A method for calculating safe following distance and a method for safe following of unmanned vehicles

Abstract

This invention discloses a method for calculating the safe following distance of autonomous vehicles, comprising: Step 1: Data acquisition; Step 2: Data preprocessing; Step 3: Data fusion, fusing the vehicle distance d and speed v information obtained from the preprocessed data in Step 2 with humidity h, temperature t, and rainfall intensity r sensed by an environmental perception sensor group to obtain comprehensive data; Step 4: Determining whether to use a first algorithm model or a second algorithm model based on the numerical range of the comprehensive data; Step 5: Determining the safe following distance. This invention integrates multiple sensors, including onboard radar sensors and an environmental perception sensor group, to achieve comprehensive real-time monitoring of surrounding vehicles and environmental conditions. This feature enables the solution to accurately sense and dynamically adjust the following distance in complex and changing traffic environments, especially under adverse weather conditions, thereby effectively preventing rear-end collisions and other traffic accidents, and greatly improving the safety performance of autonomous vehicles.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to the problem of how to calculate and maintain a safe following distance in real time and accurately in complex and ever-changing traffic environments, especially under different weather conditions. Background Technology

[0002] With the rapid development of autonomous driving technology, the safety performance of autonomous vehicles has become a major concern. Maintaining a safe distance from the vehicle in front is crucial for avoiding rear-end collisions and ensuring driving safety during autonomous vehicle operation. However, traditional methods for calculating following distance are often based on fixed algorithm models, making it difficult to adapt to complex and changing traffic environments and weather conditions. Especially in adverse weather conditions such as rain and fog, where roads are slippery and visibility is reduced, traditional following distance calculation methods often fail to provide sufficient safety assurance. Summary of the Invention

[0003] To address the problems existing in the background technology, the present invention provides a method for calculating safe following distance and a method for safe following of unmanned vehicles.

[0004] Technical solution:

[0005] A method for calculating safe following distance in autonomous driving includes the following steps:

[0006] Step 1: Data acquisition. The vehicle-mounted radar sensor detects the distance and speed information of surrounding vehicles in real time and transmits it to the data processing unit at a fixed frequency. The environmental perception sensor group detects the current humidity, temperature and rainfall intensity of the environment and transmits this data to the data processing unit at the same fixed frequency.

[0007] Step 2: Data preprocessing;

[0008] Step 3: Data fusion. The distance and speed information of the vehicle after the data preprocessing in Step 2 are fused with the humidity, temperature and rainfall intensity sensed by the environmental perception sensor group to obtain comprehensive data.

[0009] Step 4: Based on the numerical range of the comprehensive data, determine whether to use the first algorithm model or the second algorithm model to determine the safe following distance;

[0010] Step 5: Determine a safe following distance:

[0011] The safe following distance d is obtained through the first algorithm model. safe :

[0012]

[0013] In the formula, v currentThe current driving speed is represented by μ, the friction coefficient is g, the gravitational acceleration is k1, k2 and k3 are weighting coefficients, and d0 is the current measured distance.

[0014] The safe following distance d is obtained through the second algorithm model. safe :

[0015]

[0016] In the formula, v current The current driving speed is represented by k4, k5, and k6, which are weighting coefficients; a and b are constants obtained by fitting experimental data; and r0 is the current measured rainfall intensity, which is used to describe the exponential model of the friction coefficient changing with rainfall intensity.

[0017] Preferably, the data preprocessing in step 2 includes:

[0018] Data cleaning: Thresholding method is used to remove noise and outliers;

[0019] Data compression: Data compression algorithms are used to reduce the amount of data, thereby improving processing speed.

[0020] Data calibration: Adjust the data from each sensor using calibration algorithms to ensure data consistency and accuracy.

