An autonomous driving vehicle control method, terminal device, and storage medium

Abstract

The present invention relates to a method for controlling an autonomous vehicle, a terminal device, and a storage medium. The method includes: S1: Collecting current road information of the vehicle, where the road information includes traffic light information and the maximum driving speed corresponding to the current road; S2: Calculating the distance to an obstacle and the collision time between the obstacle and the vehicle during the vehicle's driving; S3: Calculating the target vehicle speed for the vehicle to reach the obstacle; S4: Calculating a control output based on the magnitude relationship between the obstacle distance and the safe distance from the obstacle, and the magnitude relationship between the collision time and the safe collision time; S5: After converting the control output into a throttle control amount and a braking control amount, controlling the vehicle using the converted throttle control amount and braking control amount. The present invention improves the safety and comfort of autonomous driving control.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and particularly to a method for controlling an autonomous driving vehicle, a terminal device, and a storage medium. Background Art

[0002] With the development of technology, automobiles have gradually transformed from simple transportation tools into intelligent mobile spaces and application terminals. Autonomous driving vehicles have different operating scenarios, and scenarios such as commuting in parks (including science and technology parks, airports, industrial plants, scenic spots), fixed-route buses (such as subway shuttles, customized buses), and autonomous driving logistics vehicles in parks are the first scenarios that are most likely to be implemented. Moreover, with the gradual increase in the number of smart parks and industrial parks, etc., the unmanned driving system for parks and fixed routes has even more demonstrated its huge application prospects. How to achieve more demand-compliant control of autonomous driving vehicles has become a difficult problem that urgently needs to be solved. Summary of the Invention

[0003] In order to solve the above problems, the present invention proposes a method for controlling an autonomous driving vehicle, a terminal device, and a storage medium.

[0004] The specific solutions are as follows:

[0005] A method for controlling an autonomous driving vehicle, comprising the following steps:

[0006] S1: Collect the current road information of the vehicle, where the road information includes traffic light information and the maximum driving speed corresponding to the current road;

[0007] S2: Calculate the distance L to the obstacle and the time to collision TTC between the obstacle and the vehicle during the driving of the vehicle;

[0008] S3: Calculate the target vehicle speed Vt when the vehicle travels to the obstacle;

[0009] S4: Calculate the control output u according to the magnitude relationship between the distance L and the safe distance L_Safe to the obstacle, and the magnitude relationship between the time to collision TTC and the safe time to collision TTS_Safe;

[0010] S5: After converting the control output u into a throttle control amount and a braking control amount, use the converted throttle control amount and braking control amount to control the vehicle.

[0011] Furthermore, the traffic light information includes the signal information, position information, and corresponding stop point information of the traffic light; the signal information of the traffic light is collected by communicating with the traffic light controllers installed on both sides of the road.

[0012] Further, when the obstacle is a traffic light, the calculation method of the obstacle distance L is as follows: collect the longitude and latitude information of the vehicle's front stop point corresponding to the traffic light and the longitude and latitude information of the vehicle's current location, and calculate the obstacle distance L based on the longitude and latitude information of the traffic light stop point and the longitude and latitude information of the vehicle's current location.

[0013] Further, the calculation method of the target vehicle speed Vt when the vehicle travels to the obstacle is as follows:

[0014] S301: Construct Table 1 that records the corresponding relationship between the obstacle distance and the vehicle driving speed when the vehicle driving requirements are met, and Table 2 that records the corresponding relationship between the obstacle distance and the maximum allowable deceleration of the vehicle braking when the vehicle driving requirements are met, where the maximum value of the vehicle driving speed in Table 1 is less than or equal to the maximum driving speed corresponding to the current road;

[0015] S302: Calculate the vehicle driving speed corresponding to the obstacle distance L based on Table 1 as the predicted target vehicle speed Vt1;

[0016] S303: Calculate the maximum allowable deceleration a of the vehicle braking corresponding to the obstacle distance L based on Table 2;

[0017] S304: Determine whether a > (Vh - Vh_last) is satisfied. If so, set the target vehicle speed Vt = (Vh - Vh_last); otherwise, set the target vehicle speed Vt = Vt1; where Vh_last is the actual vehicle speed at the previous moment.

