but is not limited to, grid coordinates, a historical set of slippage probabilities for multiple smart cars within that grid, and conditional information such as the smart car's load value and straight-line speed, environmental context data, and grid topology relationships. Environmental context data includes the timestamp of data collection, ambient temperature and humidity, smart car identification, smart car load value, straight-line speed value, and driving direction; this forms the basis for calculating high-precision conditional confidence. Grid topology relationships record information about adjacent grids, supporting the analysis of anomaly area diffusion. The driving electronic map creates a digital twin driving model for the smart cars, containing information on the impact of environmental physical characteristics on vehicle movement, thus enabling the smart cars to "memorize" complex environments.

[0039] The position deviation value refers to the error value relative to a standard position value. In this application embodiment, the range of grid size for driving the electronic map is determined by obtaining error values ​​related to the intelligent vehicle from multiple angles. The position value is represented by coordinates in a preset planar coordinate system, such as a world coordinate system or a global coordinate system.

[0040] The positional deviation values ​​generated by various error sources are random.

[0041] The multiple random positional deviations from various error sources were obtained through extensive experimental data. These errors are random, cannot be completely eliminated, and conform to the most common normal distribution (i.e., Gaussian distribution) in engineering.

[0042] The random position deviation of the intelligent vehicle is determined by its mechanical structure. For example, when the intelligent vehicle is traveling in a straight line, if the linear velocity of one drive wheel differs from that of the other drive wheels, the vehicle will exhibit a position deviation. For instance, in testing the random position deviation of the intelligent vehicle, a standard straight-line trajectory from point A to point B is established in the grid. However, in the test, after starting from point A, the vehicle travels along a curved trajectory, reaching point C. The first position coordinates at time t1 on the standard straight-line trajectory are (23 cm, 58 cm), and the second position coordinates at time t1 on the curved trajectory are (23 cm, 60 cm). Therefore, at time t1, the position deviation of the first coordinate axis is 0 cm, and the position deviation of the second coordinate axis is 3 cm. According to the Pythagorean theorem, the square root of the sum of the squares of the position deviations of the first and second coordinate axes is taken to obtain the position deviation value at time t1, which is 3 cm. Multiple random position deviation values ​​are obtained through multiple samplings within the grid.

[0043] The random position deviation of a sensor is determined by random noise. Sensor random noise refers to random fluctuations in non-target information in the output signal, mainly caused by factors such as electron thermal motion, material defects, and environmental interference. Sensor random noise includes random noise from the inertial measurement unit and random noise from the wheel speed encoder.

[0044] For example, in testing the random position deviation of sensors, if the inertial measurement unit (IMU) drifts, at time t2 within a preset time period, the IMU calculates the third position coordinates of the smart car as (25 cm, 60 cm), while the standard position coordinates at time t2 are (25 cm, 65 cm). Therefore, at time t2 in the preset plane coordinate system, the position deviation of the first coordinate axis is 0 cm, and the position deviation of the second coordinate axis is 5 cm. Using the same position deviation algorithm as before, the position deviation at time t2 is 5 cm. For example, if the standard wheel radius of the smart car is r = 0.05 m, the wheel speed encoder resolution is PPR = 500 lines / revolution, the sampling time Δt = 0.01 seconds, and N = 100 pulses are counted within Δt, the standard angular velocity information ω = (N × 2π) / (PPR × Δt) = (100 × 2 × 3.1416) / (500 × 0.01) = 628.32 / 5 = 125.664 rad / s; Standard linear velocity information v=ωⅹr=125.664ⅹ0.05=6.2832 m / s; Factors affecting the accuracy of the wheel speed encoder include inaccurate wheel radius, slippage and / or freewheeling. If the actual wheel radius r = 0.048m, the actual linear velocity information v=ωⅹr=125.664ⅹ0.048=6.0319 m / s, then the position deviation per second = 6.2832-6.0319= 0.2513m / s, and the position deviation during the sampling time = 0.2513ⅹ0.01=0.002513m.

[0045] Step S102: Determine the range of grid size for driving the electronic map based on the multiple random position deviation values ​​of each of the multiple error sources and the accuracy values ​​of each of the multiple sensors.

[0046] In engineering, according to the Central Limit Theorem, when the sample size is large enough, the random position deviation value will approach a normal distribution. This application's embodiments design the range of grid size based on the sensor's accuracy and the random position deviation values ​​from various error sources, controlling errors to occur within the grid, reducing the probability of cross-grid occurrences, reducing the additional computational load caused by cross-grid evaluation, and improving the driving efficiency of the grid-based intelligent vehicle.

