Collision detection method and device

Abstract

The invention discloses a collision detection method and device, and relates to the technical field of driving control. The method is applied to a first intelligent vehicle, and comprises the following steps: in response to the first intelligent vehicle starting to execute an obstacle avoidance process for an obstacle, obtaining a driving speed, a first distance, a real-time position and an obstacle avoidance end position of the first intelligent vehicle, and a driving speed and a real-time position of a second vehicle; obtaining first time based on the driving speed of the first intelligent vehicle and the first distance; obtaining a second distance based on the first time and the driving speed of the second vehicle; and detecting whether there is a collision risk between the first intelligent vehicle and the second vehicle based on the real-time position of the first intelligent vehicle, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance. According to the method and the device, the collision risk of the first intelligent vehicle and the opposite coming vehicle in the adjacent lane in the obstacle avoidance process is detected, so that the first intelligent vehicle is prevented from colliding with the opposite coming vehicle in the obstacle avoidance process, and the driving safety of the first intelligent vehicle is improved.

Description

Technical Field

[0001] The present application relates to the field of driving control technology, and in particular to a collision detection method and device. Background Art

[0002] Intelligent Driving Vehicle, also known as self-driving car, driverless car or autonomous car, is a vehicle that can sense the surrounding environment autonomously through the built-in intelligent driving system, and navigate and operate with minimal or no human intervention. That is, intelligent driving car is a car that integrates environmental perception, planning and decision-making, multi-level assisted driving and other functions, and concentrates on the use of computers, modern sensors, information fusion, communications, artificial intelligence and automatic control technologies.

[0003] In current technology, for obstacles ahead, smart driving cars detect information about non-emergent potholes, rocks, and other debris around the smart driving car itself through sensors and other perception devices, such as lidar, millimeter-wave radar, ultrasonic radar, and forward-looking cameras. Then, according to the shape, size, speed, direction, and position of the obstacle in the lane, the smart driving car executes the corresponding obstacle avoidance process to avoid collision with the obstacle ahead, thus achieving pre-avoidance of obstacles and completing the complete smart driving task.

[0004] However, the traffic on actual roads is more complicated. When the smart driving car is completing the process of circumventing the obstacle ahead (obstacle bypassing process), it executes a new bypass trajectory and cannot take into account the collision risk with the oncoming vehicle in the adjacent lane. It may collide with the oncoming vehicle, resulting in reduced driving safety of the smart driving car. Summary of the invention

[0005] Based on the above problems, the present application provides a collision detection method and device, which can detect the risk of collision between an intelligent driving car and an oncoming vehicle in an adjacent lane during an obstacle avoidance process, so as to avoid the collision between the intelligent driving car and the oncoming vehicle during the obstacle avoidance process, thereby improving the driving safety of the intelligent driving car.

[0006] The embodiments of the present application disclose the following technical solutions:

[0007] In a first aspect, the present application discloses a collision detection method, which is applied to a first smart car, and the method comprises:

[0008] In response to the first smart car starting to perform an obstacle avoidance process for an obstacle, obtaining the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second vehicle; wherein the first distance is the driving distance of the first smart car after completing the obstacle avoidance process, and the obstacle avoidance end position is the position of the first smart car when completing the obstacle avoidance process; the second vehicle is a vehicle located in an adjacent lane of the first smart car and traveling in the opposite direction to the first smart car;

[0009] Based on the driving speed and the first distance of the first smart car, a first time is obtained; wherein the first time is the time taken for the first smart car to complete the obstacle avoidance process;

[0010] Based on the first time and the travel speed of the second vehicle, a second distance is obtained; wherein the second distance is the travel distance of the second vehicle within the first time;

[0011] Based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance, detect whether there is a collision risk between the first smart car and the second vehicle.

[0012] Optionally, the detecting whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position, and the second distance includes:

[0013] Based on the real-time position of the first smart car and the obstacle avoidance end position, a third distance is obtained, and a sum of the third distance and the second distance is calculated to obtain a collision prediction distance;

[0014] Obtaining a real-time distance between the first smart car and the second vehicle according to the real-time position of the first smart car and the real-time position of the second vehicle;

[0015] Determining whether the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance;

[0016] When the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance, it is determined that there is no collision risk between the first smart car and the second vehicle;

[0017] When the real-time distance between the first smart car and the second vehicle is not greater than the predicted collision distance, it is determined that there is a collision risk between the first smart car and the second vehicle.

[0018] Optionally, when it is determined that there is a collision risk between the first smart car and the second vehicle, the method further includes:

[0019] The obstacle circumvention process for the obstacle is terminated, and the vehicle is decelerated, reversed, returned to the original lane, and parked; wherein the original lane is the lane where the first smart car was located before the obstacle circumvention process was started.

[0020] Optionally, when it is determined that there is a collision risk between the first smart car and the second vehicle, the method further includes:

[0021] The user is prompted that there is a risk of collision between the first smart car and the second vehicle by one or more of the display, voice and signal light of the first smart car.

[0022] Optionally, when it is determined that there is no collision risk between the first smart car and the second vehicle, the method further includes:

[0023] Continue to execute the obstacle avoidance process for the obstacle.