[0021] Preferably, in step 3, the comprehensive data is obtained by fusing the data using the following formula:

[0022] Comprehensive data = ω d ·d+ω v ·v+ω h ·h+ω t ·t+ω r ·r

[0023] Where, ω d ,ω v ,ω g ,ω t , and ω r These are the weights for distance, speed, humidity, temperature, and rainfall intensity, respectively, where d, v, h, t, and r represent the standardized data for distance, speed, humidity, temperature, and rainfall intensity, respectively.

[0024] Preferably, the standardization is performed using the following formula:

[0025]

[0026] Where m represents the standardized data, m0 represents the measured data value, and m max and m min These represent the maximum and minimum values ​​in the historical data, respectively.

[0027] Preferably, the constants and weight coefficients of the algorithm model are optimized and updated through machine learning algorithms; during the driving process, the system continuously collects historical data and current environmental change information, and uses this data to train and adjust the algorithm model to improve the accuracy and adaptability of the calculation.

[0028] Preferably, the machine learning algorithm includes neural networks and reinforcement learning.

[0029] An autonomous driving safety following method, based on the autonomous driving safety following distance calculation method described in this invention, involves obtaining the safe following distance and then having the control decision unit calculate the safe following distance d. safe This is converted into specific control commands and output to the actuators of the autonomous vehicle;

[0030] The actuator adjusts the vehicle's speed and following distance in real time based on the received control commands to maintain a safe distance from the vehicle in front.

[0031] Preferably, the control commands include brake pressure and throttle opening.

[0032] Preferably, the actuator includes a braking system and a throttle control system.

[0033] Beneficial effects of the present invention

[0034] This invention demonstrates significant benefits in improving the safety performance, adaptability, and intelligence level of autonomous vehicles.

[0035] From a safety perspective, this solution integrates multiple sensors, including onboard radar sensors and environmental perception sensor arrays, to achieve comprehensive real-time monitoring of surrounding vehicles and environmental conditions. This feature enables the solution to accurately perceive and dynamically adjust following distances in complex and changing traffic environments, especially in adverse weather conditions (such as rain and fog), thereby effectively preventing rear-end collisions and other traffic accidents, and greatly improving the safety performance of autonomous vehicles.

[0036] Secondly, the solution possesses a high degree of adaptability. Through the application of a dynamic friction coefficient model and a real-time weather adaptation algorithm, the solution can intelligently adjust the following distance based on different weather conditions (such as road slipperiness and visibility), ensuring a safe distance is maintained in various environments. Furthermore, the solution's adaptive learning mechanism allows it to continuously optimize the algorithm model based on historical data and current environmental changes, further enhancing its adaptability and accuracy.

[0037] Furthermore, the intelligence level of this solution has been significantly improved. Through multi-sensor fusion technology and complex algorithm models, the solution can process and analyze large amounts of data in real time, make rapid decisions, and output control commands, enabling autonomous vehicles to cope more intelligently with various driving conditions. This level of intelligence not only improves the driving safety of autonomous vehicles but also makes their application possible in a wider range of scenarios.

[0038] Furthermore, this solution will contribute to the further development of autonomous driving technology. By continuously optimizing and improving the algorithm and model, the safety performance and intelligence level of autonomous vehicles can be further enhanced, accelerating the popularization and application of autonomous driving technology. Simultaneously, this solution can also provide strong support for the construction of intelligent transportation solutions, promoting the intelligent and green development of urban transportation.

[0039] In summary, the autonomous driving safety following distance calculation scheme and method of the present invention have significant beneficial effects, not only improving the safety performance and adaptability of autonomous vehicles, but also promoting the further development of autonomous driving technology and the construction of intelligent transportation solutions. Attached Figure Description

[0040] Figure 1 This is a flowchart of the method of the present invention.

