Intersection passing method, device and equipment and storage medium

Abstract

The invention discloses an intersection passing method, apparatus and device, and a storage medium. The method comprises the steps of obtaining state information of a target vehicle, state information of a VRU and environment information of an intersection; determining the intersection type of the intersection according to the environment information; based on the intersection type, performing prediction and deduction according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environment information, and generating intersection passing decision information; and based on the intersection passing decision information, a control instruction is generated through the longitudinal planner to control passing or braking of the vehicle. Prediction and deduction are carried out based on the intersection type according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environment information, and then the control instruction is generated through the longitudinal planner to control passing or braking of the vehicle based on the generated intersection passing decision information. And the driving safety and comfort of the vehicle at the urban intersection are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of autonomous driving technology, and in particular to a method, device, equipment and storage medium for passing through an intersection. Background Art

[0002] With the rapid development of intelligent driving technology, the highway NOA (Navigate on Autopilot) function can no longer meet the needs of consumers. More and more consumers are beginning to demand urban navigation assistance and memory driving functions. The road conditions in urban areas are more complicated than those on highways, and there are more factors to consider. One typical scenario is the intersection traffic scenario. How to achieve comfortable and safe intersections while taking into account the traffic light information and other traffic participants at the intersection has become a hot topic in industry research.

[0003] Therefore, there is an urgent need for a road intersection passage method that can improve the safety and comfort of vehicles traveling at urban intersections. Summary of the invention

[0004] The main purpose of the present invention is to provide a method, device, equipment and storage medium for passing through an intersection, aiming to solve the technical problem of low safety and comfort of intelligent driving technology in the prior art when driving at urban intersections.

[0005] To achieve the above object, the present invention provides a method for passing through an intersection, the method comprising the following steps:

[0006] Obtain the status information of the target vehicle, the status information of the VRU, and the environment information of the intersection;

[0007] determining the intersection type of the intersection according to the environmental information;

[0008] Based on the type of the intersection, prediction and deduction are performed according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information to generate intersection traffic decision information;

[0009] Based on the intersection traffic decision information, a control instruction is generated by a longitudinal planner to control the vehicle to pass or brake.

[0010] Optionally, the step of determining the intersection type of the intersection according to the environmental information includes:

[0011] Determine whether there is traffic light information in the environmental information, and obtain a determination result;

[0012] If the judgment result indicates that traffic light information exists in the environmental information, determining that the intersection type is a standard intersection;

[0013] If the judgment result indicates that there is no traffic light information in the environmental information, it is determined that the intersection type of the intersection is a non-standard intersection.

[0014] Optionally, the step of generating intersection traffic decision information by predicting and deducing based on the intersection type according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information includes:

[0015] If the intersection type is a standard intersection, determining the current traffic light identification according to the red light information;

[0016] Determine the current driving scene of the vehicle according to the status information of the vehicle, the status information of the target vehicle and the status information of the VRU;

[0017] If the current traffic light is marked as a red light and there is corresponding countdown information, determining the remaining time of the red light according to the countdown information corresponding to the red light;

[0018] According to the current driving scenario and the remaining time of the red light, a uniform speed model is used to perform prediction and deduction to generate intersection traffic decision information.

[0019] Optionally, after the step of determining the current driving scene of the vehicle according to the status information of the vehicle, the status information of the target vehicle and the status information of the VRU, the step further includes:

[0020] If the current traffic light is marked as a green light and there is corresponding countdown information, determining the remaining time of the green light according to the countdown information corresponding to the green light;

[0021] Determine whether there is a preceding vehicle at the intersection based on the current driving scene, where the preceding vehicle refers to the preceding vehicle in the current lane;

[0022] If there is a preceding vehicle at the intersection, a uniform speed model is used to perform prediction and deduction based on the current driving scenario and the remaining time of the green light to generate intersection traffic decision information;

[0023] If there is no preceding vehicle at the intersection, a uniform acceleration model is used to perform prediction and deduction based on the current driving scenario and the remaining time of the green light to generate intersection traffic decision information.

[0024] Optionally, the step of generating intersection traffic decision information by predicting and deducing based on the intersection type according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information, further includes:

[0025] If the intersection type is a non-standard intersection, determining whether there is a VRU at the intersection;

[0026] If there is a VRU at the intersection and the VRU is outside the current lane, predict whether there is a collision risk between the vehicle and the VRU when the VRU enters or leaves the current lane according to the state information of the vehicle, the state information of the VRU and the environmental information, and obtain a prediction result;

[0027] Generate intersection traffic decision information according to the prediction results.

[0028] Optionally, if the intersection type is a non-standard intersection, after the step of determining whether there is a VRU at the intersection, the method further includes:

[0029] If there is a VRU at the intersection and the VRU is in the current lane, determining the distance between the vehicle and the zebra crossing area based on the vehicle status information and the environment information;

[0030] Determine whether the distance between the vehicle and the zebra crossing area is greater than a preset distance threshold, and obtain a distance determination result;

[0031] Predicting whether there is a collision risk between the vehicle and the VRU based on the distance judgment result, the running tracks of the vehicle and the VRU, the status information of the vehicle and the status information of the VRU, and obtaining a prediction result;

[0032] Generate intersection traffic decision information according to the prediction results.

