Driving control method, device, equipment and storage medium

Abstract

This application discloses a driving control method, device, equipment, and storage medium. The method includes: obtaining status information of a traffic light at a forward intersection and historical traffic decision information of a vehicle, the status information including: a display color and display duration corresponding to the vehicle's direction of travel, the historical traffic decision information being historical decision information used to guide the vehicle through the forward intersection; determining a driving prediction model corresponding to the display color; performing a time prediction based on the driving prediction model to obtain the arrival time required for the vehicle to travel from its current position to the stop line at the forward intersection; performing a traffic analysis based on the historical traffic decision information, arrival duration, display duration, and a preset hysteresis duration to determine current traffic decision information; and controlling the vehicle to pass through the forward intersection based on the current traffic decision information. Utilizing the technical solution provided by this application, the accuracy of the current traffic decision information can be improved while also improving the stability of previous and subsequent decisions.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and specifically to a driving control method, device, equipment and storage medium. Background Art

[0002] The rise of new energy vehicles has driven the development of autonomous driving technology. Recent research has categorized the application of autonomous driving technology into different scenarios, including traffic light scenarios. The primary challenge for autonomous vehicles in traffic light scenarios is to predict whether they can pass through and then make decisions, such as accelerating to pass or decelerating to stop. Therefore, the decision-making mechanism is crucial for achieving autonomous driving control in traffic light scenarios.

[0003] Existing autonomous driving decision-making mechanisms in traffic light scenarios primarily rely on pre-detection of traffic light status using cameras and, based on the real-time distance to the stop line, formulate decisions to minimize waiting time at the stop line and reduce traffic congestion. However, this approach can render the originally planned decision plan ineffective due to vehicle control errors and the influence of surrounding vehicles. This necessitates repeated replanning, resulting in frequent decision changes and a negative impact on the passenger experience. Summary of the Invention

[0004] This application provides a driving control method, apparatus, device, and storage medium that can improve the accuracy of current traffic decision information while enhancing the stability of previous and subsequent decisions, thereby facilitating autonomous vehicles to respond to traffic light scenarios in an intelligent and comfortable manner. The technical solutions of this application are as follows:

[0005] In one aspect, a driving control method is provided, the method comprising:

[0006] Obtaining status information of a traffic light at a forward intersection and historical traffic decision information of the vehicle, wherein the status information includes a display color and a display duration corresponding to the direction of travel of the vehicle, and the historical traffic decision information is historical decision information used to guide the vehicle through the forward intersection;

[0007] determining a driving prediction model corresponding to the display color;

[0008] Performing a travel time prediction based on the driving prediction model to obtain the travel time required for the vehicle to travel from the current position to the stop line of the preceding intersection;

[0009] Performing a traffic analysis based on the historical traffic decision information, the arrival time, the display time, and the preset delay time to determine current traffic decision information;

[0010] Based on the current traffic decision information, the vehicle is controlled to pass through the front intersection.

[0011] In another aspect, a driving control device is provided, comprising:

[0012] An information acquisition module is used to obtain status information of a traffic light at a forward intersection and historical traffic decision information of the vehicle, wherein the status information includes a display color and display duration corresponding to the direction of travel of the vehicle, and the historical traffic decision information is historical decision information used to guide the vehicle through the forward intersection;

[0013] a driving prediction model determination module, configured to determine a driving prediction model corresponding to the display color;

[0014] A duration prediction module is used to perform a duration prediction based on the driving prediction model to obtain the required arrival time for the vehicle to travel from its current position to the stop line at the preceding intersection;

[0015] a traffic analysis module, configured to perform traffic analysis based on the historical traffic decision information, the arrival time, the display time, and the preset delay time, and determine current traffic decision information;

[0016] A driving control module is used to control the vehicle to pass through the front intersection based on the current traffic decision information.

[0017] On the other hand, a driving control device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the driving control method as described above.

[0018] On the other hand, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by a processor to implement the driving control method as described above.