[0041] Figure 2 This is a system module diagram of the present invention. Detailed Implementation

[0042] The present invention will be further described below with reference to embodiments, but the scope of protection of the present invention is not limited thereto:

[0043] Combination Figure 1 A method for calculating safe following distance in autonomous driving, in a specific example, includes the following steps:

[0044] Step 1: Data Collection

[0045] • The vehicle-mounted radar sensor detects the distance (in meters) and speed (in meters per second) of surrounding vehicles in real time and transmits the information to the data processing unit at a fixed frequency (e.g., 10 times per second).

[0046] • The environmental sensing sensor group (humidity sensor, temperature sensor, raindrop sensor, etc.) detects the current environmental humidity (unit: %), temperature (unit: degrees Celsius), and rainfall intensity (unit: millimeters / minute), and transmits this data to the data processing unit at a fixed frequency.

[0047] Step 2: Data Preprocessing

[0048] Data cleaning: Thresholding methods are used to remove noise and outliers. For example, reasonable ranges are set for distance and speed; data outside these ranges are considered outliers and discarded.

[0049] Data compression: Employ data compression algorithms (such as Huffman coding) to reduce data volume and improve processing speed. Simultaneously, maintain data accuracy within acceptable limits.

[0050] Data calibration: Adjust the data of each sensor through calibration algorithms (such as the least squares method) to ensure data consistency and accuracy.

[0051] Step 3: Data Fusion

[0052] The vehicle distance and speed information detected by the vehicle radar sensor is fused with the weather conditions (such as humidity, temperature, and rainfall intensity) perceived by the environmental perception sensor group.

[0053] The fusion algorithm includes weighted fusion to form a more comprehensive and accurate traffic environment perception result (such as effective braking distance under the combined influence of weather).

[0054] Specifically, data fusion obtains a comprehensive result by assigning different weights to data from different sources and then calculating a weighted sum.

[0055] For vehicle distance and speed information detected by vehicle-mounted radar sensors, and weather conditions (humidity, temperature, rainfall intensity) perceived by environmental perception sensor groups, a weight can be assigned to each parameter, and then a weighted sum can be calculated to form a more comprehensive and accurate traffic environment perception result.

[0056] In a preferred embodiment, the weighted fusion formula can be expressed as:

[0057] Comprehensive data = ω d ·d+ω v ·v+ω h ·h+ω t ·t+ω r ·r

[0058] Where, ω d ,ω v ,ω h ,ω t , and ω r These are the weights for distance, speed, humidity, temperature, and rainfall intensity, respectively, and their values ​​are based on the importance and reliability of each parameter. The sum of these weights should equal 1.

[0059] In practical applications, the weights can be flexibly adjusted. For example, if rainfall intensity has a significant impact on braking distance, then ω... r It may be assigned a higher value.

[0060] After weighted fusion, a comprehensive perception result can be obtained, which will be used in subsequent calculation and decision-making processes.

[0061] Step 4: If the result of the standardized calculation of the comprehensive data is less than 0.5, the first algorithm model is selected; otherwise, the second algorithm model is selected to determine the safe following distance.

[0062] The safe following distance d is obtained through the first algorithm model. safe :

[0063]

[0064] In the formula, v current The current driving speed is represented by μ, the friction coefficient is g, the gravitational acceleration is k1, k2 and k3 are weighting coefficients, and d0 is the current measured distance.

[0065] The second algorithm model takes into account rainy conditions. Under rainy conditions, the control decision unit selects the dynamic friction coefficient model (μ = f(r)), which is a mapping function from rainfall intensity r to the tire-road friction coefficient μ.

[0066] To describe this model more concretely, we adopt a simplified nonlinear function form, the exponential model. Using the exponential model, the friction coefficient μ can be expressed as:

[0067] μ=a·e -br

[0068] Where a and b are constants, the friction coefficient μ decreases exponentially with the increase of rainfall intensity r, reflecting the reduction of friction caused by slippery road surfaces in rainy weather.

