Steering process collision avoidance method and system based on speed compensation

Abstract

The invention discloses a steering process collision avoidance method and system based on speed compensation, and the method comprises the steps: carrying out the filtering and compensation of collected environment information and vehicle information in the steering process of a vehicle; state judgment and scene screening are carried out on the environment information and the vehicle information after filtering and compensation processing, and system state information and potential collision risk scene information are output; and performing risk judgment according to the system state information and the potential collision risk scene information, generating a risk assessment result and judging whether an emergency braking action is triggered or not. According to the method, the problem of inaccurate speed of the target object in a large steering scene is solved, and the false triggering probability of emergency braking is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of vehicle control, and in particular relates to a steering process collision avoidance method and system based on speed compensation. Background Art

[0002] Generally, when a dangerous obstacle such as a major moving object (e.g., a movable device such as a vehicle) or an external object (e.g., a moving person such as a pedestrian or a fixed device such as a precast paver, a guardrail, and a curb) is detected in a front area of ​​the vehicle during vehicle travel, an autonomous emergency braking (AEB) system can use the detected dangerous obstacle detection information to determine that the front obstacle is a control object, and warn the driver that there is a dangerous situation with a high probability of collision when the probability of collision with the dangerous obstacle is high. If necessary, the AEB system performs autonomous emergency braking to prevent the vehicle from colliding with any obstacle. AEB application fields have recently increased and been standardized, so that many developers and companies are focusing on researching advanced and evolved AEB systems that can expand usage and utility in a manner that the advanced AEB systems can operate in more situations than conventional AEB systems, and ensure higher safety and stability than conventional AEB systems in a manner that the advanced AEB systems can prevent the vehicle from colliding with any obstacle.

[0003] Specifically, the conventional AEB system may use a fusion of front sensors designed to detect whether there is a peripheral vehicle in the longitudinal area ahead of the host vehicle to identify whether there is a peripheral vehicle, and may determine the movement of the identified peripheral vehicle (i.e., the front vehicle), so that the conventional AEB system may centrally control the detected front vehicle. However, as the AEB system has been expanded to more applications, an advanced safety system has recently been developed and established in accordance with the law, which may warn the vehicle driver of an approaching vehicle moving in a horizontal direction at an intersection or a pedestrian running in a horizontal direction at an intersection, or may perform autonomous emergency braking, thereby obtaining vehicle safety and stability and greater user convenience.

[0004] At present, the relevant JA (intersection assistance) system requires the support of corner radars during product development and later maintenance. It is generally equipped on L3 advanced vehicles equipped with advanced driving assistance functions. It is generally equipped with 4 in a group and arranged around the vehicle; taking a well-known international supplier as an example, the development and product cost of corner radar products supporting advanced driving assistance systems (ADAS, Advanced Driving Assistant System) is basically 400-600 yuan each, requiring about 2,000 yuan in costs and R&D sharing. Although the popularity of ADAS systems in intelligent networking is increasing, according to the authoritative data of the China Automobile Consumers Association, the sales volume of vehicles equipped with 4 corner radars is less than 0.5%, and it is expected that the sales volume will account for less than 5% after 2020. However, due to the requirements of CNCAP, the cost of products equipped with forward millimeter-wave radars and cameras has become mainstream, and the equipment rate is also reaching a new high. Taking a model of a mainstream OEM with monthly sales of more than 30,000 as an example, all its second-level and above models are equipped with forward millimeter-wave radars, and the ADAS equipment coverage rate is relatively high.

[0005] The existing intersection assistance uses corner radar to judge the approaching car on the curve. The disadvantage is that it must be supported by corner radar, and the equipment rate of corner radar is not high and the development cost is high, which makes it difficult to popularize it. At present, the AEB (Autonomous Emergency Braking) system related to the millimeter-wave radar considers the former goal during product development and testing, and has a narrow field of view. However, due to its own limitations, it cannot realize the intersection assistance function. Summary of the invention

[0006] The purpose of the present invention is to provide a collision avoidance method and system in a steering process based on speed compensation, which solves the problem of inaccurate target speed in large turning scenarios and reduces the probability of false triggering of emergency braking.

[0007] In order to solve the above technical problems, the technical solution of the present invention is: a collision avoidance method in a steering process based on speed compensation, comprising:

[0008] During the steering process of the vehicle, the collected environmental information and vehicle information are filtered and compensated;

[0009] Perform status judgment and scene screening on the filtered and compensated environmental information and vehicle information, and output system status information and potential collision risk scene information;

[0010] Make risk judgments based on system status information and potential collision risk scenario information, generate risk assessment results and determine whether to trigger emergency braking action.