[0047] In some specific embodiments, determining the range of grid sizes for driving the electronic map based on the multiple random location deviation values ​​of each of the multiple error sources and the accuracy values ​​of each of the multiple sensors includes: Step S102-1: Obtain the standard deviation of the error based on the multiple random position deviation values ​​of each of the various error sources.

[0048] In this specific embodiment, since multiple error sources (such as the intelligent vehicle and sensors) are all related to the position deviation value of the intelligent vehicle and can cause position deviations when the intelligent vehicle is moving, multiple random position deviation values ​​from each of the various error sources are included in the calculation range of the error standard deviation, reflecting the objectivity of the error standard deviation. For example, continuing the above example, the random position deviation value of the intelligent vehicle is 3cm, the random position deviation value of the inertial measurement unit is 5cm, and the random position deviation value of the wheel speed encoder is 0.002513m = 0.2513cm. μ If the error is zero, then the standard deviation is 2.384 cm. This example only uses three error sources, with each source using only one random position deviation value. In practical applications, a large number of random position deviation values ​​from the intelligent vehicle, the inertial measurement unit, the wheel speed encoder, and other error sources will be used to calculate the standard deviation. This demonstrates the objectivity of the standard deviation.

[0049] Because the error values ​​generated by multiple error sources are random, and the multiple random position deviations of each of these error sources tend to approximate a normal distribution (i.e., a Gaussian distribution), this specific embodiment converts the multiple random position deviations of each of the multiple error sources into the standard deviation of the error, that is, the standard deviation of the random error when the intelligent vehicle travels within a single grid.

[0050] Error standard deviation σ Used to measure the degree of dispersion of error, i.e. σ The smaller the value, the more concentrated the error becomes. μ (The mean of the error) σ The larger the value, the greater the error. μ The further away the mean error is, the better. Since the error fluctuates randomly (i.e., without systematic bias), therefore, determining... μ =0 (meaning the error fluctuates around the unbiased ideal value).

[0051] Step S102-2: Obtain the lower limit value of the grid size based on the error standard deviation.

[0052] The lower limit of the grid size is used to constrain the total fluctuation range of the error to not exceed the grid size. By confining the total fluctuation range of the error value within the grid size and reserving redundancy, we can cope with the increase in error caused by environmental changes (such as the humid season) and prevent the error range from overflowing the grid. This simplifies the complexity of data processing and improves data processing efficiency and reliability.

[0053] In some specific embodiments, obtaining the lower limit value of the grid size based on the error standard deviation includes: Step S102-21: Determine the lower limit error fluctuation range of the grid size based on the minimum error coverage probability of the error standard deviation.

[0054] Based on the 3σ principle of normal distribution: for μ The error follows a normal distribution with a value of 0. ‍x Falling in different σ The error coverage probabilities within the range are shown in Table 1 below: Table 1 Error range [- σ ,+ σ This only covers about 2 / 3 of the errors, with low confidence. Nearly 1 / 3 of the errors will exceed this range, causing the intelligent car to easily run off the grid; the error range is [-2]. σ +2 σ The error coverage exceeds 95%, indicating a high confidence level. Less than 5% of the error may be outside the acceptable range, which is acceptable in engineering. The error range is [-3]. σ +3 σ This covers almost all errors (with only a 0.27% probability of exceeding the limit). The above three error ranges can all be used as the lower limit error fluctuation range for the stated grid size. Specifically, 68.27% represents the minimum error coverage probability, and 99.73% represents the maximum error coverage probability.

[0055] Ideally, the intelligent car's straight-line travel route starts from the midpoint of one edge of the grid and travels to the midpoint of the opposite edge. However, in actual travel, positional deviations will occur. Due to the randomness of the positional deviation, the midpoint of the opposite edge is used as a reference point, and an allowable error fluctuation range is determined on both sides of the reference point, i.e., the grid edge length L = 2d, where d represents the half-width value of the grid edge. When 2d = 2... σ At that time, based on 2 σ The lower limit error fluctuation range of the grid size is determined, that is, the lower limit error fluctuation range of the grid size is [- σ ,+ σ When 2d = 4 σ At that time, based on 4 σ The lower limit error fluctuation range of the grid size is determined, that is, the lower limit error fluctuation range of the grid size is [-2]. σ +2 σ When 2d = 6 σ At that time, based on 6 σ The lower limit error fluctuation range of the grid size is determined, that is, the lower limit error fluctuation range of the grid size is [-3]. σ +3 σ This specific embodiment is not limited thereto.