[0018] Further, the method of calculating the vehicle driving speed corresponding to the obstacle distance L based on Table 1 as the predicted target vehicle speed Vt1 is as follows: Find two obstacle distances L1 and L2 adjacent to the obstacle distance L in Table 1, and L1 < L2, and obtain the vehicle driving speeds V1 and V2 corresponding to the two obstacle distances L1 and L2, and calculate the predicted target vehicle speed Vt1 according to the following formula:

[0019]

[0020] Further, when the obstacle is a traffic light, the calculation method of the target vehicle speed Vt when the vehicle travels to the obstacle is as follows: When the obstacle distance L is less than the obstacle distance threshold L_min, calculate the time time required for the current vehicle to travel to the traffic light corresponding stop point = L / Vh; When the traffic light is green and time > Light_time, or when the traffic light is red and time < Light_time, set the target vehicle speed Vt to 0, where Vh is the current vehicle speed and Light_time is the remaining time of the traffic light.

[0021] Further, the calculation method of the control output u is as follows:

[0022] (1) When L > L_Safe and TTC > TTS_Safe, the calculation formula for setting the control output u is:

[0023] u = Kp * ev + Kd * dev + Ki1 * Iv + Ki2 * Id

[0024] ev = Vh – Vt

[0025]

[0026] Iv = Iv_last + ev

[0027] Id = Id_last + L_Safe - L

[0028] Among them, Kp is the proportional coefficient, Kd is the differential coefficient, Ki1 and Ki2 are both integral coefficients, ev is the difference term, Vh is the current vehicle speed, Dev is the differential term, Iv is the integral term of speed, Id is the integral term of distance, ΔT represents the time difference between the previous moment and the current moment, ev_last is the difference term at the previous moment, Iv_last is the integral term of speed at the previous moment, and Id_last is the integral term of distance at the previous moment;

[0029] (2) When TTC ≤ TTS_Warn, the calculation method for the control output u is:

[0030] When TTC is less than the first-level warning collision time T1, set the control output u = A; otherwise, if TTC is less than the second-level warning collision time T2, set the control output u = A1 + A2 * (T2 - TTC), where A is a fixed value obtained from experience, A1 and A2 are both empirical coefficients, and the first-level warning collision time T1 is less than the second-level warning collision time T2;

[0031] (3) When TTC > TTS_Warn and L ≤ L_Safe, the calculation formula for setting the control output u is:

[0032] u = Kp′ * ev + Kd′ * dev + Ki1′ * Iv + Ki2′ * Id

[0033] Among them, Kp′ is the proportional coefficient, Kd′ is the differential coefficient, Ki1′ and Ki2′ are both integral coefficients;

[0034] (4) When TTS_Warn < TTC ≤ TTS_Safe and L > L_Safe, the calculation formula for setting the control output u is:

[0035]

[0036] Among them, Vr is the relative speed of the obstacle relative to the vehicle.

[0037] Further, the process of converting the control output u into the throttle control amount and the braking control amount is as follows:

[0038] When the control output u is less than 0, the braking control amount is set to 0, and the throttle control amount = K_bias1 - K1 * u;

[0039] When the control output u is greater than 0, the throttle control amount is set to 0, and the braking control amount = K_bias2 + K2 * u;

[0040] Among them, both K_bias1 and K_bias2 are offsets, and both K1 and K2 are proportionality coefficients.

[0041] An autonomous vehicle control terminal device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described above in the embodiments of the present invention are implemented.

[0042] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above in the embodiments of the present invention are implemented.

[0043] The present invention adopts the above technical solutions to improve the safety and comfort of autonomous driving control. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 Shown is a flowchart of Embodiment 1 of the present invention.

[0045] Figure 2 Shown is a schematic diagram of a road information configuration interface in Embodiment 1 of the present invention.