[0011] The specific steps for compensating vehicle information are as follows:

[0012] Establish a vehicle coordinate system xy, with the camera set on the vehicle as the origin of the vehicle coordinate system, the positive direction of the vehicle as the positive direction of the x-axis of the vehicle coordinate system, and the direction perpendicular to the x-axis pointing to the left side of the vehicle as the positive direction of the y-axis of the vehicle coordinate system;

[0013] The other vehicles that enter the vehicle coordinate system during the steering process of the ego vehicle are set as targets;

[0014] The lateral / longitudinal velocity of the target object after rotation compensation in the vehicle coordinate system is equal to the lateral / longitudinal relative velocity output by the vehicle sensor plus the lateral / longitudinal velocity after rotation compensation, expressed as:

[0015]

[0016] Where Vx represents the longitudinal relative speed of the target object output by the camera; Vy represents the lateral relative speed of the target object output by the camera; Vx rel Vy is the longitudinal relative velocity of rotation compensation; rel Vx is the lateral relative speed of rotation compensation; deal Vy is the longitudinal velocity of the target after rotation compensation; deal is the lateral velocity of the target after rotation compensation;

[0017] When the ego vehicle rotates, the target object has an angular velocity -W in the opposite direction relative to the ego vehicle. The speed of the target object relative to the ego vehicle caused by the rotation of the ego vehicle is expressed as:

[0018] V rel =-W×R(2)

[0019] Where V rel is the speed of the target vehicle for rotation compensation; W is the yaw rate of the vehicle; R is the turning radius of the target vehicle;

[0020] From the geometric relationship we get:

[0021]

[0022] Where θ is the angle between the velocity Vrel and the x-axis of the vehicle coordinate system; r is the turning radius of the vehicle; lon represents the longitudinal distance between the target object and the vehicle; lat represents the lateral distance between the target object and the vehicle;

[0023] The longitudinal and lateral speeds of the target vehicle relative to the ego vehicle due to rotation are expressed as:

[0024]

[0025] Substituting formulas (2), (3), and (4) into formula (1), the lateral / longitudinal velocity of the target object in the vehicle coordinate system after rotation compensation is expressed as:

[0026]

[0027] Where V is the speed of the vehicle relative to the ground.

[0028] The method for risk judgment based on system status information and potential collision risk scenario information is specifically as follows: simplifying the nonlinear steering motion of the ego vehicle into a linear problem of lateral and longitudinal decoupling, establishing lateral and longitudinal linear collision formulas, introducing the data characteristics of the ego vehicle's steering motion, setting the minimum lateral collision time threshold LatTTC_Min and the minimum longitudinal collision time threshold LonTTC_Min to filter the false triggering caused by the sudden change of data, and determining the maximum lateral collision time threshold LatTTC_Max, the minimum lateral collision time threshold LatTTC_Min, the maximum longitudinal collision time threshold LonTTC_Max, and the minimum longitudinal collision time threshold LonTTC_Min in combination with the actual vehicle data characteristics in the system status information; when LatTTC_Min≤LatTTC≤LatTTC_Max and / or LonTTC_Min≤LonTTC≤LonTTC_Max, it indicates a collision risk; wherein LatTTC is the lateral collision time of the ego vehicle, and LonTTC is the longitudinal collision time of the ego vehicle.

[0029] The data characteristics of the vehicle's steering motion are introduced into the lateral and longitudinal linear collision formulas, which are specifically expressed as follows:

[0030] Assuming that the vehicle moves at a uniform speed in a straight line at the current speed, if it collides with the target object, the longitudinal collision time should be equal to the lateral collision time, then:

[0031]

[0032] Where, LonTTC represents the calculated value of longitudinal collision time; LatTTC represents the calculated value of lateral collision time;

[0033] Introducing the steering process of the vehicle after rotation compensation, substituting the rotation-compensated formula (5) into formula (6) yields:

[0034]

[0035] In the calculation of collision time, Vy≈0 can be ignored. Assuming that the vehicle turns left, then Lon>0, lat>0, W>0, Vx deal <0, Vy deal <0, so from formula (7) we get:

[0036]

[0037] make By constructing the relationship between the longitudinal collision time and the lateral collision time, formula (8) can be simplified to:

[0038]

[0039] When k is much smaller than -1, c is much larger than 1, and LocTTC = LatTTC, formula (9) has two unequal positive solutions T1 and T2, that is, there exists an interval LatTTC∈(0,T1) such that LonTTC>LatTTC. Therefore, it can be concluded that within the range approaching zero, the longitudinal collision time is not equal to the lateral collision time, and the longitudinal collision time is greater.

[0040] The environmental information includes at least lane information, target information and sign information; the vehicle information includes at least vehicle chassis information, body information, vehicle speed, yaw angular velocity and steering wheel angle.

[0041] The present invention also provides a steering process collision avoidance system based on speed compensation, comprising a calibration observation management module, a perception information processing module, a state machine management module, a scene screening module, a risk judgment module and a braking output module; wherein,

[0042] The calibration observation management module is used to send the vehicle configuration information to other modules. The vehicle configuration information at least includes the vehicle model configuration word, the vehicle wheelbase, and the camera installation position;

[0043] A perception information processing module, used for filtering and compensating environmental information and vehicle information, and outputting the filtered and compensated vehicle information to the state machine management module and the brake output module, and outputting the filtered and compensated environmental information to the scene screening module and the brake output module;

[0044] The state machine management module is used to judge the state of the vehicle information after filtering and compensation, and output the system state information to the risk judgment module and the brake output module;

[0045] A scene screening module is used to screen the environmental information after filtering and compensation, and output the potential collision risk scene information to the risk judgment module;

[0046] A risk judgment module is used to make risk judgments based on system status information and potential collision risk scenario information, generate risk assessment results and send them to the brake output module;

[0047] The braking output module is used to generate corresponding braking instructions according to the risk assessment results and brake according to the braking instructions.