[0056] For example, ifσ If the error is 20 cm, then the error range [-20 cm, +20 cm] only covers about 2 / 3 of the errors, with low confidence. Nearly 1 / 3 of the errors will exceed this range, causing the intelligent car to easily run off the grid. The error range [-40 cm, +40 cm] covers more than 95% of the errors, with high confidence. Less than 5% of the errors may exceed the range, which is acceptable in engineering. The error range [-60 cm, +60 cm] covers almost all errors (with only a 0.27% probability of exceeding the range). All three error ranges can be used as the lower limit error fluctuation range of the grid size.

[0057] In some specific embodiments, the lower limit error fluctuation range is [- σ ,+ σ ].

[0058] in, σ It represents the standard deviation of the error.

[0059] When the grid size L is greater than or equal to 6σ, the lower limit error fluctuation range of the grid size is [-3]. σ +3 σ The confidence level is too high at 99.73%, resulting in an excessively large grid size. This leads to the loss of details in the driving electronic map, which in turn sacrifices grid accuracy and affects the efficiency of accuracy correction and precise control of the intelligent vehicle.

[0060] As shown in Table 1, when the grid size L equals 2σ, even with an error coverage probability of 68.27%, the lower limit error fluctuation range of the grid size is [- σ ,+ σ This only results in the intelligent vehicle having a greater than 31.73% probability of exceeding the grid size L, causing the error constraint of the gridded driving electronic map to fail. Compared with the 50% error coverage probability, the lower limit error fluctuation range ensures that at least 2 / 3 of the error can occur within the grid.

[0061] For example, continuing with the example above, σ =20 cm. If the lower limit error fluctuation range of the grid size is [-60 cm, +60 cm], then the grid size is equal to 120 cm, which is too high with a confidence level of 99.73%, making the grid size too large. If the lower limit error fluctuation range of the grid size is [-20 cm, +20 cm], then when the grid size is equal to 40 cm, a 68.27% error coverage probability is guaranteed.

[0062] Step S102-22: Determine the lower limit value of the grid size based on the lower limit error fluctuation range of the grid size.

[0063] This specific embodiment uses the lower limit error fluctuation range of the aforementioned grid size [- σ ,+σ ], Select 2 σ As the maximum acceptable error value, it meets the requirement of the minimum grid size, that is, the lower limit of the grid size is equal to the maximum acceptable error value, so that the error coverage probability is close to 68.27%, while exceeding 50% confidence level. It balances confidence level, reserves redundancy, and meets the efficiency and precise control of grid accuracy and accuracy correction of intelligent vehicles.

[0064] Due to the randomness of the positional deviation, the midpoint coordinates of the opposite side are used as a reference point. The allowable error fluctuation range is determined on both sides of the reference point, i.e., the grid side length L = 2d. The lower limit error fluctuation range is [- σ ,+ σ When L=2d=2 σ The lower limit for the grid size is 2. σ For example, continuing with the example above, if... σ =20 cm, then the lower limit error fluctuation range of the grid size is [-20 cm, +20 cm], that is, the lower limit value of the grid size = +20 cm - (-20 cm) = 40 cm, choose 2 σ =40 cm is the maximum acceptable error value, which meets the requirement of the minimum grid size. That is, the lower limit of the grid size is equal to the maximum acceptable error value of 40 cm, that is, the lower limit of the grid size = 20 cm × 2 = 40 cm.

[0065] In this specific embodiment, the error standard deviation conforming to a normal distribution is obtained by using multiple random position deviation values ​​from various error sources. The lower limit of the grid size is obtained by using the error standard deviation, ensuring that the error of the intelligent vehicle does not exceed the grid size, thus making the grid-driven electronic map effective.

[0066] Step S102-3: Obtain the upper limit of the grid size based on the error standard deviation and the accuracy values ​​of the plurality of sensors.

[0067] In some specific embodiments, obtaining the upper limit of the grid size based on the error standard deviation and the accuracy values ​​of the plurality of sensors includes: Step S102-31: Determine the minimum accuracy value based on the accuracy values ​​of the multiple sensors.

[0068] The higher the accuracy value of the sensor, the more precise the control and the smaller the error; the lower the accuracy value of the sensor, the more difficult it is to control and the larger the error. Therefore, this specific embodiment selects the minimum accuracy value from the accuracy values ​​of multiple sensors.

[0069] Steps S102-32: Obtain a first empirical value based on the minimum precision value which is an integer multiple of the preset precision, and obtain a second empirical value based on the maximum error coverage probability of the error standard deviation.

[0070] The maximum error coverage probability is greater than the minimum error coverage probability. For example, according to Table 1, the minimum error coverage probability is 68.27%, and the maximum error coverage probability is 99.73%.