[0046] Figure 3 Shown is a schematic diagram of a visualization curve corresponding to Table 1 in Embodiment 1 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To further illustrate the embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, mainly used to illustrate the embodiments, and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, those of ordinary skill in the art should be able to understand other possible implementation manners and the advantages of the present invention.

[0048] The present invention will be further described below in conjunction with the drawings and specific embodiments.

[0049] Embodiment 1:

[0050] Since fixed routes such as in a park have the following characteristics: relatively low speed, generally below 40 km / h during operation, unlike the autonomous driving system of passenger cars on completely open roads, which may require a speed above 60 km / h; limited road range, relatively fixed, limited road length, and the driving map can be pre-deployed and stored in the autonomous driving controller. Based on the above characteristics, an embodiment of the present invention provides a method for controlling an autonomous vehicle. As Figure 1 shown, the method includes the following steps:

[0051] S1: Collect the current road information of the vehicle.

[0052] Since the road information of fixed routes such as in a park is fixed, it can be collected and stored in advance. The road information collected in this embodiment is shown in Table 1, including longitude, latitude, road direction, elevation, road attributes, section information, the maximum driving speed corresponding to the current road, and traffic light information. The specific configuration method is as Figure 2 shown.

[0053] Table 1

[0054]

[0055] In this embodiment, the traffic light signal information is collected by communicating with the traffic light controllers installed on both sides of the road. Specifically, V2X wireless communication technology is used for communication. By collecting the traffic light signal information of the road, the vehicle can drive according to traffic rules.

[0056] Compared with the method of using an intelligent camera to identify the captured pictures to collect the traffic light signal information of the road in the prior art, it can avoid the disadvantages that the camera is greatly affected by the environment and the recognition effect may be relatively poor in bad weather such as rain, snow, and fog and under different lighting conditions.

[0057] S2: Calculate the distance L to the obstacle and the time to collision TTC between the obstacle and the vehicle during the driving process of the vehicle.

[0058] The obstacle distance L can be calculated based on the information collected by multiple sensors installed on the vehicle, such as by fusing the data collected by radar, cameras, etc. In this embodiment, when the obstacle is a traffic light, a specific calculation method for the obstacle distance L is set, that is: collect the longitude and latitude information of the vehicle's front stop point corresponding to the traffic light and the longitude and latitude information of the vehicle's current location, and calculate the obstacle distance L based on the longitude and latitude information of the traffic light stop point and the longitude and latitude information of the vehicle's current location. The vehicle's front stop point corresponding to the traffic light can be obtained by combining electronic map data and road direction. For example, there are four traffic light stop points in an intersection, and the corresponding traffic light stop point can be obtained according to the road direction in which the vehicle is traveling. It should be noted that when the obstacle distances calculated by the two methods are different, the smaller value of the two is taken.

[0059] The calculation formula for the time to collision TTC between the obstacle and the vehicle is: TTC = L / (Vh - Vr), where Vh is the current vehicle speed and Vr is the relative speed of the obstacle relative to the vehicle, which can be obtained from the corresponding sensor data.

[0060] S3: Calculate the target vehicle speed Vt when the vehicle travels to the obstacle.

[0061] The calculation of the real-time target speed should meet the vehicle driving requirements, that is, ensure the requirements in terms of safety and comfort. Safety is manifested in that the vehicle cannot collide and cannot violate traffic rules. Comfort is mainly reflected in the riding experience of passengers. There should not be too many sudden brakes, otherwise it is easy to make passengers carsick. For autonomous logistics vehicles, it is also easy to damage the items on the vehicle and the vehicle itself. Therefore, first, a reasonable vehicle speed should be calculated to avoid the vehicle colliding with obstacles or violating traffic rules and ensure the driving safety of the vehicle. Second, sudden changes in vehicle speed should be avoided, which will cause a large deceleration of the vehicle and cause discomfort to passengers, like a novice driver with poor driving skills, and even cause the consequence of carsickness to passengers.