[0048] The specific steps for compensating vehicle information are as follows:

[0049] Establish a vehicle coordinate system xy, with the camera set on the vehicle as the origin of the vehicle coordinate system, the positive direction of the vehicle as the positive direction of the x-axis of the vehicle coordinate system, and the direction perpendicular to the x-axis pointing to the left side of the vehicle as the positive direction of the y-axis of the vehicle coordinate system;

[0050] The other vehicles that enter the vehicle coordinate system during the steering process of the ego vehicle are set as targets;

[0051] The lateral / longitudinal velocity of the target object after rotation compensation in the vehicle coordinate system is equal to the lateral / longitudinal relative velocity output by the vehicle sensor plus the lateral / longitudinal velocity after rotation compensation, expressed as:

[0052]

[0053] Where Vx represents the longitudinal relative speed of the target object output by the camera; Vy represents the lateral relative speed of the target object output by the camera; Vx rel Vy is the longitudinal relative velocity of rotation compensation; rel Vx is the lateral relative speed of rotation compensation; deal Vy is the longitudinal velocity of the target after rotation compensation; deal is the lateral velocity of the target after rotation compensation;

[0054] When the ego vehicle rotates, the target object has an angular velocity -W in the opposite direction relative to the ego vehicle. The speed of the target object relative to the ego vehicle caused by the rotation of the ego vehicle is expressed as:

[0055] V rel =-W×R(2)

[0056] In the formula, Vrel is the speed of the target vehicle for rotation compensation; W is the yaw rate of the vehicle; R is the turning radius of the target vehicle;

[0057] From the geometric relationship we get:

[0058]

[0059] Where θ is the angle between the velocity Vrel and the x-axis of the vehicle coordinate system; r is the turning radius of the vehicle; lon represents the longitudinal distance between the target object and the vehicle; lat represents the lateral distance between the target object and the vehicle;

[0060] The longitudinal and lateral speeds of the target vehicle relative to the ego vehicle due to rotation are expressed as:

[0061]

[0062] Substituting formulas (2), (3), and (4) into formula (1), the lateral / longitudinal velocity of the target object in the vehicle coordinate system after rotation compensation is expressed as:

[0063]

[0064] Where V is the speed of the vehicle relative to the ground.

[0065] The method for risk judgment based on system status information and potential collision risk scenario information is specifically as follows: simplifying the nonlinear steering motion of the ego vehicle into a linear problem of lateral and longitudinal decoupling, establishing lateral and longitudinal linear collision formulas, introducing the data characteristics of the ego vehicle's steering motion, setting the minimum lateral collision time threshold LatTTC_Min and the minimum longitudinal collision time threshold LonTTC_Min to filter the false triggering caused by the sudden change of data, and determining the maximum lateral collision time threshold LatTTC_Max, the minimum lateral collision time threshold LatTTC_Min, the maximum longitudinal collision time threshold LonTTC_Max, and the minimum longitudinal collision time threshold LonTTC_Min in combination with the actual vehicle data characteristics in the system status information; when LatTTC_Min≤LatTTC≤LatTTC_Max and / or LonTTC_Min≤LonTTC≤LonTTC_Max, it indicates a collision risk; wherein LatTTC is the lateral collision time of the ego vehicle, and LonTTC is the longitudinal collision time of the ego vehicle.

[0066] The data characteristics of the vehicle's steering motion are introduced into the lateral and longitudinal linear collision formulas, which are specifically expressed as follows:

[0067] Assuming that the vehicle moves at a uniform speed in a straight line at the current speed, if it collides with the target object, the longitudinal collision time should be equal to the lateral collision time, then:

[0068]

[0069] Where, LonTTC represents the calculated value of longitudinal collision time; LatTTC represents the calculated value of lateral collision time;

[0070] Introducing the steering process of the vehicle after rotation compensation, substituting the rotation-compensated formula (5) into formula (6) yields:

[0071]

[0072] In the calculation of collision time, Vy≈0 can be ignored. Assuming that the vehicle turns left, then lon>0, lat>0, W>0, Vx dea l<0,Vy deal <0, so from formula (7) we get:

[0073]

[0074] make By constructing the relationship between the longitudinal collision time and the lateral collision time, formula (8) can be simplified to:

[0075]

[0076] When k is much smaller than -1, c is much larger than 1, and LonTTC = LatTTC, formula (9) has two unequal positive solutions T1 and T2, that is, there exists an interval LattTTC∈(0,T1) such that LonTTC>LatTTC. Therefore, it can be concluded that within the range approaching zero, the longitudinal collision time is not equal to the lateral collision time, and the longitudinal collision time is greater.

[0077] The camera is set at the center of the front of the vehicle.

[0078] Compared with the prior art, the present invention has the following beneficial effects:

[0079] The present invention uses a perception information processing module to perform rotation compensation on the relative speed of the target object detected by the vehicle sensor relative to the vehicle, thereby solving the problem of inaccurate target object speed in large turning scenarios; the present invention uses a risk judgment module to decouple the lateral and longitudinal risks, and selects appropriate TTC maximum and minimum thresholds, thereby simplifying the algorithm, reducing the number of calculation examples, and reducing the probability of false triggering of emergency braking. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] Figure 1 A schematic diagram of a flow chart of an embodiment of the present invention;

[0081] Figure 2 is a functional architecture diagram of an embodiment of the present invention;

[0082] Figure 3 is a schematic diagram of rotation compensation in an embodiment of the present invention;

[0083] Figure 4 Schematic diagram of the principle of risk judgment in an embodiment of the present invention. DETAILED DESCRIPTION

[0084] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0085] The technical solution of the present invention is:

[0086] Embodiment 1:

[0087] A collision avoidance method for steering process based on speed compensation, such as Figure 1 As shown, including:

[0088] S1. During the steering process of the vehicle, the collected environmental information and vehicle information are filtered and compensated;

[0089] S2, performing status judgment and scene screening on the filtered and compensated environmental information and vehicle information, and outputting system status information and potential collision risk scene information;

[0090] S3. Perform risk assessment based on system status information and potential collision risk scenario information, generate risk assessment results and determine whether to trigger emergency braking action.