[0019] The driving control method, device, equipment, and storage medium provided in this application have the following technical effects:

[0020] By utilizing the technical solution provided in this application, a reasonable estimate of the time required for a vehicle to reach the stop line at an intersection is made based on a driving prediction model corresponding to the display color. At the same time, historical traffic decision information and preset delay time are introduced to assist in analyzing traffic decisions based on arrival time. While improving the accuracy of current traffic decision information, it can also improve the stability of previous and subsequent decisions, reduce the possibility of decision jumps, and help autonomous driving vehicles respond to traffic light scenarios in an intelligent and physically comfortable manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 This is a flow chart of a driving control method provided in an embodiment of the present application;

[0023] Figure 2 This is a flow chart of a method for predicting arrival time provided by an embodiment of the present application;

[0024] Figure 3 This is a projection diagram provided by an embodiment of the present application;

[0025] Figure 4 This is a flow chart of another arrival time prediction method provided by an embodiment of the present application;

[0026] Figure 5 This is a flow chart of an embodiment of the present application providing a method for performing traffic analysis based on historical traffic decision information, arrival time, display time, and preset delay time to determine current traffic decision information;

[0027] Figure 6 This is a flowchart of a decision-making mechanism in a traffic light scenario provided by an embodiment of the present application;

[0028] Figure 7 This is a schematic diagram of a driving control device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0029] The following will be combined with the accompanying drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0030] It should be noted that the terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0031] The following describes a driving control method provided by an embodiment of the present application. Figure 1 A flowchart of a driving control method provided in an embodiment of the present application. It should be noted that this specification provides method operation steps as described in the embodiment or flowchart, but may include more or fewer operation steps based on conventional or non-creative work. The order of steps listed in the embodiment is only one way of executing the steps among many, and does not represent the only execution order. When the actual system or product is executed, it can be executed in sequence or in parallel (for example, in a parallel processor or multi-threaded processing environment) according to the method shown in the embodiment or the accompanying drawings. Specifically, Figure 1 As shown, the above method may include:

[0032] S101, obtain the status information of the traffic light at the intersection ahead and the historical traffic decision information of the vehicle. The status information includes: the display color and display duration corresponding to the travel direction of the vehicle. The historical traffic decision information is the historical decision information used to guide the vehicle to pass through the intersection ahead.

[0033] In the embodiment of the present specification, the historical traffic decision information may be traffic decision information determined by traffic analysis at the moment before the current moment.

[0034] In a specific embodiment, the time interval between the previous moment and the current moment can be determined based on a preset decision cycle. Specifically, the preset decision cycle can be pre-set based on actual driving conditions and driving control accuracy. Optionally, the preset decision cycle can be 100ms.

[0035] In a specific embodiment, the traffic decision information can be used to guide the vehicle to pass through the intersection ahead. Specifically, the traffic decision information can instruct: control the vehicle to slow down and stop, or control the vehicle to accelerate and pass through the intersection ahead.

[0036] In the embodiments of this specification, the vehicle may be a vehicle with an automatic driving function.

[0037] In the embodiment of this specification, the direction of travel of the vehicle can be the direction of the vehicle passing the intersection ahead. Specifically, the direction of travel can include: left turn, straight ahead, and right turn. The display color can include: red, yellow, and green. The display duration can be a countdown indication corresponding to the display color.

[0038] In a specific embodiment, when the real-time distance between the vehicle and the stop line at the intersection ahead is less than a preset detection interval, the status information of the traffic light at the intersection ahead and the historical traffic decision information of the vehicle ahead can be obtained.

[0039] Specifically, the preset detection distance can be pre-set based on the driving conditions in actual applications.

[0040] In one example, the vehicle and the high-precision map elements in front can be projected onto the Frenet coordinate system (a coordinate system used to describe the direction of vehicles and obstacles relative to the road) to obtain the projection range of the vehicle on the s axis (S back ,S front ), where S back represents the projection of the rear end of the vehicle and S front Represents the projection of the vehicle's front end; at the same time, determine the coordinates (S, L) of the stop line at the intersection ahead in the Frenet coordinate system; assume that the preset detection distance for entering the traffic light scene is Dis check , when S front In range (S-Dis check , S), it is determined that the vehicle enters the traffic light scene; if the vehicle enters the traffic light scene, the status information of the traffic light at the intersection ahead is obtained.

[0041] Specifically, the high-precision map elements ahead may include but are not limited to: traffic lights, stop lines at intersections, road signs, etc.

[0042] S102: Determine a driving prediction model corresponding to the display color.

[0043] S103: Perform a travel time prediction based on the travel prediction model to obtain the travel time required for the vehicle to travel from the current position to the stop line at the intersection ahead.

[0044] In the embodiment of this specification, the driving prediction model can be used to predict the driving process of the vehicle from the current position to the stop line of the next intersection.

[0045] In a specific embodiment, Figure 2 As shown, before determining the driving prediction model corresponding to the display color, the method may further include:

[0046] S201, obtaining the historical predicted driving trajectory of the vehicle;

[0047] In the embodiments of this specification, the historical predicted driving trajectory can be a predicted driving trajectory generated by trajectory prediction at the previous moment before the current moment. Specifically, the historical predicted driving trajectory can include: multiple predicted trajectory points and the predicted arrival times corresponding to the multiple predicted trajectory points.