[0033] Optionally, the step of generating a control instruction to control the passage or braking of the vehicle through a longitudinal planner based on the intersection passage decision information includes:

[0034] If the intersection passing decision information indicates that the intersection is passing and there is no preceding vehicle, a cruise mode is executed by a longitudinal planner, and a control instruction is generated based on the cruise mode to control the passing of the vehicle;

[0035] If the intersection passing decision information indicates that the intersection is passing and there is a preceding vehicle, a following vehicle mode is executed by a longitudinal planner, and a control instruction is generated based on the following vehicle mode to control the passing of the self-vehicle;

[0036] If the intersection traffic decision information indicates intersection braking, the longitudinal planner executes the driving mode, and generates a control instruction based on the driving mode to control the braking of the vehicle.

[0037] In addition, to achieve the above-mentioned purpose, the present invention also provides a road crossing device, the device comprising:

[0038] An information acquisition module is used to obtain the status information of the target vehicle, the status information of the VRU, and the environmental information of the intersection;

[0039] An intersection type determination module, used to determine the intersection type of the intersection according to the environmental information;

[0040] A decision generation module, for generating intersection traffic decision information by predicting and deducing based on the intersection type, the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information;

[0041] The longitudinal control module is used to generate control instructions to control the vehicle to pass or brake based on the intersection traffic decision information through a longitudinal planner.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes an intersection passage device, which includes: a memory, a processor, and an intersection passage program stored in the memory and executable on the processor, wherein the intersection passage program is configured to implement the steps of the intersection passage method described above.

[0043] In addition, to achieve the above-mentioned purpose, the present invention further proposes a storage medium, on which a road intersection passing program is stored, and when the road intersection passing program is executed by a processor, the steps of the road intersection passing method described above are implemented.

[0044] The present invention discloses the steps of obtaining the state information of the target vehicle, the state information of the VRU and the environmental information of the intersection; determining the intersection type of the intersection according to the environmental information; based on the intersection type, predicting and deducing according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information to generate intersection traffic decision information; based on the intersection traffic decision information, generating control instructions to control the vehicle to pass or brake through a longitudinal planner. Since the present invention is based on the intersection type, predicting and deducing according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information, and then generating control instructions to control the vehicle to pass or brake through a longitudinal planner based on the generated intersection traffic decision information, compared with the prior art, the present invention effectively improves the safety and comfort of vehicles driving at urban intersections. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A schematic diagram of a flow chart of a first embodiment of a method for passing through an intersection according to the present invention;

[0046] Figure 2 The overall architecture diagram of the intersection passage method of the present invention;

[0047] Figure 3 It is a structural diagram of the longitudinal planner in the intersection traffic method of the present invention;

[0048] Figure 4 It is a schematic diagram of the sliding mode control principle in the intersection passage method of the present invention;

[0049] Figure 5 A diagram showing a parking area determination framework in the intersection passage method of the present invention;

[0050] Figure 6 A schematic diagram of a flow chart of a second embodiment of a method for passing through an intersection according to the present invention;

[0051] Figure 7 A schematic diagram of a standard intersection traffic decision module in the intersection traffic method of the present invention;

[0052] Figure 8 A schematic diagram of a flow chart of a third embodiment of a method for passing through an intersection according to the present invention;

[0053] Fig. 9 A schematic diagram of a non-standard intersection traffic decision module in the intersection traffic method of the present invention;

[0054] Fig.10 This is an example diagram of the VRU on the right side of the lane when passing through a non-standard intersection in the intersection passing method of the present invention;

[0055] Fig.11 It is a structural block diagram of the first embodiment of the intersection traffic device of the present invention;

[0056] Fig.12 It is a structural diagram of the intersection traffic equipment in the hardware operating environment involved in the embodiment of the present invention.

[0057] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0058] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0059] The embodiment of the present invention provides a method for passing through an intersection, referring to Figure 1 , Figure 1 It is a schematic diagram of the flow chart of the first embodiment of the method for passing through an intersection of the present invention.

[0060] In this embodiment, the intersection passing method includes steps S10 to S40:

[0061] Step S10: Acquire the status information of the target vehicle, the status information of the VRU and the environment information of the intersection.

[0062] It should be noted that the execution subject of this embodiment can be a computer server device with data processing, network communication and program running functions used in a car, such as a vehicle controller (VCU) of a car, or an electronic device capable of realizing the above functions, a road crossing device, etc. The following takes a road crossing device (car) including a vehicle controller as an example to illustrate this embodiment and the following embodiments.

[0063] It should be understood that in a specific implementation, the state information of the target vehicle, the state information of the VRU and the environment information of the intersection can be obtained through sensors such as cameras and radars.

[0064] It needs to be explained that the above-mentioned target vehicle may be a vehicle near the vehicle detected by a camera or radar; the status information of the target vehicle may include the position information and speed information of the target vehicle; the status information of the VRU may include the position information and speed information of the VRU; the environmental information of the intersection may include the traffic light information, stop line information, road surface marking information and zebra crossing information of the intersection.

[0065] It should be noted that VRU (Vulnerable Road User) is used to refer to relatively vulnerable road users in road traffic. These users face higher risks when driving on the road due to their own characteristics, such as slower speed, less protection or poor visibility. VRU includes but is not limited to pedestrians, cyclists, motorcyclists, tricycle drivers, and people using other non-motorized vehicles.

[0066] Step S20: Determine the intersection type of the intersection according to the environmental information.

[0067] It should be explained that the above-mentioned intersection types may include standard intersections and non-standard intersections. A standard intersection is an intersection with traffic light information, and a non-standard intersection is an intersection without traffic light information.

[0068] In a specific implementation, it is possible to determine whether there is traffic light information in the environmental information and obtain a judgment result; if the judgment result indicates that there is traffic light information in the environmental information, then the intersection type of the intersection is determined to be a standard intersection; if the judgment result indicates that there is no traffic light information in the environmental information, then the intersection type of the intersection is determined to be a non-standard intersection.