[0091] The specific steps for compensating vehicle information are as follows:

[0092] Establish a vehicle coordinate system xy, with the camera set on the vehicle as the origin of the vehicle coordinate system, the positive direction of the vehicle as the positive direction of the x-axis of the vehicle coordinate system, and the direction perpendicular to the x-axis pointing to the left side of the vehicle as the positive direction of the y-axis of the vehicle coordinate system;

[0093] The other vehicles that enter the vehicle coordinate system during the steering process are set as targets;

[0094] The lateral / longitudinal velocity of the target object after rotation compensation in the vehicle coordinate system is equal to the lateral / longitudinal relative velocity output by the vehicle sensor plus the lateral / longitudinal velocity after rotation compensation, expressed as:

[0095]

[0096] Where Vx represents the longitudinal relative speed of the target object output by the camera; Vy represents the lateral relative speed of the target object output by the camera; Vx rel Vy is the longitudinal relative velocity of rotation compensation; rel Vx is the lateral relative speed of rotation compensation; deal Vy is the longitudinal velocity of the target after rotation compensation; deal is the lateral velocity of the target after rotation compensation;

[0097] When the ego vehicle rotates, the target object has an angular velocity -W in the opposite direction relative to the ego vehicle. The speed of the target object relative to the ego vehicle caused by the rotation of the ego vehicle is expressed as:

[0098] V rel =-W×R(2)

[0099] Where V rel is the speed of the target vehicle for rotation compensation; W is the yaw rate of the vehicle; R is the turning radius of the target vehicle;

[0100] From the geometric relationship we get:

[0101]

[0102] Where θ is the angle between the velocity Vrel and the x-axis of the vehicle coordinate system; r is the turning radius of the vehicle; lon represents the longitudinal distance between the target object and the vehicle; lat represents the lateral distance between the target object and the vehicle;

[0103] The longitudinal and lateral speeds of the target vehicle relative to the ego vehicle due to rotation are expressed as:

[0104]

[0105] Substituting formulas (2), (3), and (4) into formula (1), the lateral / longitudinal velocity of the target object in the vehicle coordinate system after rotation compensation is expressed as:

[0106]

[0107] Where V is the speed of the vehicle relative to the ground.

[0108] like Figure 4 As shown, the method for risk judgment based on system status information and potential collision risk scenario information is specifically as follows: simplifying the nonlinear steering motion of the ego vehicle into a linear problem of lateral and longitudinal decoupling, establishing lateral and longitudinal linear collision formulas, introducing the data characteristics of the ego vehicle steering motion, setting the minimum lateral collision time threshold LatTTC_Min and the minimum longitudinal collision time threshold LonTTC_Min to filter the false triggering caused by the sudden change of data, and determining the maximum lateral collision time threshold LatTTC_max, the minimum lateral collision time threshold LatTTC_Min, the maximum longitudinal collision time threshold LonTTC_Max, and the minimum longitudinal collision time threshold LonTTC_Min in combination with the actual vehicle data characteristics in the system status information. When LatTTC_Min≤LatTTC≤LatTTC_Max and / or LonTTC_Min≤LonTTC≤LonTTC_Max, it indicates that there is a collision risk; wherein LatTTC is the lateral collision time of the ego vehicle, and LonTTC is the longitudinal collision time of the ego vehicle.

[0109] The data characteristics of the vehicle's steering motion are introduced into the lateral and longitudinal linear collision formulas, which are specifically expressed as follows:

[0110] Assuming that the vehicle moves at a uniform speed in a straight line at the current speed, if it collides with the target object, the longitudinal collision time should be equal to the lateral collision time, then:

[0111]

[0112] Where, LonTTC represents the calculated value of longitudinal collision time; LatTTC represents the calculated value of lateral collision time;

[0113] Introducing the steering process of the vehicle after rotation compensation, substituting the rotation-compensated formula (5) into formula (6) yields:

[0114]

[0115] In the calculation of collision time, Vy≈0 can be ignored. Assuming that the vehicle turns left, then lon>0, lat>0, W>0, Vx deal <0, Vy deal <0, so from formula (7) we get:

[0116]

[0117] make By constructing the relationship between the longitudinal collision time and the lateral collision time, formula (8) can be simplified to:

[0118]

[0119] When k is much smaller than -1, c is much larger than 1, and LonTTC = latTTC, formula (9) has two unequal positive solutions T1 and T2, that is, there exists an interval LatTTC∈(0,T1) such that LonTTC>LatTTC. Therefore, it can be concluded that within the range approaching zero, the longitudinal collision time is not equal to the lateral collision time, and the longitudinal collision time is greater.