[0048] In a specific embodiment, the historical predicted driving trajectory may be a predicted trajectory on a preset road coordinate system. In one example, the preset road coordinate system may be a Frenet coordinate system.

[0049] Accordingly, the above-mentioned determination of the driving prediction model corresponding to the display color may include:

[0050] S202, when the display color is green, determining that the historical predicted driving trajectory is a driving prediction model;

[0051] The above-mentioned time prediction based on the driving prediction model can be used to obtain the time required for the vehicle to reach the stop line at the next intersection from the current position, which can include:

[0052] S203, determining a predicted arrival time of the vehicle at the stop line based on the historical predicted driving trajectory;

[0053] S204: Obtain arrival time based on the difference between the predicted arrival time and the current time.

[0054] In one example, the center position of the stop line is projected onto the historical predicted driving trajectory of the Frenet coordinate system, and the projection point is denoted as P. The projection diagram is shown as follows: Figure 3 As shown, and according to the formula T arrive =T p –T current Calculate the arrival time T arrive , where T p is the timestamp corresponding to point P in the historical predicted driving trajectory, T current The current timestamp.

[0055] It can be seen from the above embodiments that when the display color is green, the time required for the vehicle to reach the stop line at the intersection ahead from the current position is predicted based on the historical predicted driving trajectory, so that the predicted arrival time is slightly longer than the actual arrival time. In this relatively conservative way, a reasonable estimate is made of whether the stop line can be passed in time, thereby greatly reducing the possibility of decision jumps.

[0056] In a specific embodiment, determining the driving prediction model corresponding to the display color may include:

[0057] S401, when the display color is red, determining that the preset uniform acceleration model is the driving prediction model;

[0058] In the embodiments of this specification, the preset uniform acceleration model may be a kinematic model derived from a preset acceleration. Specifically, the preset acceleration may be a target acceleration for the vehicle. The target acceleration may be preset based on actual driving conditions and vehicle speed control requirements. Optionally, the target acceleration may be the maximum acceleration for the vehicle.

[0059] The above-mentioned time prediction based on the driving prediction model can be used to obtain the time required for the vehicle to reach the stop line at the next intersection from the current position, which can include:

[0060] S402, obtaining the current speed and remaining distance of the vehicle, where the remaining distance is the distance from the current position to the stop line;

[0061] S403, determining a preset desired vehicle speed and target acceleration;

[0062] Specifically, the preset expected vehicle speed may be an expected vehicle speed of the vehicle in the current driving scenario.

[0063] In an optional embodiment, the preset expected vehicle speed may be the speed limit of the current road. Optionally, the speed limit is obtained from electronic map data.

[0064] S404, performing acceleration distance analysis based on a preset uniform acceleration model and a target acceleration to obtain the acceleration distance required for the vehicle to increase from its current speed to a preset desired speed;

[0065] S405 , determining the arrival time based on the comparison result of the acceleration distance and the remaining distance.

[0066] Specifically, the target acceleration of the vehicle is recorded as A, the current speed is recorded as V, and the preset expected speed is recorded as V desire , according to the formula Dis remain =S–S front Get the remaining distance Dis from the vehicle to the stop line remain , and according to the formula Dis desire =0.5×(V desire 2 -V 2 ) / A to get the acceleration distance Dis required for the vehicle to change from the current speed to the preset desired speed desire , and based on the acceleration distance Dis deSire Comparison result with the remaining distance Dis remain , determine the arrival time.

[0067] As can be seen from the above embodiments, when the display color is red, the time required for the vehicle to reach the stop line at the intersection ahead from the current position is predicted based on the preset uniform acceleration model, so that the predicted arrival time is slightly longer than the actual arrival time. In this relatively conservative way, a reasonable estimate is made of whether the stop line can be passed in time, thereby greatly reducing the possibility of decision jumps.

[0068] In an optional embodiment, if Figure 4 As shown, the above-mentioned determination of the arrival time based on the comparison result of the acceleration distance and the remaining distance may include:

[0069] S406 , if the comparison result indicates that the acceleration distance is greater than or equal to the remaining distance, performing a vehicle speed analysis based on the current vehicle speed and the target acceleration to determine a predicted vehicle speed when the vehicle reaches the stop line;

[0070] S407 , determining the arrival time based on the ratio of the vehicle speed difference to the target acceleration, where the vehicle speed difference is the difference between the predicted vehicle speed and the current vehicle speed.