[0069] Step S30: Based on the intersection type, prediction and deduction are performed according to the state information of the own vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information to generate intersection traffic decision information.

[0070] It should be noted that when the vehicle approaches an intersection, if the intersection type is a standard intersection, the straight or turn arrow signs on the road surface and the traffic light information of the vehicle's lane can be determined based on environmental information; then, based on the traffic light information, the vehicle's status information, and the target vehicle's status information, predictions and deductions are performed to determine whether the vehicle can pass through the intersection.

[0071] When the vehicle approaches an intersection, if the intersection type is a non-standard intersection, the straight or turn arrow mark on the road surface can be determined based on the environmental information; then, based on the traffic light information, the status information of the vehicle, the status information of the target vehicle and the status information of the VRU, a prediction is made to determine whether the vehicle can pass through the intersection.

[0072] It should be explained that the above-mentioned intersection traffic decision information may include three situations: the intersection can be passed without a preceding vehicle, the intersection can be passed with a preceding vehicle and the intersection brakes.

[0073] Step S40: Based on the intersection traffic decision information, a longitudinal planner generates a control instruction to control the vehicle to pass or brake.

[0074] It should be understood that the longitudinal planner is mainly responsible for planning the vehicle's driving state in the time dimension, that is, speed planning and acceleration planning. It determines the vehicle's driving speed, acceleration and other parameters in the future based on road conditions, traffic conditions, vehicle dynamics and passenger comfort requirements, thereby generating a safe, comfortable and efficient driving trajectory.

[0075] It should be noted that controlling the braking of the vehicle refers to controlling the vehicle to slow down or stop moving.

[0076] For example, refer to Figure 2 , Figure 2 The overall architecture diagram of the intersection passage method of the present invention. In the figure, first, the speed and position information of the target vehicle and VRU, as well as the traffic light information, stop line and other environmental information of the intersection are obtained; then it is determined whether there is traffic light information at the intersection, and the intersection type is divided into standard intersection and non-standard intersection to perform the intersection passage decision module; in the intersection passage decision module, if there is traffic light information at the intersection, the intersection type is determined to be a standard intersection, and prediction and deduction are performed based on the traffic light information at the intersection, the target vehicle connection and the position and speed information of the vehicle, and a decision is made whether the intersection can be passed; in the intersection passage decision module, if there is no traffic light information at the intersection, the intersection type is determined to be a non-standard intersection, and prediction and deduction are performed based on the target vehicle, VUR and the position and speed information of the vehicle, and a decision is made whether the intersection can be passed; if the intersection cannot be passed, the longitudinal planner is used to solve, the longitudinal deceleration for comfortable braking at the intersection is calculated, and the vehicle braking is controlled; if the intersection can be passed, the longitudinal planner is used to solve, the longitudinal acceleration of the intersection is calculated, and the vehicle is controlled to pass the intersection.

[0077] After the intersection traffic decision module outputs the intersection traffic signal (i.e., intersection traffic decision information), the longitudinal planner controls the vehicle to perform the corresponding acceleration and deceleration. The architecture of the longitudinal planner is as follows: Figure 3 As shown, Figure 3 The longitudinal planner in the intersection traffic method of the present invention is an architectural diagram. In the figure, the longitudinal planner (Lgt Planner) includes three control modes: Cruise_Pln (cruise mode), Follow_Pln (following mode) and Creep_Pln (creeping mode). The cruise mode refers to a mode in which the vehicle is controlled to move forward at a speed preset by the driver without continuously stepping on the accelerator pedal. The following mode refers to a mode in which the vehicle senses the vehicle in front and automatically adjusts the speed of the vehicle according to the speed change of the vehicle in front to maintain a safe distance. The creeping mode refers to a mode in which the vehicle is controlled to brake and start comfortably.

[0078] In a specific implementation, if the intersection passage decision information indicates that the vehicle is to pass the intersection and there is no vehicle ahead, the cruise mode is executed through the longitudinal planner, and a control instruction is generated based on the cruise mode to control the vehicle to pass; if the intersection passage decision information indicates that the vehicle is to pass the intersection and there is a vehicle ahead, the following mode is executed through the longitudinal planner, and a control instruction is generated based on the following mode to control the vehicle to pass; if the intersection passage decision information indicates braking at the intersection, the steering mode is executed through the longitudinal planner, and a control instruction is generated based on the steering mode to control the braking of the vehicle.

[0079] For example, refer to Figure 4 , Figure 4 This is a schematic diagram of the sliding mode control principle in the intersection passing method of the present invention. Follow_Pln is designed based on the sliding film control algorithm. By solving Follow_Pln, the vehicle and the preceding vehicle are controlled to maintain a safe distance through the intersection. In the figure, the entire sliding mode control process consists of two parts: 1. Normal motion segment: located outside the section, as shown in the figure x0→A segment; 2. Sliding mode motion segment: located in the sliding mode area on the section, as shown in the figure A→O segment.

[0080] In this embodiment, the steps of designing the synovial control are as follows:

[0081] 1. System state equation:

[0082]

[0083] Among them, R represents the relative distance Range; RR represents the relative speed, represents the derivative of R, represents the derivative of RR.

[0084] 2. Set the switching function:

[0085]

[0086] Among them, A ego A represents the acceleration of the vehicle; lead represents the acceleration of the preceding vehicle, and α1 and α2 are calibration parameters that make the equation S=α1R+α2RR approach a steady state.