[0069] Next, combining a real-time weather adaptation algorithm, the following distance d is dynamically adjusted based on the current rainfall intensity r. safe The formula for calculating d. Given d. safe =G(V current, μ,d-eff), where G is a complex function that takes into account the current velocity V. current The friction coefficient μ and the effective braking distance d-eff are related. The effective braking distance d-eff is related to the vehicle's maximum deceleration and initial velocity, but under rainy conditions, the change in the friction coefficient must also be considered. Therefore, d-eff is expressed as:

[0070]

[0071] Where g is the acceleration due to gravity.

[0072] Substituting the above μ and d-eff into d safeFrom the calculation formula, we get:

[0073]

[0074] Since the specific form of the G function is quite complex and involves the interaction of multiple parameters, we simplify it in this scheme. G is a weighted summation or product, that is:

[0075]

[0076] In the formula, v current The formula represents the current driving speed; k4, k5, and k6 are weighting coefficients; a and b are constants obtained by fitting experimental data; and r0 is the current measured rainfall intensity, used to describe the exponential model of the friction coefficient changing with rainfall intensity. This formula comprehensively considers the influence of speed, friction coefficient, and effective braking distance on following distance as a second algorithm model.

[0077] The control decision unit calculates the safe following distance d that meets the current driving conditions based on the selected algorithm model and relevant parameters (such as the current driving speed Vcurrent, the current measured distance, etc.) using the specific algorithm described above. safe During the calculation process, it is necessary to acquire rainfall intensity data r in real time, calculate the μ value through a dynamic friction coefficient model, and then substitute it into the following distance calculation formula.

[0078] Case 1 (using the first algorithm model):

[0079] (1) Scene description:

[0080] Environmental conditions: Sunny (rainfall intensity r = 0 mm / min), temperature 50℃, humidity 40%;

[0081] Vehicle status: Current speed v current =20m / s (approximately 72km / h), the vehicle radar detects the distance to the vehicle in front as d=50m.

[0082] Road surface friction coefficient: μ=0.7 (standard reference value).

[0083] (2) Data Standardization and Integration

[0084] ① Data standardization

[0085] To eliminate the influence of different dimensions and units, the data is standardized. A 0-1 standardization method is used to map each parameter to the [0,1] interval.

[0086] Distance d standardization: Assuming the maximum distance in historical data is 100 meters and the minimum distance is 10 meters, then:

[0087]

[0088] Velocity v standardization: Assuming the maximum velocity in historical data is 30 m / s and the minimum is 5 m / s, then:

[0089]

[0090] Humidity h-standardization: Assuming the maximum humidity value in historical data is 100% and the minimum is 30%, then:

[0091]

[0092] Temperature t-standardization: Assuming the maximum temperature in historical data is 35 degrees Celsius and the minimum is 5 degrees Celsius, then:

[0093]

[0094] Rainfall intensity r standardization: Assuming the maximum rainfall intensity in historical data is 10 mm / min and the minimum is 0 mm / min, then:

[0095]

[0096] ② Data fusion

[0097] According to the formula in the patent, the standardized data is weighted and fused. The weights are as follows:

[0098] ω d =0.3; ω v =0.2; ω h =0.1; ω t =0.1; ω r =0.3; (the sum is 1).

[0099] Total data = 0.3 × 0.444 + 0.2 × 0.6 + 0.1 × 0.143 + 0.1 × 0.667 + 0.3 × 0 = 0.334

[0100] If the result after weighted fusion is less than 0.5, the first algorithm model is triggered.

[0101] Model parameters:

[0102] The weight coefficients of the first algorithm were optimized using historical data: k1 = 0.4, k2 = 0.5, k3 = 0.1. g = 9.8 m / s 2

[0103] (3) Calculation process

[0104] According to the first algorithm formula:

[0105] Case 2 (using the second algorithm model):

[0106] (1) Scene Description

[0107] Weather conditions: Heavy rain, rainfall intensity r = 5 mm / min, temperature 20℃, humidity 80%.