[0071] Specifically, when the acceleration distance required to reach the preset desired speed is greater than or equal to the remaining distance (ie, Dis desire ≥Dis remain ), the vehicle can always pass the stop line at the maximum acceleration, so the time required to reach the stop line is calculated using the uniform acceleration model formula T arrive , that is, according to the formula Get the arrival time T arrive .

[0072] In an optional embodiment, if Figure 4 As shown, the above-mentioned determination of the arrival time based on the comparison result of the acceleration distance and the remaining distance may include:

[0073] S408, if the comparison result indicates that the acceleration distance is less than the remaining distance, performing an acceleration duration analysis based on the preset uniform acceleration model and the target acceleration to determine a predicted acceleration duration required for the vehicle to accelerate from the current speed to the preset desired speed;

[0074] S409, determining a predicted travel time from a target position to a stop line based on a preset desired vehicle speed, where the target position is the predicted position of the vehicle after the vehicle has traveled the acceleration distance from its current position;

[0075] S410: The sum of the predicted acceleration time and the predicted driving time is used as the arrival time.

[0076] Specifically, when the acceleration distance required to reach the preset desired speed is less than or equal to the remaining distance (ie, Dis desire Less than Dis remain), the vehicle will first reach the preset desired speed based on the target acceleration and then drive through the stop line at a constant speed based on the preset desired speed. According to the formula T desire =(V desire -V) / A max Calculate the vehicle's speed to reach V desire The predicted acceleration time T required desire , then according to the formula T arrive =T desire +(Dis remain -Dis desire ) / V desire , get the arrival time T arrive .

[0077] It can be seen from the above embodiments that when the remaining distance is less than the acceleration distance, the vehicle can continue to pass the stop line at the maximum acceleration. Otherwise, when the acceleration distance is less than the remaining distance, the vehicle will first reach the preset expected speed at the maximum acceleration and then pass the stop line at a constant speed. By comparing the remaining distance with the acceleration distance, different arrival times can be determined, which can improve the applicability and rationality of the arrival time prediction method.

[0078] S104: Perform traffic analysis based on historical traffic decision information, arrival time, display time, and preset delay time to determine current traffic decision information.

[0079] In the embodiment of this specification, the preset hysteresis time may be a buffer time for reducing frequent decision switching. Specifically, the preset hysteresis time may be pre-set in combination with the stability requirements of decision switching in actual applications. Optionally, the preset hysteresis time may be 1 second.

[0080] In an optional embodiment, if Figure 5 As shown, the above traffic analysis based on historical traffic decision information, arrival time, display time and preset delay time is performed to determine the current traffic decision information, which may include:

[0081] S601, when the display color is red, determining a first duration difference between the display duration and the arrival duration;

[0082] S602 , when the historical traffic decision information indicates controlling the vehicle to decelerate and stop, current traffic decision information is determined based on a comparison result of the first time difference and a preset hysteresis time.

[0083] In a specific embodiment, determining the current passage decision information based on the comparison result of the first time difference and the preset delay time may include:

[0084] When the first time difference is less than the preset hysteresis time, T arrive -T remaln <Tbuffer In the case of , the current traffic decision information is set to: control the vehicle to slow down and stop;

[0085] Or, when the first time difference is greater than or equal to the preset hysteresis time, T arrive -T remain ≥T buffer In the case of , the current traffic decision information is set to: control the vehicle to accelerate through the intersection ahead.

[0086] It can be seen from the above embodiments that when the display color is red and the historical traffic decision information indicates to control the vehicle to slow down and stop, the current traffic decision information is determined based on the comparison result of the first time difference and the preset hysteresis time, and the stability of the previous and subsequent decisions, i.e., the historical traffic decision information and the current traffic decision information, is improved by introducing a hysteresis strategy and considering the historical traffic decision information.

[0087] In an optional embodiment, if Figure 5 As shown, after determining the first duration difference between the display duration and the arrival duration, the method may further include:

[0088] S603 , when the historical traffic decision information indicates controlling the vehicle to accelerate through the intersection ahead, current traffic decision information is determined based on the first time difference.

[0089] In a specific embodiment, determining the current passage decision information based on the first time difference may include:

[0090] In the first time difference is less than 0, that is, T arrive -T remain When <0, the current traffic decision information is set to: control the vehicle to slow down and stop;

[0091] Or, in the first time difference is greater than or equal to 0, that is, T arrive -T remain When ≥0, the current traffic decision information is set to: control the vehicle to accelerate through the intersection ahead.