[0087] Movement along the synovial surface:

[0088]

[0089] 3. Set the approach rate:

[0090]

[0091] Movement along the synovial surface:

[0092]

[0093] In the approach motion stage, the designed synovial control can make the system move quickly toward the sliding surface at a relatively high speed. In the sliding mode stage, it is not desirable for the system to have a very high speed, otherwise it will cause movement back and forth across the synovial surface (i.e., chattering). Based on Lyapunov's second method, an approach rate is selected to ensure that when the synovial surface S=0 is reached, the state variables will gradually tend to a steady state after reaching the sliding surface.

[0094] It needs to be explained that is a constant speed approach rate, and there may be other approach rates. In this embodiment, Follow_Pln selects a constant speed approach rate. It should be understood that A ego_req It can be the control quantity output by the longitudinal planner, that is, the control instruction generated by the longitudinal planner.

[0095] It should be understood that under Follow_Pln (following mode), there are also a variety of different following scenarios, for example, 1. There is a car in front and no car behind; 2. There is a car in front and a car behind, etc.

[0096] It should be noted that in Creep_Pln (Ruxing mode), it is necessary to determine in real time whether the vehicle is in the parking area. If the vehicle is not in the parking area, the vehicle is controlled by Follow_Pln or Cruise_Pln. Only when the vehicle is in the parking area, the vehicle will perform Creep_Pln. For example, refer to Figure 5 , Figure 5This is the architecture diagram for judging the parking area in the intersection passing method of the present invention. In the figure, the inputs are: the flag bit (TargetExistFlag) indicating whether there is a preceding vehicle target currently, the relative distance (Range) between the host vehicle and the preceding vehicle (if there is no preceding vehicle, Range represents the distance from the host vehicle to the intersection stop line), the speed of the host vehicle (VehicleSpeed), the speed difference (RangeRate) between the host vehicle and the preceding vehicle (if there is no preceding vehicle, it represents the speed reduction when the host vehicle brakes to a stop), and the flag bit (TargetStationary) indicating whether the preceding vehicle is stationary; then, based on the input parameters, it is determined in real time whether the host vehicle is in the parking area; the output is: the flag bit (InStopZone) for judging whether the current host vehicle is in the parking area.

[0097] InStopZone is 1 when all of the following conditions are satisfied simultaneously:

[0098] 1. Range < 5m;

[0099] 2. TargetStationary < 1m / s (if there is no preceding vehicle, it is defaulted to 0);

[0100] 3. RangeRate < K1 (empirical value);

[0101] 4. TargetExistFlag does not change (if there is no preceding vehicle, it represents the confidence level of the stop line).

[0102] It should be noted that Creep_Pln is mainly designed based on the PID algorithm, as detailed below:

[0103]

[0104] It should be noted that when the host vehicle enters the parking area, the expected speed V is obtained by looking up the table based on the relative distance between the host vehicle and the preceding vehicle or the stop line desire , and the difference is taken with the current speed V cur , and through the proportionality coefficient K p , the acceleration A is calculated creep , to control the vehicle to stop comfortably; when the host vehicle leaves the parking area, if there is a preceding vehicle, it follows the preceding vehicle to start comfortably with the starting acceleration A start , if there is no preceding vehicle, a small acceleration A_follow is sent based on Creep_Pln (creeping mode) to control the vehicle to start comfortably.

[0105] Cruise_Pln (cruise mode) is also mainly designed based on the PID algorithm, as detailed below:

[0106]

[0107] It should be noted that Cruise_Pln has two modes, one is efficiency mode and the other is normal mode: 1. When in efficiency mode, the longitudinal planner will calculate the vehicle speed V based on the intersection decision module. desire2 , calculate a corresponding A cruise , and sends it to the actuator to control the vehicle to "rush" through the intersection; 2. When in the inefficient traffic mode, the longitudinal planner will be based on the road speed limit V at the intersection. desire1 , calculate a corresponding A cruise , and sent to the actuator to control the vehicle to cross the intersection comfortably.

[0108] In a specific implementation, the feasibility of the intersection passage method of the present invention can also be verified through simulation.

[0109] This embodiment discloses obtaining the state information of the target vehicle, the state information of the VRU, and the environmental information of the intersection; determining the intersection type of the intersection according to the environmental information; based on the intersection type, predicting and deducing according to the state information of the own vehicle, the state information of the target vehicle, the state information of the VRU, and the environmental information, generating intersection traffic decision information; based on the intersection traffic decision information, generating control instructions to control the passage or braking of the own vehicle through a longitudinal planner. Since this embodiment is based on the intersection type, predicting and deducing according to the state information of the own vehicle, the state information of the target vehicle, the state information of the VRU, and the environmental information, and then generating control instructions to control the passage or braking of the own vehicle through a longitudinal planner based on the generated intersection traffic decision information, compared with the prior art, this embodiment effectively improves the safety and comfort of vehicles driving at urban intersections.

[0110] refer to Figure 6 , Figure 6 It is a flowchart diagram of the second embodiment of the method for passing through an intersection of the present invention.

[0111] Based on the above first embodiment, in this embodiment, step S30 includes steps S301 to S304:

[0112] Step S301: If the intersection type is a standard intersection, determine the current traffic light sign according to the red light information.

[0113] Step S302: Determine the current driving scene of the own vehicle according to the state information of the own vehicle, the state information of the target vehicle and the state information of the VRU.

[0114] Step S303: If the current traffic light is marked as a red light and there is corresponding countdown information, the remaining time of the red light is determined according to the countdown information corresponding to the red light.

[0115] Step S304: Based on the current driving scenario and the remaining time of the red light, a uniform speed model is used to perform prediction and deduction to generate intersection traffic decision information.