[0108] Vehicle status: Current speed v current =20m / s (72km / h), radar detects the distance to the vehicle in front d=50m.

[0109] Dynamic friction coefficient: With fitting parameters a = 0.8 and b = 0.1, μ = 0.8e is calculated. -0.5 ≈0.4852.

[0110] (2) Data Standardization and Integration

[0111] ① Data standardization

[0112] Distance d standardization: Assuming the maximum distance in historical data is 100 meters and the minimum distance is 10 meters, then:

[0113]

[0114] Velocity v standardization: Assuming the maximum velocity in historical data is 30 m / s and the minimum is 5 m / s, then:

[0115]

[0116] Humidity h-standardization: Assuming the maximum humidity value in historical data is 100% and the minimum is 80%, then:

[0117]

[0118] Temperature t-standardization: Assuming the maximum temperature in historical data is 35 degrees Celsius and the minimum is 5 degrees Celsius, then:

[0119]

[0120] Rainfall intensity r standardization: Assuming the maximum rainfall intensity in historical data is 10 mm / min and the minimum is 0 mm / min, then:

[0121]

[0122] ② Data fusion

[0123] According to the formula in the patent, the standardized data is weighted and fused. The weights are as follows:

[0124] ω d =0.3; ω v =0.2; ωh =0.1; ω t =0.1; ω r =0.3; (the sum is 1).

[0125] Total data = 0.3 × 0.444 + 0.2 × 0.6 + 0.1 × 0.714 + 0.1 × 0.5 + 0.3 × 0.5 = 0.524

[0126] If the result after weighted fusion is greater than 0.5, the second algorithm model is triggered.

[0127] Model parameters:

[0128] The weight coefficients of the second algorithm were optimized using historical data: k4 = 0.3, k5 = 0.5, k6 = 0.2. g = 9.8 m / s 2

[0129] (3) Calculation process

[0130] According to the first algorithm formula:

[0131] This calculation process fully considers the relative speed and distance between vehicles, as well as the specific impact of weather conditions on braking performance (such as increased braking distance due to slippery roads). In this way, the system can dynamically adjust the following distance according to different weather conditions to ensure driving safety.

[0132] Step 6: Output control commands

[0133] The control decision unit will calculate the safe following distance d. safe This is converted into specific control commands (such as brake pressure, throttle opening, etc.) and output to the actuators of the autonomous vehicle (such as the braking system and throttle control system).

[0134] The actuator adjusts the vehicle's speed and following distance in real time based on the received control commands to maintain a safe distance from the vehicle in front.

[0135] Step 7: Adaptive Learning and Optimization

[0136] The system has an adaptive learning mechanism that optimizes and updates the algorithm model through machine learning algorithms (such as neural networks and reinforcement learning).

[0137] During operation, the system continuously collects historical data and information on current environmental changes, using this data to train and adjust the algorithm model to improve the accuracy and adaptability of calculations.

[0138] This invention also discloses an autonomous driving safe following method. Based on the aforementioned autonomous driving safe following distance calculation method, after obtaining the safe following distance, the control decision unit will calculate the safe following distance d. safe This is converted into specific control commands and output to the actuators of the autonomous vehicle;

[0139] The actuator adjusts the vehicle's speed and following distance in real time based on the received control commands to maintain a safe distance from the vehicle in front.

[0140] This invention also proposes an unmanned driving safety following distance calculation system, combined with Figure 2 It mainly includes the following modules:

[0141] Vehicle-mounted radar sensors: used to detect the distance and speed of surrounding vehicles in real time.

[0142] Environmental sensing sensor group: including humidity sensor, temperature sensor, raindrop sensor, etc., used to sense current weather conditions and environmental changes in real time.

[0143] Data processing unit: Receives data from various sensors and performs preprocessing and fusion analysis.

[0144] Algorithm Model Library: Stores various algorithm models, including dynamic friction coefficient models, real-time weather adaptation algorithms, etc.