[0120] The environmental information includes at least lane information, target information and sign information; the vehicle information includes at least vehicle chassis information, body information, vehicle speed, yaw angular velocity and steering wheel angle.

[0121] The above embodiments may be stored in a computer-readable storage medium, which stores executable instructions. When the instructions are executed by a processor, the processor implements the method described in the above embodiments.

[0122] Embodiment 2:

[0123] A collision avoidance system during steering process based on speed compensation, such as Figure 2 As shown, it includes a calibration observation management module, a perception information processing module, a state machine management module, a scene screening module, a risk judgment module and a braking output module; wherein,

[0124] The calibration observation management module is used to send vehicle configuration information to other modules. The vehicle configuration information at least includes the vehicle model configuration word, the vehicle wheelbase, and the camera installation position. This module is used to define the variables that need to be set as adjustable as calibration quantities, and define the internal variables that need to be observed in real time as observation quantities. It can be applied to various parts of the software module to realize the real-time adjustment and observability of internal variables. This module is an important way to debug the actual vehicle.

[0125] The perception information processing module is used to filter and compensate the environmental information and vehicle information, and output the filtered and compensated vehicle information to the state machine management module and the brake output module, as well as output the filtered and compensated environmental information to the scene screening module and the brake output module; the sensor data is post-processed such as filtering, denoising, and calibration to ensure the accuracy and stability of the perception information, including secondary modules such as data filtering and rotation compensation. The rotation compensation module is specifically introduced: it mainly compensates for the lateral and longitudinal relative speeds of the target object detected by the sensor when the vehicle turns. Many sensor suppliers have errors in the detection of the lateral and longitudinal speeds of the target object when the vehicle turns, and do not consider the influence of the inertial coordinate system to the non-inertial coordinate system when the vehicle rotates. Therefore, the relative speed of the target object is added with the speed compensation caused by the rotation of the vehicle, such as Figure 3 shown.

[0126] The state machine management module is used to judge the state of the vehicle information after filtering and compensation, and output the system state information to the risk judgment module and the brake output module; through the vehicle's own sensor, including vehicle speed, yaw angular velocity, steering wheel angle and other vehicle state related signals, it classifies and judges the state that will cause the function to enter a fault, enter a prohibited state or enter a normal enabled state, and reserves expandable states such as the suppression state and the initialization state. This module outputs the system state signal state and the function enable signal enable as the state drive signal for subsequent brake judgment.

[0127] The scene screening module is used to screen the environmental information after filtering and compensation, and output the potential collision risk scene information to the risk judgment module; analyze the road vehicle information and other information output by the perception information processing module, determine whether it is currently near an intersection, and determine to enter the scene screening stage, and then screen out potential collision risk scenes based on the relationship between the vehicle position speed and the road obstacle structure, including secondary modules such as intersection screening and target object screening.

[0128] The risk judgment module is used to make risk judgments based on system status information and potential collision risk scenario information, generate risk assessment results and send them to the braking output module; based on the screened scenarios, the collision risk is assessed using pre-set rules or machine learning algorithms, and then based on the risk assessment results, it is determined whether emergency braking action needs to be triggered, including secondary modules such as lateral risk judgment, longitudinal risk judgment, and comprehensive risk judgment.

[0129] The braking output module is used to generate corresponding braking instructions according to the risk assessment results and brake according to the braking instructions. Based on the results of risk judgment, the corresponding braking instructions are generated, including the braking force and braking duration. During the braking process, adjustments are made according to real-time perception information to ensure the stability and safety of the braking operation, including secondary modules such as deceleration setting and state jump.

[0130] The specific steps for compensating vehicle information are as follows:

[0131] Establish a vehicle coordinate system xy, with the camera set on the vehicle as the origin of the vehicle coordinate system, the positive direction of the vehicle as the positive direction of the x-axis of the vehicle coordinate system, and the direction perpendicular to the x-axis pointing to the left side of the vehicle as the positive direction of the y-axis of the vehicle coordinate system;

[0132] The other vehicles that enter the vehicle coordinate system during the steering process of the ego vehicle are set as targets;

[0133] The lateral / longitudinal velocity of the target object after rotation compensation in the vehicle coordinate system is equal to the lateral / longitudinal relative velocity output by the vehicle sensor plus the lateral / longitudinal velocity after rotation compensation, expressed as:

[0134]

[0135] Where Vx represents the longitudinal relative speed of the target object output by the camera, in meters per second (m / s); Vy represents the lateral relative speed of the target object output by the camera, in meters per second (m / s); Vx rel Vy is the longitudinal relative speed of rotation compensation, in meters per second (m / s); rel is the lateral relative speed of the rotation compensation, in meters per second (m / s); Vxdeal is the longitudinal speed of the target object after compensation, in meters per second (m / s); Vydeal is the lateral speed of the target object after compensation, in meters per second (m / s).