[0116] It should be noted that after step S302, it also includes: if the current traffic light is marked as a green light and there is corresponding countdown information, then the remaining time of the green light is determined according to the countdown information corresponding to the green light; based on the current driving scenario, it is determined whether there is a preceding vehicle at the intersection, and the preceding vehicle refers to the vehicle in front of the current lane; if there is a preceding vehicle at the intersection, based on the current driving scenario and the remaining time of the green light, a uniform speed model is used to perform prediction and deduction to generate intersection passage decision information; if there is no preceding vehicle at the intersection, based on the current driving scenario and the remaining time of the green light, a uniform acceleration model is used to perform prediction and deduction to generate intersection passage decision information.

[0117] It should be noted that the uniform speed model of the vehicle is as follows:

[0118] S_ego=V_ego*t;

[0119] Among them, V_ego is the speed of the vehicle, t is the driving time of the vehicle, and S_ego is the distance traveled by the vehicle.

[0120] It should be noted that the uniform acceleration model of the vehicle is as follows:

[0121] S_ego=V_ego*t+0.5*Areq*t*t';

[0122] Among them, V_ego is the speed of the ego vehicle, t' is the time the ego vehicle travels, Areq is the acceleration of the ego vehicle, and S_ego is the distance the ego vehicle travels.

[0123] For example, refer to Figure 7 , Figure 7 The figure is a schematic diagram of the standard intersection traffic decision module in the intersection traffic method of the present invention. In the figure, when the traffic light at the intersection is red; if the current state satisfies condition 1, it means that traffic can be achieved (that is, after the red light turns green, the vehicle does not need to slow down and can continue to drive, which means that the vehicle can pass the intersection at the current speed); if the current state satisfies condition 2 or 3, it means that the vehicle needs to brake at the intersection. When the traffic light at the intersection is green; if the current state satisfies condition 4, 5 or 6, it means that traffic can be achieved; if the current state satisfies condition 7 or 8, it means that the vehicle needs to brake at the intersection.

[0124] It should be noted that condition 1 is:

[0125] Cur_V*(Tred-offset)<remainingDis&&Cur_V> V_Limit;

[0126] In the formula, Cur_V is the current speed of the vehicle, Tred is the remaining time of the red light, remainingDis is the distance to the stop line of the intersection, V_Limit is the minimum speed for passing the intersection, and offset is the redundancy for the remaining time of the red light. That is, if the vehicle is driving at a constant speed at the current speed, and the distance traveled during the remaining time of the red light does not exceed the intersection, after the red light turns green, the vehicle does not need to slow down and can continue to drive, which means that the vehicle can pass the intersection at the current speed.

[0127] Condition 2 is: Red Light without counter, which means that the red light at the intersection has no countdown information.

[0128] Condition 3 is: Cur_V*(Tred-offset)≥remainingDis or Cur_V≤V_Limit.

[0129] When the traffic light at the intersection is green, if the green light has countdown information, a judgment is made based on the remaining time of the green light and the vehicle's speed. When condition 4 is met, the decision state machine outputs a crossing signal.

[0130] Condition 4 is:

[0131] Cur_V*(Tgreen-offset)>remainingDis;

[0132] In the formula, Cur_V is the current speed of the vehicle, Tgreen is the remaining time of the green light, remainingDis is the distance to the stop line of the intersection, and offset is the redundant offset for the remaining time of the green light. That is, if the vehicle is driving at a constant speed at the current speed and can successfully pass the intersection within the remaining time of the green light, it means that the vehicle can pass the intersection at the current speed.

[0133] If condition 4 is not satisfied, that is, condition 7 is satisfied, then the decision state machine outputs a signal to brake at the intersection. Condition 7 is: Cur_V*(Tgreen-offset)≤remainingDis.

[0134] Efficiency mode: If there is no vehicle ahead at the intersection and there is countdown information on the green light, the uniform acceleration model can be used to predict the distance traveled by the vehicle, and combined with the remaining time of the green light, it can be determined whether the intersection can be crossed. When condition 6 is met, the decision state machine outputs a crossing signal, and condition 6 is as follows:

[0135] Cur_V*(Tgreen-offset)+0.5*A_Setspd*(Tgreen-offse')*(Tgreen-offset')>remainingDis;

[0136] Among them, Cur_V is the current speed of the vehicle, Tgreen is the remaining time of the green light, remainingDis is the distance to the stop line of the intersection, A_Setspd is the comfortable acceleration for the request to pass the green light, and offset' is the redundancy for the remaining time of the green light. That is, if there is no vehicle ahead at the intersection, the uniform acceleration model is used to predict the distance that the vehicle will travel within the remaining time of the green light. If the vehicle can pass the intersection, it means that the vehicle can pass the intersection with uniform acceleration.

[0137] If condition 6 is not satisfied, that is, condition 8 is satisfied, it means that the vehicle cannot pass the intersection even if it accelerates, and the decision state machine outputs a signal to brake at the intersection. Condition 8 is:

[0138] Cur_V*(Tgreen-offset)+0.5*A_Setspd*(Tgreen-offse')*(Tgreen-offset')≤remainingDis;

[0139] Condition 5 is: GreenLightWithout counter, which means that the green light at the intersection has no countdown information, and the decision state machine outputs a crossing signal.