[0024] Optionally, in response to the first smart car starting to execute the obstacle avoidance process for the obstacle, obtaining the driving speed, the first distance, the real-time position and the obstacle avoidance end position of the first smart car, and the driving speed and the real-time position of the second vehicle, includes:

[0025] In response to the first smart car starting to execute an obstacle avoidance process for the obstacle, detecting whether there is a second vehicle;

[0026] When it is determined that there is a second vehicle, the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second vehicle are obtained.

[0027] Optionally, in response to the first smart car starting to execute the obstacle avoidance process for the obstacle, detecting whether the second vehicle exists includes:

[0028] In response to the first smart car starting to execute an obstacle avoidance process, detecting whether a second vehicle exists based on perception data acquired by the first smart car; wherein the perception data includes perception data acquired by one or more perception devices.

[0029] Optionally, the method further includes:

[0030] When it is determined that the second vehicle does not exist, the obstacle avoidance process for the obstacle is directly continued.

[0031] In a second aspect, the present application discloses a collision detection device, which is applied to a first smart car, comprising:

[0032] a data acquisition module, configured to acquire, in response to the first smart car starting to perform an obstacle avoidance process for an obstacle, a driving speed, a first distance, a real-time position, and an obstacle avoidance end position of the first smart car, and a driving speed and a real-time position of a second vehicle; wherein the first distance is a driving distance of the first smart car after completing the obstacle avoidance process, and the obstacle avoidance end position is a position of the first smart car after completing the obstacle avoidance process; and the second vehicle is a vehicle located in an adjacent lane of the first smart car and traveling in an opposite direction to the first smart car;

[0033] A time determination module, configured to obtain a first time based on the driving speed of the first smart car and the first distance; wherein the first time is the time taken for the first smart car to complete the obstacle avoidance process;

[0034] A distance determination module, configured to obtain a second distance based on the first time and the travel speed of the second vehicle; wherein the second distance is a travel distance of the second vehicle within the first time;

[0035] A collision detection module is used to detect whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance.

[0036] Optionally, the collision detection module is specifically used to:

[0037] Based on the real-time position of the first smart car and the obstacle avoidance end position, a third distance is obtained, and a sum of the third distance and the second distance is calculated to obtain a collision prediction distance;

[0038] Obtaining a real-time distance between the first smart car and the second vehicle according to the real-time position of the first smart car and the real-time position of the second vehicle;

[0039] Determining whether the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance;

[0040] When the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance, it is determined that there is no collision risk between the first smart car and the second vehicle;

[0041] When the real-time distance between the first smart car and the second vehicle is not greater than the predicted collision distance, it is determined that there is a collision risk between the first smart car and the second vehicle.

[0042] Optionally, the collision detection device further includes: an execution module. The execution module is used to terminate the obstacle avoidance process for the obstacle, slow down and reverse back to the original lane and stop the vehicle when it is determined that there is a collision risk between the first smart car and the second vehicle.

[0043] Optionally, the execution module is further configured to, when it is determined that there is no collision risk between the first smart car and the second vehicle, continue to execute the obstacle avoidance process for the obstacle.

[0044] Optionally, the collision detection device further includes: a prompt module. The prompt module is used to prompt a user of the collision risk between the first smart car and the second vehicle through one or more of a display, voice and signal light of the first smart car when determining that there is a collision risk between the first smart car and the second vehicle.

[0045] Optionally, the data acquisition module is specifically used to detect whether a second vehicle exists in response to the first smart car starting to execute an obstacle avoidance process; when it is determined that a second vehicle exists, obtain the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second vehicle.

[0046] Optionally, the execution module is also used to directly continue to execute the obstacle avoidance process for the obstacle when it is determined that the second vehicle does not exist.

[0047] Compared with the prior art, the present application has the following beneficial effects: through the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance, the collision risk of the first smart car with the oncoming vehicle (i.e., the second vehicle) in the adjacent lane during the obstacle avoidance process can be detected, so as to avoid the collision of the smart driving car with the oncoming vehicle during the obstacle avoidance process, thereby improving the driving safety of the smart driving car. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0049] Figure 1 A schematic diagram of a flow chart of a collision detection method provided in an embodiment of the present application;

[0050] Figure 2 An example diagram of information carried in the obstacle avoidance strategy provided in an embodiment of the present application;

[0051] Figure 3A schematic diagram of a process for detecting whether there is a collision risk between a first smart car and a second vehicle provided in an embodiment of the present application;

[0052] Figure 4 An example diagram of the relationship between the real-time distance between the first smart car and the second vehicle and the predicted collision distance provided in an embodiment of the present application;

[0053] Figure 5 A schematic diagram of the structure of a collision detection device provided in an embodiment of the present application;

[0054] Figure 6 A schematic structural diagram of a first smart car provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] As described above, when the smart driving car completes the process of bypassing the obstacle ahead (the process of bypassing the obstacle), it executes a new bypass trajectory. Due to the complex traffic on the actual road conditions and the certain blind spots of the smart driving car when bypassing the obstacle, it cannot take into account the collision risk of the oncoming vehicle in the leading lane during the process of bypassing the obstacle, and may collide with the oncoming vehicle, resulting in reduced driving safety of the smart driving car. For example: when the smart driving car is in the process of bypassing the obstacle and has driven to the adjacent lane according to the bypassing trajectory, if there happens to be an oncoming vehicle in the adjacent lane at this time, the smart driving car may collide with the oncoming vehicle during the process of bypassing the obstacle, causing traffic congestion, and may even affect the safety of the users on the smart driving car.