[0071] The highest confidence level in Table 1 is achieved when the maximum error coverage probability is 99.73%, i.e., the error range is [-3]. σ +3 σ ], L=2d =6 σ .For example, σ =20 cm, the confidence level of the error range [-60 cm, +60 cm] is 99.73%, and the second empirical value = L = 6 σ =20 cm x 6 = 120 cm. This increases the coverage of the grid size, incorporates more random positional deviations into the grid size, and reduces the probability of cross-grid calculations.

[0072] In some specific embodiments, the preset precision integer multiple is equal to 5.

[0073] The preset accuracy multiple is an empirical value obtained through extensive experimentation. When the grid size is greater than 5 times the sensor's accuracy value, it can avoid miscalibration caused by sensor noise. For example, if the positioning accuracy of the inertial measurement unit is ±1 cm, the first empirical value = 5 × 1 cm = 5 cm.

[0074] Steps S102-33: Determine the upper limit of the grid size based on the maximum value between the first empirical value and the second empirical value.

[0075] For example, continuing with the above example, if the first empirical value is 5 cm and the second empirical value is 120 cm, then the upper limit of the grid size is determined to be 120 cm.

[0076] The upper limit of the grid size in this specific embodiment provides a reserved redundancy, taking into account the accuracy of the sensor, the accuracy of the grid, and the computational load, ensuring the efficiency and precise control of the intelligent vehicle's accuracy correction, and avoiding miscorrection caused by sensor noise.

[0077] In some specific embodiments, the upper limit of the grid size is equal to n× σWhere n is a positive integer greater than 1 and less than 6. n is an empirical value obtained through extensive experiments, and n=5 is determined to be the optimal value. When n=6, the computational load becomes too large, affecting the response speed of the intelligent vehicle; when n<5, the error coverage probability is low, and the probability of exceeding the grid is high, leading to cross-grid error correction, which also results in excessive computational load and affects the response speed of the intelligent vehicle. Therefore, n=5 is the optimal value that achieves a balance between the two.

[0078] For example, continuing with the above example, if σ =20 cm, the second empirical value is equal to 5σ=100cm, which is less than the second empirical value of 6. σ =120cm, that is, the upper limit of the error fluctuation range of the grid size [-2.5]. σ +2.5 σ ] = [-50 cm, +50 cm], below [-3 Figure 2 +3 ​ [-60 cm, +60 cm]. Although the confidence level was slightly reduced, the computational load was reduced while maintaining mesh accuracy, thus ensuring the efficiency of accuracy correction and precise control of the intelligent vehicle.

[0079] In some specific embodiments, the method further includes: Step S111: When the navigation path of the driving electronic map is characterized as a dry straight road segment, the grid is divided using the upper limit value of the grid size.

[0080] For example, the humidity value of the navigation path can be collected by a humidity sensor set in the application environment. When the humidity value is below 40%, the navigation path is dry; when the humidity value is greater than or equal to 40%, the navigation path is slippery. Alternatively, the dryness of the driving path can be determined by the slip information collected by various sensors of the intelligent vehicle itself. When the standard speed of the left wheel is 95 rpm and the actual speed is 102 rpm, the navigation path is slippery; when the standard speed of the left wheel is 95 rpm and the actual speed is 94-96 rpm, the navigation path is dry.

[0081] Step S112: When the navigation path of the driving electronic map is characterized as a curved section or a slippery section, the grid is divided using the lower limit value of the grid size.

[0082] For example, since the probability of errors and the deviation values ​​are small on dry straight sections, a 100cm grid is used on dry straight sections of the navigation path; since the probability of errors and the deviation values ​​are large on curved or slippery sections, a 20cm grid is used on curved or slippery sections of the navigation path in order to correct deviations in a timely manner.

[0083] In this specific embodiment, on the navigation path driven by the electronic map, the navigation path is dynamically divided into grids by intelligently recognizing road conditions, thereby achieving a balance between accuracy and efficiency.

[0084] This application embodiment obtains the accuracy values ​​of multiple sensors related to displacement within the intelligent vehicle and multiple random position deviation values ​​from various error sources. Based on the multiple random position deviation values ​​from the various error sources and the accuracy values ​​of the multiple sensors, it determines the range of the grid size for driving the electronic map. The total fluctuation range of the error values ​​is constrained within the grid size, with redundancy reserved to cope with increased errors due to environmental changes, preventing the error range from overflowing the grid. This simplifies the complexity of data processing and improves data processing efficiency and reliability.