[0136] When the ego vehicle rotates, the target object has an angular velocity -W in the opposite direction relative to the ego vehicle. The speed of the target object relative to the ego vehicle caused by the rotation of the ego vehicle is expressed as:

[0137] V rel =-W×R(2)

[0138] Where V relis the speed of the target vehicle for rotation compensation, in meters per second (m / s); W is the yaw rate of the vehicle, in radians per second (rad / s); R is the turning radius of the target vehicle, in meters (m);

[0139] From the geometric relationship we get:

[0140]

[0141] Wherein, θ is the angle between the velocity Vrel and the horizontal axis of the vehicle, in radians; r is the turning radius of the vehicle, in meters; lon is the longitudinal distance between the target object and the vehicle, in meters; lat is the lateral distance between the target object and the vehicle, in meters;

[0142] The longitudinal and lateral speeds of the target vehicle relative to the ego vehicle due to rotation are expressed as:

[0143]

[0144] Substituting formulas (2), (3), and (4) into formula (1), the lateral / longitudinal velocity of the target object in the vehicle coordinate system after rotation compensation is expressed as:

[0145]

[0146] Where V is the speed of the vehicle relative to the earth, in meters per second (m / s).

[0147] The method for risk judgment based on system status information and potential collision risk scenario information is specifically as follows: simplifying the nonlinear steering motion of the ego vehicle into a linear problem of lateral and longitudinal decoupling, establishing lateral and longitudinal linear collision formulas, introducing the data characteristics of the ego vehicle's steering motion, setting the minimum lateral collision time threshold LatTTC_Min and the minimum longitudinal collision time threshold LonTTC_Min to filter the false triggering caused by the sudden change of data, and determining the maximum lateral collision time threshold LatTTC_Max, the minimum lateral collision time threshold LatTTC_Min, the maximum longitudinal collision time threshold LonTTC_Max, and the minimum longitudinal collision time threshold LonTTC_Min in combination with the actual vehicle data characteristics in the system status information; when LatTTC_Min≤LatTTC≤LonTTC_Max and / or lonTTC_Min≤LonTTC≤LonTTC_Max, it indicates a collision risk; wherein latTTC is the lateral collision time of the ego vehicle, and LonTTC is the longitudinal collision time of the ego vehicle.

[0148] The data characteristics of the vehicle's steering motion are introduced into the lateral and longitudinal linear collision formulas, which are specifically expressed as follows:

[0149] Assuming that the vehicle moves at a uniform speed in a straight line at the current speed, if it collides with the target object, the longitudinal collision time should be equal to the lateral collision time, then:

[0150]

[0151] Where, LonTTC represents the calculated value of longitudinal collision time; LatTTC represents the calculated value of lateral collision time;

[0152] Introducing the steering process of the vehicle after rotation compensation, substituting the rotation-compensated formula (5) into formula (6) yields:

[0153]

[0154] In the calculation of collision time, Vy≈0 can be ignored. Assuming that the vehicle turns left, then lon>0, lat>0, W>0, Vx deal <0, Vy deal <0, so from formula (7) we get:

[0155]

[0156] make By constructing the relationship between the longitudinal collision time and the lateral collision time, formula (8) can be simplified to:

[0157]

[0158] When k is much smaller than -1, c is much larger than 1, and LonTTC = LatTTC, formula (9) has two unequal positive solutions T1 and T2, that is, there exists an interval LatTTC∈(0,T1) such that LonTTC>LatTTC. Therefore, it can be concluded that within the range approaching zero, the longitudinal collision time is not equal to the lateral collision time, and the longitudinal collision time is greater.

[0159] The time trigger thresholds for lateral and longitudinal collisions are preliminarily located through simulation, and finally determined by combining the data characteristics of the actual vehicle.

[0160] In this embodiment, the camera is set at the center of the front of the vehicle. Figure 3 shown.

[0161] Figure 3 Explanation of symbols:

[0162] a) xy represents the vehicle coordinate system, with the camera as the origin, the vehicle's longitudinal axis forward as the positive direction of the x-axis, and the vertical x-axis pointing to the left side of the vehicle as the positive direction of the y-axis;

[0163] b) lon represents the longitudinal distance of the target object in the vehicle coordinate system; lat represents the lateral distance of the target object in the vehicle coordinate system;

[0164] c) V is the speed of the vehicle relative to the ground, W is the yaw rate of the vehicle, and r is the turning radius of the vehicle;

[0165] d) Vx is the longitudinal relative speed of the target object in the vehicle coordinate system output by the sensor, and Vy is the lateral relative speed of the target object in the vehicle coordinate system output by the sensor;

[0166] e) R is the turning radius of the target vehicle relative to the ego vehicle;

[0167] f) Vrel is the speed of rotation compensation, Vxrel is the longitudinal speed of rotation compensation, Vyrel is the lateral speed of rotation compensation, and θ is the angle between the speed Vrel and the lateral axis of the vehicle;

[0168] g) Vxdeal is the longitudinal velocity of the target object in the vehicle coordinate system after compensation, and Vydeal is the lateral velocity of the target object in the vehicle coordinate system after compensation.

[0169] Embodiment 3:

[0170] The present invention also provides an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; a computer program is stored in the memory, and when the program is executed by the processor, the processor executes the steps of a steering process collision avoidance method based on speed compensation.

[0171] Embodiment 4:

[0172] The present invention also provides a computer-readable storage medium on which executable instructions are stored. When the instructions are executed by a processor, the processor implements the steering process collision avoidance method based on speed compensation.

[0173] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0174] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0175] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0177] It will be easily understood by those skilled in the art that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A collision avoidance method in a steering process based on speed compensation, characterized in that: include: During the steering process of the vehicle, the collected environmental information and vehicle information are filtered and compensated; Perform status judgment and scene screening on the filtered and compensated environmental information and vehicle information, and output system status information and potential collision risk scene information; Make risk judgments based on system status information and potential collision risk scenario information, generate risk assessment results and determine whether to trigger emergency braking action.