[0062] In this embodiment, the calibration look-up table method is mainly used in the calculation of the target vehicle speed Vt. The specific method is as follows:

[0063] S301: Construct Table 1 recording the corresponding relationship between the obstacle distance and the vehicle driving speed when meeting the vehicle driving requirements and Table 2 recording the corresponding relationship between the obstacle distance and the maximum allowable deceleration of vehicle braking when meeting the vehicle driving requirements.

[0064] S302: Calculate the vehicle driving speed corresponding to the obstacle distance L based on Table 1 as the predicted target vehicle speed Vt1.

[0065] S303: Calculate the maximum allowable deceleration a of vehicle braking corresponding to the obstacle distance L based on Table 2.

[0066] S304: Determine whether a > (Vh - Vh_last) is satisfied. If so, set the target vehicle speed Vt = (Vh - Vh_last); otherwise, set the target vehicle speed Vt = Vt1; where Vh_last is the actual vehicle speed at the previous moment.

[0067] In this embodiment, set Table 1 as calib_table_v, and its calibration relationship is as follows:

[0068] calib_vector_obsdist[7] = {0, 8, 10, 15, 30, 40, 100};

[0069] calib_vector_speed[7] = {0, 0, 8, 15, 20, 30, 30};

[0070] Where calib_vector_obsdist is the obstacle distance vector, with the unit of meter; calib_vector_deacc is the vehicle driving speed, with the unit of meter per second.

[0071] For easy understanding, calib_vector_obsdist can be used as the x-axis and calib_vector_speed as the y-axis for visualization, as Figure 3 So.

[0072] The maximum value of calib_vector_speed should be less than or equal to the maximum driving speed corresponding to the current road. The maximum value of calib_vector_obsdist is the maximum distance of the detectable obstacle. For the park scenario, it is sufficient to set the visible distance of the general obstacle to 100.

[0073] In this way, for the detected obstacle distance L in front, find two adjacent obstacle distances L1 and L2 to the obstacle distance L from Table 1, and L1 < L2, and obtain the vehicle driving speeds V1 and V2 corresponding to the two obstacle distances L1 and L2, and calculate the predicted target vehicle speed Vt1 according to the following formula:

[0074]

[0075] In this embodiment, set Table 2 as calib_table_a, and its calibration relationship is as follows:

[0076] calib_vector_obsdist[7] = {0, 3, 5, 15, 19.9, 30, 50};

[0077] calib_vector_deacc[7] = {5, 5, 5, 3, 2, 1, 0};

[0078] Among them, calib_vector_obsdist is the obstacle distance vector; calib_vector_deacc is the maximum allowable deceleration vector, with the unit of m / (s*s). This corresponding relationship defines the maximum allowable deceleration at different distances. The farther the distance, the smaller the corresponding deceleration; the closer the distance, the larger the corresponding deceleration. When setting the deceleration calibration curve, the human experience is also considered. The following - 2 / m / s / s is set as the following - car deceleration under non - special emergency situations. After real - vehicle tests, it is summarized that the deceleration below this value is relatively gentle and basically will not cause much discomfort.

[0079] (1) Further, this embodiment also sets a calculation method for the corresponding target speed Vt for the special case where the obstacle is a traffic light, that is: when the obstacle distance L is less than the obstacle distance threshold L_min, calculate the time time = L / Vh required for the current vehicle to travel to the corresponding stop point of the traffic light; when the traffic light is green and time>Light_time, or when the traffic light is red and time<Light_time, set the target speed Vt to 0. Light_st: represents the current light state, whether it is red or green; Light_time represents the remaining duration of the current light state (i.e., the countdown time displayed on the traffic light). Light_st and Light_time can be obtained from the traffic light signal information.

[0080] S4: Calculate the control output u according to the size relationship between the distance L and the obstacle safety distance L_Safe, and the size relationship between the time - to - collision TTC and the safe time - to - collision TTS_Safe.

[0081] Those skilled in the art need to preset the obstacle safety distance L_Safe and the safe time - to - collision TTS_Safe in advance.