[0092] It can be seen from the above embodiments that since the historical traffic decision information is also the traffic decision generated after the hysteresis strategy was introduced at the previous moment, when the display color is red and the historical traffic decision information indicates controlling the vehicle to accelerate through the intersection ahead, the current traffic decision information is determined based on the first time difference, that is, the comparison result of the display time and the arrival time, and the hysteresis strategy is no longer introduced, thereby avoiding the impact of excessive buffering time on decision accuracy and improving the accuracy and rationality of the current traffic decision information.

[0093] In an optional embodiment, after performing the travel time prediction based on the driving prediction model to obtain the travel time required for the vehicle to travel from the current position to the next intersection, the method may further include:

[0094] 1) When the display color is green, determine a second duration difference between the arrival duration and the display duration;

[0095] 2) Based on the comparison result of the second time difference and the preset delay time, determine the current passage decision information.

[0096] Specifically, based on the comparison result of the second time difference and the preset delay time, determining the current passage decision information may include:

[0097] When the second time difference is less than or equal to the preset hysteresis time, that is, T remain -T arrive ≤T buffer In the case of , the current traffic decision information is set to: control the vehicle to slow down and stop;

[0098] Or, when the second time difference is greater than the preset hysteresis time, T remain -T arrive >T buffer In the case of , the current traffic decision information is set to: control the vehicle to accelerate through the intersection ahead.

[0099] It can be seen from the above embodiments that when the display color is green, the current traffic decision information is determined based on the comparison result of the second time difference and the preset hysteresis time, and the stability of the previous and next decisions, i.e., the historical traffic decision information and the current traffic decision information, is improved by introducing a hysteresis strategy.

[0100] S105: Based on the current traffic decision information, control the vehicle to pass through the intersection ahead.

[0101] In a specific embodiment, controlling the vehicle to pass through the intersection ahead based on the current traffic decision information may include:

[0102] 1) Obtain driving control decision information;

[0103] Specifically, the driving control decision information here can be used to instruct the vehicle to perform driving control. In a specific embodiment, the driving control decision information can include: decision information for different obstacles and traffic elements.

[0104] 2) Fusing the vehicle speed control decision information and the driving control decision information to obtain the target control information;

[0105] Specifically, the vehicle speed control decision information and the driving control decision information may be fused based on the control priority of the corresponding information to obtain the target control information.

[0106] 3) Based on the target control information, control the vehicle to pass the intersection ahead.

[0107] It can be seen from the above embodiments that a reasonable estimate of the time required for a vehicle to reach the stop line at an intersection is made based on a driving prediction model corresponding to the display color. At the same time, historical traffic decision information and preset delay time are introduced to assist in analyzing traffic decisions based on the arrival time. While improving the accuracy of the current traffic decision information, it can also improve the stability of previous and subsequent decisions and reduce the possibility of decision jumps, which is conducive to autonomous driving vehicles responding to traffic light scenarios in an intelligent and physically comfortable manner.

[0108] In an optional embodiment, after obtaining the status information of the traffic light at the intersection ahead, the method may further include:

[0109] When the display color is yellow, the current traffic decision information is set to control the vehicle to slow down and stop.

[0110] In an optional embodiment, after performing the time prediction based on the driving prediction model to obtain the time required for the vehicle to reach the stop line at the next intersection from the current position, the method may further include:

[0111] 1) Based on the display color and display duration, calculate the remaining time corresponding to the display color.

[0112] Specifically, when the display color is green, the remaining time T remain = Display duration T; When the display color is red, if the left turn direction is red and the vehicle is going straight, T remain =T; if the traffic light for going straight is green and the vehicle is turning left, T remain =T+T yellow , where T yellow Indicates the yellow light waiting time. There is still a yellow light waiting time after the green light in the straight direction ends. Therefore, the yellow light waiting time can be added when calculating the remaining time of the red light in the current direction. Generally, the yellow light waiting time can be 3s. In other cases, T remain =infinity.

[0113] 2) Based on historical traffic decision information, arrival time, remaining time and preset delay time, traffic analysis is performed to determine the current traffic decision information.

[0114] Specifically, the detailed content of "conducting a traffic analysis based on historical traffic decision information, arrival time, remaining time and preset delay time to determine the current traffic decision information" here is similar to the detailed content of the above-mentioned step S104 "conducting a traffic analysis based on historical traffic decision information, arrival time, display time and preset delay time to determine the current traffic decision information". It is only necessary to replace the display time in the relevant detailed scheme with the remaining time here, and no further details will be given here.

[0115] In an optional embodiment, the driving control method provided in the present application may be repeatedly executed based on a preset decision cycle until the vehicle has passed the stop line at the intersection ahead.