2. The method for avoiding collision during steering process based on speed compensation according to claim 1, characterized in that: The specific steps for compensating vehicle information are as follows: Establish a vehicle coordinate system xy, with the camera set on the vehicle as the origin of the vehicle coordinate system, the positive direction of the vehicle as the positive direction of the x-axis of the vehicle coordinate system, and the direction perpendicular to the x-axis pointing to the left side of the vehicle as the positive direction of the y-axis of the vehicle coordinate system; The other vehicles that enter the vehicle coordinate system during the steering process of the ego vehicle are set as targets; The lateral / longitudinal velocity of the target object after rotation compensation in the vehicle coordinate system is equal to the lateral / longitudinal relative velocity output by the vehicle sensor plus the lateral / longitudinal velocity after rotation compensation, expressed as: Where Vx represents the longitudinal relative speed of the target object output by the camera; Vy represents the lateral relative speed of the target object output by the camera; Vx rel Vy is the longitudinal relative velocity of rotation compensation; rel Vx is the lateral relative speed of rotation compensation; deal Vy is the longitudinal velocity of the target after rotation compensation; deal is the lateral velocity of the target after rotation compensation; When the ego vehicle rotates, the target object has an angular velocity -W in the opposite direction relative to the ego vehicle. The speed of the target object relative to the ego vehicle caused by the rotation of the ego vehicle is expressed as: In rel =-W×R(2) Where V rel is the speed of the target vehicle for rotation compensation; W is the yaw rate of the vehicle; R is the turning radius of the target vehicle; From the geometric relationship we get: Where θ is the angle between the velocity Vrel and the x-axis of the vehicle coordinate system; r is the turning radius of the vehicle; lon represents the longitudinal distance between the target object and the vehicle; lat represents the lateral distance between the target object and the vehicle; The longitudinal and lateral speeds of the target vehicle relative to the ego vehicle due to rotation are expressed as: Substituting formulas (2), (3), and (4) into formula (1), the lateral / longitudinal velocity of the target object in the vehicle coordinate system after rotation compensation is expressed as: Where V is the speed of the vehicle relative to the ground.

3. The method for avoiding collision during steering process based on speed compensation according to claim 2, characterized in that: The method for risk judgment based on system status information and potential collision risk scenario information is specifically as follows: simplifying the nonlinear steering motion of the ego vehicle into a linear problem of lateral and longitudinal decoupling, establishing lateral and longitudinal linear collision formulas, introducing the data characteristics of the ego vehicle's steering motion, setting the minimum lateral collision time threshold LatTTC_Min and the minimum longitudinal collision time threshold LonTTC_Min to filter the false triggering caused by the sudden change of data, and determining the maximum lateral collision time threshold LatTTC_Max, the minimum lateral collision time threshold LatTTC_Min, the maximum longitudinal collision time threshold LonTTC_Max, and the minimum longitudinal collision time threshold LonTTC_Min in combination with the actual vehicle data characteristics in the system status information; when LatTTC_Min≤LatTTC≤LatTTC_Max and / or LonTTC_Min≤LonTTC≤LonTTC_Max, it indicates a collision risk; wherein LatTTC is the lateral collision time of the ego vehicle, and LonTTC is the longitudinal collision time of the ego vehicle.

4. The method for avoiding collision during steering process based on speed compensation according to claim 3, characterized in that: The data characteristics of the vehicle's steering motion are introduced into the lateral and longitudinal linear collision formulas, which are specifically expressed as follows: Assuming that the vehicle moves at a uniform speed in a straight line at the current speed, if it collides with the target object, the longitudinal collision time should be equal to the lateral collision time, then: Where, LonTTC represents the calculated value of longitudinal collision time; LatTTC represents the calculated value of lateral collision time; Introducing the steering process of the vehicle after rotation compensation, substituting the rotation-compensated formula (5) into formula (6) yields: In the calculation of collision time, Vy≈0 can be ignored. Assuming that the vehicle turns left, then lon>0, lat>0, W>0, Vx deal <0, Vy deal <0, so from formula (7) we get: make By constructing the relationship between the longitudinal collision time and the lateral collision time, formula (8) can be simplified to: When k is much smaller than -1, c is much larger than 1, and LonTTC=LatTTC, formula (9) has two unequal positive solutions T1 and T2, that is, there exists an interval LatTTC∈(0, T1) such that LonTTC>LatTTC. Therefore, it can be concluded that within the range approaching zero, the longitudinal collision time is not equal to the lateral collision time, and the longitudinal collision time is greater.

5. The method for avoiding collision during steering process based on speed compensation according to claim 2, characterized in that: The environmental information includes at least lane information, target information and sign information; the vehicle information includes at least vehicle chassis information, body information, vehicle speed, yaw angular velocity and steering wheel angle.