[0145] Control Decision Unit: Based on the output of the data processing unit and the algorithm models in the algorithm model library, it calculates the safe following distance and outputs control commands to the actuators of the autonomous vehicle.

[0146] The specific embodiments described herein are merely illustrative of the spirit of the invention. Those skilled in the art to which this invention pertains may make various modifications or additions to the described specific embodiments or use similar methods to substitute them, without departing from the spirit of the invention or exceeding the scope defined by the appended claims.

Claims

1. A method for calculating safe following distance in autonomous driving, characterized in that... It includes the following steps: Step 1: Data acquisition. The vehicle-mounted radar sensor detects the distance and speed information of surrounding vehicles in real time and transmits it to the data processing unit at a fixed frequency. The environmental perception sensor group detects the current humidity, temperature and rainfall intensity of the environment and transmits this data to the data processing unit at the same fixed frequency. Step 2: Data preprocessing; Step 3: Data fusion. The distance and speed information of the vehicle after the data preprocessing in Step 2 are fused with the humidity, temperature and rainfall intensity sensed by the environmental perception sensor group to obtain comprehensive data. Step 4: Based on the numerical range of the comprehensive data, determine whether to use the first algorithm model or the second algorithm model to determine the safe following distance; Step 5: Determine a safe following distance: The safe following distance d is obtained through the first algorithm model. safe : In the formula, v current The current driving speed is represented by μ, the friction coefficient is g, the gravitational acceleration is k1, k2 and k3 are weighting coefficients, and d0 is the current measured distance. The safe following distance d is obtained through the second algorithm model. safe : In the formula, v current The current driving speed is represented by k4, k5, and k6, which are weighting coefficients; a and b are constants obtained by fitting experimental data; and r0 is the current measured rainfall intensity, which is used to describe the exponential model of the friction coefficient changing with rainfall intensity.

2. The method according to claim 1, characterized in that... The data preprocessing described in step 2 includes: Data cleaning: Thresholding method is used to remove noise and outliers; Data compression: Data compression algorithms are used to reduce the amount of data, thereby improving processing speed. Data calibration: Adjust the data from each sensor using calibration algorithms to ensure data consistency and accuracy.

3. The method according to claim 1, characterized in that... In step 3, the comprehensive data is obtained by fusing the data using the following formula: Comprehensive data = ω d ·d+ω v ·v+ω h ·h+ω t ·t+ω r ·r Where, ω d ,ω v ,ω h ,ω t , and ω r These are the weights for distance, speed, humidity, temperature, and rainfall intensity, respectively, where d, v, h, t, and r represent the standardized data for distance, speed, humidity, temperature, and rainfall intensity, respectively.

4. The method according to claim 3, characterized in that... The standardization is performed using the following formula: Where m represents the standardized data, m0 represents the measured data value, and m max and m min These represent the maximum and minimum values ​​in the historical data, respectively.

5. The method according to claim 1, characterized in that... The constants and weight coefficients of the algorithm model are optimized and updated through machine learning algorithms. During the driving process, the system continuously collects historical data and information on current environmental changes, and uses this data to train and adjust the algorithm model to improve the accuracy and adaptability of the calculation.

6. The method according to claim 5, characterized in that... The machine learning algorithms include neural networks and reinforcement learning.

7. A method for safe following of unmanned vehicles, based on the method for calculating safe following distance for unmanned vehicles as described in any one of claims 1-6, characterized in that... After obtaining the safe following distance, the control decision unit will calculate the safe following distance d. safe This is converted into specific control commands and output to the actuators of the autonomous vehicle; The actuator adjusts the vehicle's speed and following distance in real time based on the received control commands to maintain a safe distance from the vehicle in front.

8. The method according to claim 7, characterized in that The control commands include brake pressure and throttle opening.

9. The method according to claim 7, characterized in that... The actuators include a braking system and a throttle control system.

Images