[0082] After calculating the target speed Vt in the previous step, in the next step, the vehicle is controlled in combination with the current vehicle speed Vh to change the vehicle speed from the current vehicle speed Vh to the target speed Vt. Similarly, the first goal of the control is to ensure safety and prevent the vehicle from colliding, and then to ensure the comfort of the ride as much as possible. Based on the above goals, in this embodiment, a segmented PID control strategy is adopted for following the vehicle in front. At the same time, considering the scenario of obstacle crossing, the vehicle can be emergently braked to ensure vehicle safety.

[0083] The segmented PID mainly includes the following situations:

[0084] (1) When L > L_Safe and TTC > TTS_Safe, it indicates that the vehicle is still relatively safe. A set of long-distance safe following PID control parameters are used to calculate the control output u. The proportion of the parameter P will be relatively small to ensure the comfort of following as much as possible. At this time, the calculation formula for setting the control output u is:

[0085] u = Kp * ev + Kd * dev + Ki1 * Iv + Ki2 * Id

[0086] ev = Vh – Vt

[0087]

[0088] Iv = Iv_last + ev

[0089] Id = Id_last + L_Safe - L

[0090] Among them, Kp is the proportional coefficient, Kd is the differential coefficient, Ki1 and Ki2 are both integral coefficients, ev is the difference term, Vh is the current vehicle speed, Dev is the differential term, Iv is the integral term of speed, Id is the integral term of distance, ΔT represents the time difference between the previous moment and the current moment, ev_last is the difference term of the previous moment, Iv_last is the integral term of speed of the previous moment, and Id_last is the integral term of distance of the previous moment.

[0091] By adding the integral term of distance, the control error can be eliminated and the compliance of long-distance following can be improved.

[0092] (2) When TTC ≤ TTS_Warn, the vehicle is in a relatively dangerous situation. The calculation method of the control output u is:

[0093] When TTC is less than the first-level warning collision time T1, set the control output u = A; otherwise, if TTC is less than the second-level warning collision time T2, set the control output u = A1 + A2 * (T2 - TTC), where A is a fixed value obtained according to experience and is set to 7 in this embodiment, A1 and A2 are both empirical coefficients and are set to 3 and 5 respectively in this embodiment, the first-level warning collision time T1 is less than the second-level warning collision time T2, and is set to 0.8 and 1.6 respectively in this embodiment. The above parameters are all the best results that meet the requirements through multiple experiments.

[0094] (3) When TTC > TTS_Warn and L ≤ L_Safe, the calculation formula for setting the control output u is:

[0095] u = Kp′ * ev + Kd′ * dev + Ki1′ * Iv + Ki2′ * Id

[0096] Among them, Kp′ is the proportional coefficient, Kd′ is the differential coefficient, and Ki1′ and Ki2′ are both integral coefficients.

[0097] This mode only differs in the PID parameters from (1).

[0098] (4) When TTS_Warn < TTC ≤ TTS_Safe and L > L_Safe, a deceleration control strategy is adopted. According to the relationship between the obstacle distance and the relative speed, the current control output is calculated. At this time, the calculation formula for setting the control output u is:

[0099]

[0100] S5: After converting the control output u into the throttle control amount and the braking control amount, the converted throttle control amount and braking control amount are used to control the vehicle.

[0101] In this embodiment, the throttle and brake percentages are used for control, so the control output u must be converted into the throttle control amount and the braking control amount. Since the vehicle needs to accelerate when u is less than 0 and decelerate when u is greater than 0, the process of converting the control output u into the throttle control amount and the braking control amount is set as follows:

[0102] When the control output u is less than 0, the braking control amount is set to 0, and the throttle control amount = K_bias1 - K1 * u;

[0103] When the control output u is greater than 0, the throttle control amount is set to 0, and the braking control amount = K_bias2 + K2 * u;

[0104] Among them, K_bias1 and K_bias2 are both offsets, and K1 and K2 are both proportional coefficients. Those skilled in the art need to preset these parameters according to the empirical values of multiple experiments.