6. A collision avoidance system during steering process based on speed compensation, characterized in that: It includes calibration observation management module, perception information processing module, state machine management module, scenario screening module, risk judgment module and braking output module; in, The calibration observation management module is used to send the vehicle configuration information to other modules. The vehicle configuration information at least includes the vehicle model configuration word, the vehicle wheelbase, and the camera installation position; A perception information processing module, used for filtering and compensating environmental information and vehicle information, and outputting the filtered and compensated vehicle information to the state machine management module and the brake output module, and outputting the filtered and compensated environmental information to the scene screening module and the brake output module; The state machine management module is used to judge the state of the vehicle information after filtering and compensation, and output the system state information to the risk judgment module and the brake output module; A scene screening module is used to screen the environmental information after filtering and compensation, and output the potential collision risk scene information to the risk judgment module; A risk judgment module is used to make risk judgments based on system status information and potential collision risk scenario information, generate risk assessment results and send them to the brake output module; The braking output module is used to generate corresponding braking instructions according to the risk assessment results and brake according to the braking instructions.

7. The speed-compensated steering process collision avoidance system according to claim 6, characterized in that: The specific steps for compensating vehicle information are as follows: Establish a vehicle coordinate system xy, with the camera set on the vehicle as the origin of the vehicle coordinate system, the positive direction of the vehicle as the positive direction of the x-axis of the vehicle coordinate system, and the direction perpendicular to the x-axis pointing to the left side of the vehicle as the positive direction of the y-axis of the vehicle coordinate system; The other vehicles that enter the vehicle coordinate system during the steering process of the ego vehicle are set as targets; The lateral / longitudinal velocity of the target object after rotation compensation in the vehicle coordinate system is equal to the lateral / longitudinal relative velocity output by the vehicle sensor plus the lateral / longitudinal velocity after rotation compensation, expressed as: Where Vx represents the longitudinal relative speed of the target object output by the camera; Vy represents the lateral relative speed of the target object output by the camera; Vx rel Vy is the longitudinal relative velocity of rotation compensation; rel Vx is the lateral relative speed of rotation compensation; deal Vy is the longitudinal velocity of the target after rotation compensation; deal is the lateral velocity of the target after rotation compensation; When the ego vehicle rotates, the target object has an angular velocity -W in the opposite direction relative to the ego vehicle. The speed of the target object relative to the ego vehicle caused by the rotation of the ego vehicle is expressed as: In rel =-W×R(2) Where V rel is the speed of the target vehicle for rotation compensation; W is the yaw rate of the vehicle; R is the turning radius of the target vehicle; From the geometric relationship we get: Where θ is the angle between the velocity Vrel and the x-axis of the vehicle coordinate system; r is the turning radius of the vehicle; lon represents the longitudinal distance between the target object and the vehicle; lat represents the lateral distance between the target object and the vehicle; The longitudinal and lateral speeds of the target vehicle relative to the ego vehicle due to rotation are expressed as: Substituting formulas (2), (3), and (4) into formula (1), the lateral / longitudinal velocity of the target object in the vehicle coordinate system after rotation compensation is expressed as: Where V is the speed of the vehicle relative to the ground.

8. The speed-compensated steering process collision avoidance system according to claim 7, characterized in that: The method for risk judgment based on system status information and potential collision risk scenario information is specifically as follows: simplifying the nonlinear steering motion of the ego vehicle into a linear problem of lateral and longitudinal decoupling, establishing lateral and longitudinal linear collision formulas, introducing the data characteristics of the ego vehicle's steering motion, setting the minimum lateral collision time threshold LatTTC_Min and the minimum longitudinal collision time threshold LonTTC_Min to filter the false triggering caused by the sudden change of data, and determining the maximum lateral collision time threshold LatTTC_Max, the minimum lateral collision time threshold LatTTC_Min, the maximum longitudinal collision time threshold LonTTC_Max, and the minimum longitudinal collision time threshold LonTTC_Min in combination with the actual vehicle data characteristics in the system status information; when LatTTC_Min≤LatTTC≤LatTTC_Max and / or LonTTC_Min≤LonTTC≤LonTTC_Max, it indicates a collision risk; wherein LatTTC is the lateral collision time of the ego vehicle, and LonTTC is the longitudinal collision time of the ego vehicle.

9. The speed-compensated steering process collision avoidance system according to claim 8, characterized in that: The data characteristics of the vehicle's steering motion are introduced into the lateral and longitudinal linear collision formulas, which are specifically expressed as follows: Assuming that the vehicle moves at a uniform speed in a straight line at the current speed, if it collides with the target object, the longitudinal collision time should be equal to the lateral collision time, then: Where, LonTTC represents the calculated value of longitudinal collision time; LatTTC represents the calculated value of lateral collision time; Introducing the steering process of the vehicle after rotation compensation, substituting the rotation-compensated formula (5) into formula (6) yields: In the calculation of collision time, Vy≈0 can be ignored. Assuming that the vehicle turns left, then lon>0, lat>0, W>0, Vx deal <0, Vy deal <0, so from formula (7) we get: make By constructing the relationship between the longitudinal collision time and the lateral collision time, formula (8) can be simplified to: When k is much smaller than -1, c is much larger than 1, and LonTTC=LatTTC, formula (9) has two unequal positive solutions T1 and T2, that is, there exists an interval LatTTC∈(0, T1) such that LonTTC>LatTTC. Therefore, it can be concluded that within the range approaching zero, the longitudinal collision time is not equal to the lateral collision time, and the longitudinal collision time is greater.

10. The speed-compensated steering process collision avoidance system according to claim 6, characterized in that: The camera is set at the center of the front of the vehicle.

Images