[0085] like ​ As shown in the figure, this application provides a control system for controlling an intelligent vehicle, including: Group control device 11 stores a driving electronic map and determines the range of grid size of the driving electronic map by the method according to any one of claims 1 to 9; The host computer 12 controls the movement of the intelligent vehicle 13 based on the electronic map.

[0086] In this embodiment, the production plan is formulated based on the MES system, the rolling production plan, and the inventory bill of materials. Production tasks for each process island are generated according to the production plan and production schedule, including transportation tasks for the intelligent vehicles. The host computer 12 integrates with the production line equipment (including the intelligent vehicles), acquires equipment status (running, stopped, faulty), and generates control commands based on the production tasks. The intelligent vehicles execute the production tasks according to the control commands.

[0087] The method for controlling the intelligent vehicle 13 to drive using a driving electronic map may include: when the current position of the intelligent vehicle is not the location of the navigation QR code, determining the target location of the target QR code on the original navigation path and the current grid of the intelligent vehicle in the driving electronic map based on the current position; based on the positional relationship between the current grid and the original navigation path in the driving electronic map, combined with the current position and the attribute information of the grids on the original navigation path (including normal driving values, such as driving speed and driving direction angle), determining an escape strategy for the intelligent vehicle to reach the target location. This escape strategy includes: identifying the grid closest to the current position in the original navigation path as the connecting grid, controlling the intelligent vehicle to drive from the current position to the connecting grid, and then, starting from the connecting grid, driving through the corresponding grid based on the normal driving values ​​of each grid passed on the original navigation path until reaching the target location. By using the driving electronic map for compensation, the intelligent vehicle can accurately return to the navigation path even in complex environments, reducing the difficulty of escape and improving the efficiency of escape.

[0088] Finally, it should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the systems or apparatus disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple, and relevant parts can be referred to the method section.

[0089] The above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for determining the grid of an electronic map, characterized in that, include: Acquire the accuracy values ​​of multiple displacement-related sensors inside the intelligent vehicle, as well as the random positional deviation values ​​of multiple error sources; The range of grid size for driving the electronic map is determined based on the multiple random positional deviation values ​​of each of the various error sources and the accuracy values ​​of each of the various sensors.

2. The method according to claim 1, characterized in that, The process of determining the range of grid sizes for driving the electronic map based on multiple random position deviation values ​​from each of the various error sources and the accuracy values ​​from each of the various sensors includes: The standard deviation of the error is obtained based on the multiple random positional deviation values ​​of each of the various error sources; The lower limit of the grid size is obtained based on the error standard deviation; The upper limit of the grid size is obtained based on the error standard deviation and the accuracy values ​​of the plurality of sensors.

3. The method according to claim 2, characterized in that, The step of obtaining the lower limit value of the grid size based on the error standard deviation includes: The lower limit error fluctuation range of the grid size is determined based on the minimum error coverage probability of the error standard deviation. The lower limit value of the grid size is determined based on the lower limit error fluctuation range of the grid size.

4. The method according to claim 3, characterized in that, The lower limit error fluctuation range is [- σ ,+ σ ],in, σ It represents the standard deviation of the error.

5. The method according to claim 3, characterized in that, The step of obtaining the upper limit value of the grid size based on the error standard deviation and the accuracy values ​​of the plurality of sensors includes: The minimum accuracy value is determined based on the accuracy values ​​of the individual sensors. A first empirical value is obtained based on the minimum precision value, which is an integer multiple of a preset precision value. A second empirical value is obtained based on the maximum error coverage probability of the error standard deviation, wherein the maximum error coverage probability is greater than the minimum error coverage probability; The upper limit of the grid size is determined based on the maximum value between the first empirical value and the second empirical value.

6. The method according to claim 5, characterized in that, The preset precision integer multiple is equal to 5.

7. The method according to claim 5, characterized in that, The upper limit of the grid size is equal to 5. σ ,in, σ It represents the standard deviation of the error.

8. The method according to claim 1, characterized in that, The method further includes: When the navigation path of the driving electronic map is characterized as a dry straight road segment, the grid is divided using the upper limit value of the grid size; When the navigation path of the driving electronic map is characterized as a curved section or a slippery section, the grid is divided using the lower limit value of the grid size.

9. The method according to claim 1, characterized in that, The various sources of error include the intelligent vehicle and sensors.

10. A control system for controlling an intelligent vehicle, characterized in that, include: A group control device, storing a driving electronic map, determines the range of grid sizes of the driving electronic map by the method according to any one of claims 1 to 9; The host computer controls the movement of the intelligent vehicle based on the electronic map.

Images