[0105] Embodiment 1 of the present invention is applicable to medium and low-speed autonomous driving vehicle systems such as park commuting and fixed routes, and various optimization processes are specifically carried out for the safety and comfort of the vehicle, including using vehicle-road collaborative wireless communication technology to improve the accuracy of traffic light signal recognition and increase safety, adopting a segmented PID control strategy to improve control safety and comfort, introducing a calibration vector to limit the deceleration of the vehicle and improve the comfort of passengers, and optimizing the control parameters by combining the autonomous driving map with the driving road characteristics. It is an effective and feasible driving speed control scheme and has been verified and used in actual projects.

[0106] Embodiment 2:

[0107] The present invention also provides a control terminal device for an autonomous driving vehicle, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps in the above method embodiment of Embodiment 1 of the present invention are implemented.

[0108] Further, as an executable solution, the control terminal device for the autonomous driving vehicle may be a computing device such as an in-vehicle computer or a cloud server. The control terminal device for the autonomous driving vehicle may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the above-described composition structure of the control terminal device for the autonomous driving vehicle is only an example of the control terminal device for the autonomous driving vehicle, and does not constitute a limitation on the control terminal device for the autonomous driving vehicle. It may include more or fewer components than the above, or combine some components, or different components. For example, the control terminal device for the autonomous driving vehicle may further include an input / output device, a network access device, a bus, etc. The embodiments of the present invention do not make limitations in this regard.

[0109] Further, as an executable solution, the so-called processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The processor is the control center of the control terminal device for the autonomous driving vehicle, and connects various parts of the entire control terminal device for the autonomous driving vehicle through various interfaces and lines.

[0110] The memory can be used to store the computer program and / or module. By running or executing the computer program and / or module stored in the memory, and invoking the data stored in the memory, the processor realizes various functions of the autonomous vehicle control terminal device. The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include high-speed random access memory, and can also include non-volatile memory, such as a hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one magnetic disk storage device, flash device, or other volatile solid-state storage devices.

[0111] The present invention also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of the above method of the embodiments of the present invention are realized.

[0112] If the modules / units integrated in the autonomous vehicle control terminal device are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be realized. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), and software distribution medium, etc.

[0113] Although the present invention is specifically shown and described in combination with the preferred embodiments, those skilled in the art should understand that various changes can be made to the present invention in terms of form and details without departing from the spirit and scope of the present invention defined by the appended claims, and all of them are within the protection scope of the present invention.

Claims

1. A method for controlling an autonomous vehicle, characterized in that, It includes the following steps: S1: Collect the current road information of the vehicle. The road information includes traffic light information and the maximum driving speed corresponding to the current road; S2: Calculate the distance L to the obstacle and the time to collision TTC between the obstacle and the vehicle during the vehicle's driving; S3: Calculate the target vehicle speed Vt when the vehicle travels to the obstacle; S4: Calculate the control output u according to the magnitude relationship between the distance L and the safe distance L_Safe to the obstacle, and the magnitude relationship between the time to collision TTC and the safe time to collision TTS_Safe; S5: After converting the control output u into a throttle control amount and a braking control amount, control the vehicle using the converted throttle control amount and braking control amount; Among them, the calculation method of the control output u is as follows: (1) When L > L_Safe and TTC > TTS_Safe, set the calculation formula of the control output u as: u = Kp * ev + Kd * dev + Ki1 * Iv + Ki2 * Id ev = Vh – Vt Iv = Iv_last + ev Id = Id_last + L_Safe - L Among them, Kp is the proportionality coefficient, Kd is the differential coefficient, Ki1 and Ki2 are both integral coefficients, ev is the difference term, Vh is the current vehicle speed, Dev is the differential term, Iv is the integral term of speed, Id is the integral term of distance, ΔT represents the time difference between the previous moment and the current moment, ev_last is the difference term of the previous moment, Iv_last is the integral term of speed of the previous moment, and Id_last is the integral term of distance of the previous moment; (2) When TTC ≤ TTS_Warn, the calculation method of the control output u is: When TTC is less than the first-level warning collision time T1, set the control output u = A; otherwise, if TTC is less than the second-level warning collision time T2, set the control output u = A1 + A2 * (T2 - TTC), where A is a fixed value obtained according to experience, and A1 and A2 are both empirical coefficients, and the first-level warning collision time T1 is less than the second-level warning collision time T2; (3) When TTC > TTS_Warn and L ≤ L_Safe, set the calculation formula of the control output u as: u = Kp′ * ev + Kd′ * dev + Ki1′ * Iv + Ki2′ * Id Among them, Kp′ is the proportionality coefficient, Kd′ is the differential coefficient, and Ki1′ and Ki2′ are both integral coefficients; (4) When TTS_Warn < TTC ≤ TTS_Safe and L > L_Safe, set the calculation formula of the control output u as: Among them, Vr is the relative speed of the obstacle relative to the vehicle; The process of converting the control output u into a throttle control amount and a braking control amount is: When the control output u is less than 0, set the braking control amount to 0, and the throttle control amount = K_bias1 - K1 * u; When the control output u is greater than 0, set the throttle control amount to 0, and the braking control amount = K_bias2 + K2 * u; Among them, K_bias1 and K_bias2 are both offsets, and K1 and K2 are both proportionality coefficients.