[0140] This embodiment discloses that if the intersection type is a standard intersection, the current traffic light identification is determined according to the red light information; the current driving scene of the own vehicle is determined according to the status information of the own vehicle, the status information of the target vehicle and the status information of the VRU; if the current traffic light identification is a red light and there is corresponding countdown information, the remaining time of the red light is determined according to the countdown information corresponding to the red light; according to the current driving scene and the remaining time of the red light, a uniform speed model is used to perform prediction and deduction to generate intersection traffic decision information. This embodiment performs prediction and deduction based on red light information, the status information of the own vehicle and the status information of the target vehicle when the intersection type is a standard intersection, and generates intersection traffic decision information. Compared with the prior art, this embodiment effectively improves the safety of vehicles driving at urban intersections with traffic light information.

[0141] refer to Figure 8 , Figure 8 It is a schematic flow chart of the third embodiment of the method for passing through an intersection of the present invention.

[0142] Based on the above embodiments, in this embodiment, the step S30 further includes steps S301' to S303':

[0143] Step S301': If the intersection type is a non-standard intersection, determine whether there is a VRU at the intersection.

[0144] Step S302': if there is a VRU at the intersection and the VRU is outside the current lane, predict whether there is a collision risk between the vehicle and the VRU when the VRU enters or leaves the current lane based on the vehicle status information, the VRU status information and the environmental information, and obtain a prediction result.

[0145] Step S303': Generate intersection traffic decision information according to the prediction result.

[0146] It should be noted that after step S301', it also includes: if there is a VRU at the intersection and the VRU is in the current lane, determining the distance between the vehicle and the zebra crossing area based on the status information of the vehicle and the environmental information; judging whether the distance between the vehicle and the zebra crossing area is greater than a preset distance threshold, and obtaining a distance judgment result; predicting whether there is a collision risk between the vehicle and the VRU based on the distance judgment result, the running trajectory of the vehicle and the VRU, the status information of the vehicle and the status information of the VRU, and obtaining a prediction result; and generating intersection traffic decision information according to the prediction result.

[0147] It should be understood that if the distance between the vehicle and the zebra crossing area is less than the preset distance threshold, it means that the vehicle is close to the zebra crossing area; if the distance between the vehicle and the zebra crossing area is greater than or equal to the preset distance threshold, it means that the vehicle is not close to the zebra crossing area.

[0148] For example, refer to Fig. 9 , Fig. 9 This is a schematic diagram of the non-standard intersection traffic decision module in the intersection traffic method of the present invention. In the figure, when there is no traffic light information at the intersection and there is no VRU target, the non-standard intersection decision module directly outputs the intersection traffic signal. When there is a VRU target and the VRU target is outside the lane, the intersection decision module is required to predict and determine whether there is a collision risk between the vehicle and the VRU when the VRU enters or leaves the lane, as follows:

[0149]

[0150] v veh *time reach >x VRU -x veh +L veh

[0151] v veh *time leave <x VRU -x veh-L veh ;

[0152] In the formula, time reach Indicates the time when VRU enters the right lane line, y_RLane indicates the lateral coordinate of the right lane line, y_VRU indicates the lateral coordinate of VRU, v_VRU indicates the lateral speed of VRU, time leach Indicates the time when the VRU leaves the left lane line, y LLane Indicates the lateral coordinate of the left lane line, v veh represents the speed of the vehicle, x VRU Indicates the vertical position of the VRU, x veh represents the longitudinal position of the vehicle, L veh Indicates the length of the vehicle.

[0153] For example, refer to Fig.10 , Fig.10 This is an example diagram of the VRU on the right side of the lane when passing a non-standard intersection in the intersection passing method of the present invention. In the figure, VRU is taken as an example on the right side of the lane. If the longitudinal position of the vehicle has exceeded VRU when VRU just enters the lane, the non-standard intersection decision module outputs an intersection passing signal, otherwise it outputs an intersection braking signal; if the longitudinal position of the vehicle does not exceed VRU when VRU just leaves the lane, the non-standard intersection decision module outputs an intersection passing signal, otherwise it outputs an intersection braking signal; if VRU is in the lane, but the vehicle is not close to the zebra crossing area, it is necessary to predict whether there is a collision risk based on VRU and the vehicle trajectory, and the detailed design is as follows:

[0154]

[0155] v veh *time leave <x VRU -x veh -L veh .

[0156] That is, if the VRU is in the lane, and the longitudinal position of the ego vehicle is predicted to be no more than that of the VRU when the VRU leaves the lane, that is, there is no risk of collision. However, for safety reasons, the non-standard intersection decision module outputs a signal to yield to pedestrians (lowering the target speed of the ego vehicle), otherwise it outputs an intersection brake signal;

[0157] It should be noted that if the VRU is in the lane and the ego vehicle is close to the zebra crossing area, it is necessary to predict whether there is a collision risk based on the VRU and ego vehicle trajectory. The detailed design is as follows:

[0158] cross linex -offset x <x VRU <cross linex+offset x ;

[0159] y VRU <offset y ;

[0160] x VRU -x veh <v veh *t collison ;

[0161] x VRU -x veh <dis_collison。

[0162] That is, when the VRU is in the zebra crossing area, if the vehicle is close to the target or there is a risk of collision in a short time, the non-standard intersection decision module outputs an intersection brake signal, otherwise it outputs an intersection pass signal.