[0116] See also Figure 6 , Figure 6 This is a flowchart of a decision-making mechanism in a traffic light scenario provided by an embodiment of the present application. Specifically, when the vehicle is detected to be in a traffic light scenario, the current light color and countdown indication are obtained. 1) If the light is yellow, a deceleration and stop decision is generated; 2) If the light is red, the uniform acceleration model is used to calculate the arrival time T at the stop line. arrive , and then calculate the remaining time T based on the traffic light color and countdown indication in the adjacent direction of the passing direction remain , and compare T arrive and T remain , judge whether it is possible to pass the intersection ahead, and generate a deceleration and stop decision if it is not possible to pass the intersection ahead normally; 3) When the traffic light is green, use the historical predicted driving trajectory to calculate the arrival time T at the stop line arrive , and then use the countdown indication as the remaining time T remain , and compare T arrive and T remain , judge whether it is possible to pass the intersection ahead, and generate a deceleration and stop decision if it is not possible to pass the intersection ahead normally.

[0117] It can be seen from the technical solutions provided by the above embodiments of the present application that, when the display color is green, the time required for the vehicle to reach the stop line at the intersection ahead from the current position is predicted based on the historical predicted driving trajectory; when the display color is red, the time required for the vehicle to reach the stop line at the intersection ahead from the current position is predicted based on the preset uniform acceleration model. The estimated arrival times by these two models will be slightly longer than the actual arrival time. In this relatively conservative way, a reasonable estimate is made of whether the stop line can be passed in time. In addition, historical traffic decision information and preset hysteresis time are introduced to assist in the analysis of traffic decisions based on arrival time. While improving the accuracy of the current traffic decision information, the stability of the previous and subsequent decisions, i.e., the historical traffic decision information and the current traffic decision information, can be improved, and the possibility of decision jumps can be reduced, which is conducive to autonomous driving vehicles responding to traffic light scenarios in an intelligent and comfortable manner.

[0118] The embodiment of the present application provides a driving control device, such as Figure 7 As shown, the above-mentioned device may include:

[0119] Information acquisition module 810 is used to obtain status information of traffic lights at the upcoming intersection and historical traffic decision information of the vehicle. The status information includes: display color and display duration corresponding to the vehicle's travel direction; the historical traffic decision information is historical decision information used to guide the vehicle through the upcoming intersection;

[0120] A driving prediction model determination module 820 is used to determine a driving prediction model corresponding to a display color;

[0121] The duration prediction module 830 is used to perform a duration prediction based on the driving prediction model to obtain the required arrival time for the vehicle to travel from the current position to the stop line at the next intersection;

[0122] Traffic analysis module 840, for performing traffic analysis based on historical traffic decision information, arrival time, display time, and preset delay time to determine current traffic decision information;

[0123] The driving control module 850 is used to control the vehicle to pass the intersection ahead based on the current traffic decision information.

[0124] In a specific embodiment, the above device may further include:

[0125] A historical predicted driving trajectory acquisition module is used to obtain the historical predicted driving trajectory of the vehicle;

[0126] The driving prediction model determination module 820 may include:

[0127] The first module determination unit is used to determine that the historical predicted driving trajectory is a driving prediction model when the display color is green;

[0128] The duration prediction module 830 may include:

[0129] A predicted arrival time determination unit, configured to determine a predicted arrival time of the vehicle when it reaches the stop line based on a historically predicted driving trajectory;

[0130] The first arrival duration unit is configured to obtain an arrival duration based on a difference between the predicted arrival time and the current time.

[0131] In a specific embodiment, the driving prediction model determination module 820 may include:

[0132] The second module determination unit is used to determine that the preset uniform acceleration model is the driving prediction model when the display color is red;

[0133] The duration prediction module 830 may include:

[0134] The remaining distance acquisition unit is used to obtain the current speed and remaining distance of the vehicle. The remaining distance is the distance from the current position to the stop line.

[0135] a preset desired vehicle speed determining unit, configured to determine a preset desired vehicle speed and a target acceleration;

[0136] An acceleration distance analysis unit is used to perform acceleration distance analysis based on a preset uniform acceleration model and a target acceleration to obtain the acceleration distance required for the vehicle to accelerate from its current speed to a preset desired speed;

[0137] The second arrival time unit is configured to determine the arrival time based on a comparison result between the acceleration distance and the remaining distance.

[0138] In an optional embodiment, the second arrival duration unit may include:

[0139] a predicted vehicle speed determination unit, configured to perform a vehicle speed analysis based on the current vehicle speed and the target acceleration to determine a predicted vehicle speed when the vehicle reaches the stop line if the comparison result indicates that the acceleration distance is greater than or equal to the remaining distance;

[0140] The third arrival time unit is used to determine the arrival time based on the ratio of the vehicle speed difference to the target acceleration, where the vehicle speed difference is the difference between the predicted vehicle speed and the current vehicle speed.