2. The method for controlling an autonomous vehicle according to claim 1, characterized in that: The traffic light information includes the signal information, location information, and corresponding stop point information of the traffic light; the signal information of the traffic light is collected by communicating with the traffic light controllers installed on both sides of the road.

3. The method for controlling an autonomous vehicle according to claim 1, characterized in that: When the obstacle is a traffic light, the calculation method of the obstacle distance L is as follows: collect the longitude and latitude information of the vehicle's front stop point corresponding to the traffic light and the longitude and latitude information of the vehicle's current location, and calculate the obstacle distance L based on the longitude and latitude information of the traffic light stop point and the longitude and latitude information of the vehicle's current location.

4. The method for controlling an autonomous vehicle according to claim 1, characterized in that: The calculation method of the target vehicle speed Vt when the vehicle travels to the obstacle is as follows: S301: Construct Table 1 that records the corresponding relationship between the obstacle distance and the vehicle driving speed when the vehicle driving requirements are met, and Table 2 that records the corresponding relationship between the obstacle distance and the maximum allowable deceleration of the vehicle braking when the vehicle driving requirements are met, where the maximum value of the vehicle driving speed in Table 1 is less than or equal to the highest driving speed corresponding to the current road; S302: Calculate the vehicle driving speed corresponding to the obstacle distance L based on Table 1 as the predicted target vehicle speed Vt1; S303: Calculate the maximum allowable deceleration a of the vehicle braking corresponding to the obstacle distance L based on Table 2; S304: Determine whether a > (Vh - Vh_last) is satisfied. If so, set the target vehicle speed Vt = (Vh - Vh_last); otherwise, set the target vehicle speed Vt = Vt1; where Vh is the current vehicle speed and Vh_last is the actual vehicle speed of the vehicle at the previous moment.

5. The method for controlling an autonomous vehicle according to claim 4, characterized in that:The method of calculating the vehicle driving speed corresponding to the obstacle distance L based on Table 1 as the predicted target vehicle speed Vt1 is as follows: find two adjacent obstacle distances L1 and L2 to the obstacle distance L in Table 1, and L1 < L2, and obtain the vehicle driving speeds V1 and V2 corresponding to the two obstacle distances L1 and L2, and calculate the predicted target vehicle speed Vt1 according to the following formula:

6. The automatic driving vehicle control method according to claim 1, characterized in that: When the obstacle is a traffic light, the calculation method of the target vehicle speed Vt when the vehicle travels to the obstacle is as follows: when the obstacle distance L is less than the obstacle distance threshold L_min, calculate the time time = L / Vh required for the current vehicle to travel to the stop point corresponding to the traffic light; when the traffic light is green and time > Light_time, or when the traffic light is red and time < Light_time, set the target vehicle speed Vt to 0, where Vh is the current vehicle speed and Light_time is the remaining time of the traffic light.

7. An automatic driving vehicle control system, characterized in that: It includes a processor, a memory, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 6.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, it implements the steps of the method described in any one of claims 1 to 6.

Images