[0163] This embodiment discloses that if the intersection type is a non-standard intersection, it is determined whether there is a VRU at the intersection; if there is a VRU at the intersection and the VRU is outside the current lane, it is predicted whether there is a collision risk between the vehicle and the VRU when the VRU enters or leaves the current lane based on the status information of the vehicle, the status information of the VRU and the environmental information, and a prediction result is obtained; if there is a VRU at the intersection and the VRU is in the current lane, the distance between the vehicle and the zebra crossing area is determined based on the status information of the vehicle and the environmental information; it is determined whether the distance between the vehicle and the zebra crossing area is greater than a preset distance threshold, and a distance judgment result is obtained; based on the distance judgment result, the running trajectory of the vehicle and the VRU, the status information of the vehicle and the status information of the VRU, it is predicted whether there is a collision risk between the vehicle and the VRU, and a prediction result is obtained; and intersection traffic decision information is generated according to the prediction result. Compared with the prior art, this embodiment effectively improves the safety of vehicles driving at urban intersections where there is no traffic light information.

[0164] In addition, an embodiment of the present invention further proposes a storage medium, on which a road intersection passing program is stored. When the road intersection passing program is executed by a processor, the steps of the road intersection passing method described above are implemented.

[0165] Reference Fig.11 , Fig.11 It is a structural block diagram of the first embodiment of the intersection traffic device of the present invention.

[0166] like Fig.11 As shown, the intersection passage device proposed in the embodiment of the present invention includes: an information acquisition module 901, an intersection type judgment module 902, a decision generation module 903 and a longitudinal control module 904.

[0167] The information acquisition module 901 is used to acquire the status information of the target vehicle, the status information of the VRU and the environment information of the intersection.

[0168] The intersection type determination module 902 is used to determine the intersection type of the intersection according to the environmental information.

[0169] The decision generation module 903 is used to generate intersection traffic decision information by predicting and deducing based on the intersection type, the state information of the own vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information.

[0170] The longitudinal control module 904 is used to generate a control instruction to control the vehicle to pass or brake based on the intersection traffic decision information through a longitudinal planner.

[0171] The intersection type judgment module 902 is also used to judge whether there is traffic light information in the environmental information and obtain a judgment result; if the judgment result indicates that there is traffic light information in the environmental information, the intersection type of the intersection is determined to be a standard intersection; if the judgment result indicates that there is no traffic light information in the environmental information, the intersection type of the intersection is determined to be a non-standard intersection.

[0172] The longitudinal control module 904 is also used to execute the cruise mode through the longitudinal planner if the intersection passage decision information indicates that the vehicle is passing the intersection and there is no vehicle ahead, and generate a control instruction based on the cruise mode to control the passage of the vehicle; if the intersection passage decision information indicates that the vehicle is passing the intersection and there is a vehicle ahead, execute the following mode through the longitudinal planner, and generate a control instruction based on the following mode to control the passage of the vehicle; if the intersection passage decision information indicates braking at the intersection, execute the steering mode through the longitudinal planner, and generate a control instruction based on the steering mode to control the braking of the vehicle.

[0173] The embodiment of the present device discloses obtaining the state information of the target vehicle, the state information of the VRU, and the environmental information of the intersection; determining the intersection type of the intersection according to the environmental information; based on the intersection type, predicting and deducing according to the state information of the own vehicle, the state information of the target vehicle, the state information of the VRU, and the environmental information, generating intersection traffic decision information; based on the intersection traffic decision information, generating control instructions to control the passage or braking of the own vehicle through a longitudinal planner. Since the embodiment of the present device predicts and deduces according to the state information of the own vehicle, the state information of the target vehicle, the state information of the VRU, and the environmental information based on the intersection type, and then generates control instructions to control the passage or braking of the own vehicle through a longitudinal planner based on the generated intersection traffic decision information, compared with the prior art, the embodiment of the present device effectively improves the safety and comfort of vehicles driving at urban intersections.

[0174] Based on the above-mentioned first embodiment of the road intersection passage device of the present invention, a second embodiment of the road intersection passage device of the present invention is proposed.

[0175] In this embodiment, the decision generation module 903 is also used to determine the current traffic light sign according to the red light information if the intersection type is a standard intersection; determine the current driving scene of the vehicle according to the status information of the vehicle, the status information of the target vehicle and the status information of the VRU; if the current traffic light sign is a red light and there is corresponding countdown information, determine the remaining time of the red light according to the countdown information corresponding to the red light; and generate intersection traffic decision information by using a uniform speed model for prediction and deduction based on the current driving scene and the remaining time of the red light.

[0176] The decision generation module 903 is also used to determine the remaining time of the green light according to the countdown information corresponding to the green light if the current traffic light is marked as a green light and there is corresponding countdown information; determine whether there is a preceding vehicle at the intersection based on the current driving scenario, and the preceding vehicle refers to the vehicle in front of the current lane; if there is a preceding vehicle at the intersection, predict and deduce using a uniform speed model based on the current driving scenario and the remaining time of the green light to generate intersection passage decision information; if there is no preceding vehicle at the intersection, predict and deduce using a uniform acceleration model based on the current driving scenario and the remaining time of the green light to generate intersection passage decision information.

[0177] Other embodiments or specific implementations of the intersection passage device of the present invention can refer to the above-mentioned method embodiments, which will not be described in detail here.

[0178] The present application provides an intersection passage device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the intersection passage method in the above-mentioned embodiment one.

[0179] Reference below Fig.12, which shows a schematic diagram of the structure of a road crossing device suitable for implementing the embodiment of the present application. The road crossing device in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Fig.12 The intersection traffic equipment shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0180] like Fig.12 As shown, the intersection access device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM) 1004. Various programs and data required for the operation of the intersection access device are also stored in the RAM 1004. The processing device 1001, the ROM 1002, and the RAM 1004 are connected to each other via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the intersection access device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an intersection access device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have instead.