[0141] In an optional embodiment, the second arrival duration unit may include:

[0142] an acceleration duration analysis unit, configured to perform an acceleration duration analysis based on a preset uniform acceleration model and a target acceleration to determine a predicted acceleration duration required for the vehicle to accelerate from its current speed to a preset desired speed when the comparison result indicates that the acceleration distance is less than the remaining distance;

[0143] A predicted driving time determination unit, configured to determine a predicted driving time of the vehicle from a target position to a stop line based on a preset expected vehicle speed, wherein the target position is a predicted position of the vehicle after the vehicle has traveled an accelerated distance from its current position;

[0144] The fourth arrival time unit is configured to take the sum of the predicted acceleration time and the predicted driving time as the arrival time.

[0145] In an optional embodiment, the traffic analysis module 840 may include:

[0146] A first duration difference determining unit, configured to determine a first duration difference between the display duration and the arrival duration when the display color is red;

[0147] The first current passage decision information unit is used to determine the current passage decision information based on the comparison result of the first time difference and the preset hysteresis time when the historical passage decision information indicates to control the vehicle to decelerate and stop.

[0148] In an optional embodiment, the above device may further include:

[0149] The second current traffic decision information unit is used to determine the current traffic decision information based on the first time difference when the historical traffic decision information indicates controlling the vehicle to accelerate to pass the front intersection.

[0150] In an optional embodiment, the above device may further include:

[0151] A second duration difference determining unit, configured to determine a second duration difference between the arrival duration and the display duration when the display color is green;

[0152] The third current passage decision information unit is used to determine the current passage decision information based on the comparison result of the second time difference and the preset delay time.

[0153] The device and method embodiments in the above-mentioned device embodiments are based on the same inventive concept.

[0154] An embodiment of the present application provides a driving control device, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the driving control method provided in the above-mentioned method embodiment.

[0155] The memory can be used to store software programs and modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area. The program storage area can store the operating system, application programs required for the functions, etc.; the data storage area can store data created based on the use of the above devices, etc. In addition, the memory can include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0156] The method embodiments provided in the embodiments of the present application can be executed in a vehicle-mounted terminal or a similar computing device, that is, the above-mentioned computer equipment may include a vehicle-mounted terminal or a similar computing device.

[0157] An embodiment of the present application also provides a storage medium, which can be set in a server to store at least one instruction or at least one program related to implementing a driving control method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the driving control method provided by the above method embodiment.

[0158] Optionally, in this embodiment, the storage medium may be located in at least one of a plurality of network servers in a computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media capable of storing program code, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0159] It can be seen from the embodiments of the driving control method, device, equipment or storage medium provided by the present application that, using the technical solution provided by the present application, when the display color is green, the arrival time required for the vehicle to reach the stop line at the intersection ahead is predicted based on the historical predicted driving trajectory; when the display color is red, the arrival time required for the vehicle to reach the stop line at the intersection ahead is predicted based on the preset uniform acceleration model. The arrival times estimated by these two models will be slightly longer than the actual arrival time. In this relatively conservative way, a reasonable estimate is made of whether the stop line can be passed in time. In addition, historical traffic decision information and preset hysteresis time are introduced to assist in the analysis of traffic decision based on arrival time. While improving the accuracy of the current traffic decision information, the stability of the previous and subsequent decisions, i.e., the historical traffic decision information and the current traffic decision information, can be improved, and the possibility of decision jumps can be reduced, which is conducive to the autonomous driving vehicle to respond to traffic light scenarios in an intelligent and physically comfortable manner.

[0160] It should be noted that the order of the embodiments of the present application described above is for descriptive purposes only and does not represent the superiority or inferiority of the embodiments. The above description is of specific embodiments of this specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0161] The various embodiments in this specification are described in a progressive manner. Similar portions between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from the other embodiments. In particular, the device, equipment, and storage medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simplified. For relevant portions, refer to the descriptions of the method embodiments.

[0162] Those skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program. The above program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk, or an optical disk, etc.

[0163] The above is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application.

Claims

1. A driving control method, characterized in that: The method comprises: Obtaining status information of a traffic light at a forward intersection and historical traffic decision information of the vehicle, wherein the status information includes a display color and a display duration corresponding to the direction of travel of the vehicle, and the historical traffic decision information is historical decision information used to guide the vehicle through the forward intersection; determining a driving prediction model corresponding to the display color; Performing a travel time prediction based on the driving prediction model to obtain the travel time required for the vehicle to travel from the current position to the stop line of the preceding intersection; Performing a traffic analysis based on the historical traffic decision information, the arrival time, the display time, and the preset delay time to determine current traffic decision information; Based on the current traffic decision information, the vehicle is controlled to pass through the front intersection.

2. The method according to claim 1, characterized in that Before determining the driving prediction model corresponding to the display color, the method further includes: Obtaining a historical predicted driving trajectory of the vehicle; Determining the driving prediction model corresponding to the display color includes: When the display color is green, determining that the historical predicted driving trajectory is the driving prediction model; The time length prediction based on the driving prediction model to obtain the time length required for the vehicle to reach the stop line at the front intersection from the current position includes: Determining a predicted arrival time of the vehicle at the stop line based on the historical predicted driving trajectory; The arrival duration is obtained based on the difference between the predicted arrival time and the current time.

3. The method according to claim 1, characterized in that Determining the driving prediction model corresponding to the display color includes: When the display color is red, determining the preset uniform acceleration model as the driving prediction model; The time length prediction based on the driving prediction model to obtain the time length required for the vehicle to reach the stop line at the front intersection from the current position includes: Obtaining the current speed and remaining distance of the vehicle, where the remaining distance is the distance from the current position to the stop line; Determine a preset desired vehicle speed and target acceleration; performing an acceleration distance analysis based on the preset uniform acceleration model and the target acceleration to obtain an acceleration distance required for the vehicle to increase from the current speed to the preset desired speed; The arrival time is determined based on a comparison result of the acceleration distance and the remaining distance.

4. The method according to claim 3, characterized in that The determining the arrival time based on the comparison result of the acceleration distance and the remaining distance includes: If the comparison result indicates that the acceleration distance is greater than or equal to the remaining distance, performing a vehicle speed analysis based on the current vehicle speed and the target acceleration to determine a predicted vehicle speed when the vehicle reaches the stop line; determining the arrival time based on a ratio of a vehicle speed difference to the target acceleration, wherein the vehicle speed difference is a difference between the predicted vehicle speed and the current vehicle speed; Alternatively, if the comparison result indicates that the acceleration distance is less than the remaining distance, an acceleration duration analysis is performed based on the preset uniform acceleration model and the target acceleration to determine a predicted acceleration duration required for the vehicle to accelerate from the current vehicle speed to the preset desired vehicle speed; Determining a predicted travel time of the vehicle from a target position to the stop line based on the preset expected vehicle speed, the target position being a predicted position of the vehicle after traveling the acceleration distance from the current position; The sum of the predicted acceleration duration and the predicted driving duration is used as the arrival duration.

5. The method according to claim 1, wherein The performing of traffic analysis based on the historical traffic decision information, the arrival time, the display time, and the preset delay time to determine the current traffic decision information includes: When the display color is red, determining a first duration difference between the display duration and the arrival duration; When the historical passage decision information indicates controlling the vehicle to decelerate and stop, the current passage decision information is determined based on a comparison result of the first time difference and the preset hysteresis time.

6. The method according to claim 5, characterized in that After determining the first duration difference between the display duration and the arrival duration, the method further includes: When the historical traffic decision information indicates controlling the vehicle to accelerate through the front intersection, the current traffic decision information is determined based on the first time difference.

7. The method according to claim 1, characterized in that After performing the time prediction based on the driving prediction model to obtain the time required for the vehicle to travel from the current position to the front intersection, the method further includes: When the display color is green, determining a second duration difference between the arrival duration and the display duration; The current passage decision information is determined based on a comparison result of the second time difference and the preset delay time.

8. A driving control device, characterized in that: The device comprises: An information acquisition module is used to obtain status information of a traffic light at a forward intersection and historical traffic decision information of the vehicle, wherein the status information includes a display color and display duration corresponding to the direction of travel of the vehicle, and the historical traffic decision information is historical decision information used to guide the vehicle through the forward intersection; a driving prediction model determination module, configured to determine a driving prediction model corresponding to the display color; A duration prediction module is used to perform a duration prediction based on the driving prediction model to obtain the required arrival time for the vehicle to travel from its current position to the stop line at the preceding intersection; a traffic analysis module, configured to perform traffic analysis based on the historical traffic decision information, the arrival time, the display time, and the preset delay time, and determine current traffic decision information; A driving control module is used to control the vehicle to pass through the front intersection based on the current traffic decision information.

9. A driving control device, characterized in that: The device includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the driving control method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The storage medium stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the driving control method according to any one of claims 1 to 7.

Images