[0181] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0182] The intersection passage equipment provided by the present application adopts the intersection passage method in the above embodiment, which can solve the technical problem of low safety and comfort of intelligent driving technology in the existing technology at urban intersections. Compared with the existing technology, the beneficial effects of the intersection passage equipment provided by the present application are the same as the beneficial effects of the intersection passage method provided by the above embodiment, and the other technical features of the intersection passage equipment are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0183] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0184] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0185] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0186] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0187] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0188] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for passing through an intersection, characterized in that: The method comprises: Obtain the status information of the target vehicle, the status information of the VRU, and the environment information of the intersection; determining the intersection type of the intersection according to the environmental information; Based on the type of the intersection, prediction and deduction are performed according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information to generate intersection traffic decision information; Based on the intersection traffic decision information, a control instruction is generated by a longitudinal planner to control the vehicle to pass or brake.

2. The method for passing through an intersection as claimed in claim 1, characterized in that: The step of determining the intersection type of the intersection according to the environmental information comprises: Determine whether there is traffic light information in the environmental information, and obtain a determination result; If the judgment result indicates that traffic light information exists in the environmental information, determining that the intersection type is a standard intersection; If the judgment result indicates that there is no traffic light information in the environmental information, it is determined that the intersection type of the intersection is a non-standard intersection.

3. The method for passing through an intersection as claimed in claim 2, characterized in that: The step of generating intersection traffic decision information by predicting and deducing based on the intersection type according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information comprises: If the intersection type is a standard intersection, determining the current traffic light identification according to the red light information; Determine the current driving scene of the vehicle according to the status information of the vehicle, the status information of the target vehicle and the status information of the VRU; If the current traffic light is marked as a red light and there is corresponding countdown information, determining the remaining time of the red light according to the countdown information corresponding to the red light; According to the current driving scenario and the remaining time of the red light, a uniform speed model is used to perform prediction and deduction to generate intersection traffic decision information.

4. The method for passing through an intersection as claimed in claim 3, characterized in that: After the step of determining the current driving scene of the vehicle according to the status information of the vehicle, the status information of the target vehicle and the status information of the VRU, the method further includes: If the current traffic light is marked as a green light and there is corresponding countdown information, determining the remaining time of the green light according to the countdown information corresponding to the green light; Determine whether there is a preceding vehicle at the intersection based on the current driving scene, where the preceding vehicle refers to the preceding vehicle in the current lane; If there is a preceding vehicle at the intersection, a uniform speed model is used to perform prediction and deduction based on the current driving scenario and the remaining time of the green light to generate intersection traffic decision information; If there is no preceding vehicle at the intersection, a uniform acceleration model is used to perform prediction and deduction based on the current driving scenario and the remaining time of the green light to generate intersection traffic decision information.

5. The method for passing through an intersection as claimed in claim 2, characterized in that: The step of generating intersection traffic decision information by predicting and deducing based on the intersection type according to the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information also includes: If the intersection type is a non-standard intersection, determining whether there is a VRU at the intersection; If there is a VRU at the intersection and the VRU is outside the current lane, predict whether there is a collision risk between the vehicle and the VRU when the VRU enters or leaves the current lane according to the state information of the vehicle, the state information of the VRU and the environmental information, and obtain a prediction result; Generate intersection traffic decision information according to the prediction results.

6. The method for passing through an intersection as claimed in claim 5, characterized in that: If the intersection type is a non-standard intersection, after the step of determining whether there is a VRU at the intersection, the method further includes: If there is a VRU at the intersection and the VRU is in the current lane, determining the distance between the vehicle and the zebra crossing area based on the vehicle status information and the environment information; Determine whether the distance between the vehicle and the zebra crossing area is greater than a preset distance threshold, and obtain a distance determination result; Predicting whether there is a collision risk between the vehicle and the VRU based on the distance judgment result, the running tracks of the vehicle and the VRU, the status information of the vehicle and the status information of the VRU, and obtaining a prediction result; Generate intersection traffic decision information according to the prediction results.

7. The method for passing through an intersection as claimed in claim 1, characterized in that: The step of generating a control instruction to control the passage or braking of the vehicle through a longitudinal planner based on the intersection passage decision information includes: If the intersection passing decision information indicates that the intersection is passing and there is no preceding vehicle, a cruise mode is executed by a longitudinal planner, and a control instruction is generated based on the cruise mode to control the passing of the vehicle; If the intersection passing decision information indicates that the intersection is passing and there is a preceding vehicle, a following vehicle mode is executed by a longitudinal planner, and a control instruction is generated based on the following vehicle mode to control the passing of the self-vehicle; If the intersection traffic decision information indicates intersection braking, the longitudinal planner executes the driving mode, and generates a control instruction based on the driving mode to control the braking of the vehicle.

8. A road crossing device, characterized in that: The device comprises: An information acquisition module is used to obtain the status information of the target vehicle, the status information of the VRU, and the environmental information of the intersection; An intersection type determination module, used to determine the intersection type of the intersection according to the environmental information; A decision generation module, for generating intersection traffic decision information by predicting and deducing based on the intersection type, the state information of the vehicle, the state information of the target vehicle, the state information of the VRU and the environmental information; The longitudinal control module is used to generate control instructions to control the vehicle to pass or brake based on the intersection traffic decision information through a longitudinal planner.

9. A road crossing device, characterized in that: The device comprises: a memory, a processor, and an intersection passing program stored in the memory and executable on the processor, wherein the intersection passing program is configured to implement the steps of the intersection passing method according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium stores an intersection passing program, and when the intersection passing program is executed by the processor, the steps of the intersection passing method according to any one of claims 1 to 7 are implemented.

Images