[0056] The present application provides a collision detection method, including: in response to a first smart car starting to execute an obstacle avoidance process for an obstacle, obtaining the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, as well as the driving speed and real-time position of the second vehicle; obtaining the first time based on the driving speed and first distance of the first smart car; obtaining the second distance based on the first time and the driving speed of the second vehicle; and detecting whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance. The present application can detect the collision risk of the first smart car with an oncoming vehicle (i.e., the second vehicle) in the adjacent lane during the obstacle avoidance process through the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance, so as to avoid the collision of the smart driving car with the oncoming vehicle during the obstacle avoidance process, thereby improving the driving safety of the smart driving car.

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0058] Embodiment 1:

[0059] Combine the following Figure 1-Figure 4 , a collision detection method provided by an embodiment of the present application is introduced in detail. Specifically, a collision detection method provided by an embodiment of the present application is applied to a first smart car, and the first smart car is a smart driving car.

[0060] like Figure 1 As shown, a collision detection method provided in an embodiment of the present application includes the following steps:

[0061] S101, in response to the first smart car starting to execute an obstacle avoidance process, obtaining a driving speed, a first distance, a real-time position and an obstacle avoidance end position of the first smart car, and a driving speed and a real-time position of a second smart car.

[0062] Among them, obstacles refer to all objects that appear in front of the first intelligent vehicle while it is driving and are higher than the height of the laser radar scanning surface.

[0063] The second vehicle is located in an adjacent lane of the first smart car and is traveling in the opposite direction to the first smart car. The adjacent lane is actually the lane to which the first smart car needs to travel when performing an obstacle avoidance process.

[0064] The first distance is the distance traveled by the first smart car after completing the obstacle avoidance process, and the obstacle avoidance end position is the position of the first smart car after completing the obstacle avoidance process.

[0065] Specifically, when the first intelligent vehicle (intelligent driving vehicle) detects an obstacle in front of the vehicle through the perception module, it executes a corresponding obstacle avoidance route (strategy) according to information such as the shape, size, speed, orientation, and position of the obstacle in the lane, so that the first intelligent vehicle executes the corresponding obstacle avoidance process according to the route (strategy). The obstacle avoidance strategy includes the position from which the first intelligent vehicle starts to drive to the adjacent lane, the position from which the first intelligent vehicle starts to return to the original lane from the adjacent lane, the position of the first intelligent vehicle when the obstacle avoidance process is completed, and the distance traveled during the complete obstacle avoidance process.

[0066] For ease of understanding, the following Figure 2 Let's take an example to introduce the information carried in the obstacle avoidance strategy (route). Figure 2In the example, the obstacle avoidance strategy of smart car A for obstacle B is taken as an example.

[0067] like Figure 2 As shown in the figure, in the obstacle avoidance strategy of smart car A for obstacle B, smart car A starts to execute the obstacle avoidance process at position P1 (i.e., starts to drive towards the adjacent lane); smart car A starts to return from the adjacent lane to the original lane at position P2; smart car A completes the entire obstacle avoidance process at position P3, i.e., position P3 is the obstacle avoidance end position. Among them, the distance S1 in the lateral distance (driving direction of smart car A) from position P1 to position P3 is the first distance.

[0068] Exemplarily, the obstacle avoidance route can be obtained in the following manner: the perception module on the first smart car senses the state of the surrounding obstacles and its own operating state; then, the self-motion action within the next preset time under its own operating state and the obstacle movement action of the surrounding obstacles within the next preset time are analyzed, and the self-motion action and the obstacle movement action are compared. When it is analyzed that there will be a collision, the obstacle avoidance route is planned, and the self-motion action is automatically adjusted to execute the corresponding obstacle avoidance process.

[0069] It should be noted that the first distance is the distance in the driving direction of the first smart car.

[0070] In a possible implementation, in response to the first smart car starting to execute the obstacle avoidance process, it is detected whether there is a second vehicle; when it is determined that there is a second vehicle, the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, as well as the driving speed and real-time position of the second vehicle are obtained. When the first smart car detects that there is a second vehicle traveling in the opposite direction in the adjacent lane, it means that the oncoming vehicle may affect the obstacle avoidance process of the first smart car, that is, there is a possibility that the first smart car may collide with the second vehicle during the obstacle avoidance process, so the driving speed, first distance and real-time position of the first smart car, as well as the driving speed and real-time position of the second vehicle are obtained.

[0071] Specifically, in response to the first smart car starting to execute the obstacle avoidance process for the obstacle, based on the perception data obtained by the first smart car, it is detected whether the second vehicle exists.

[0072] The perception data includes the perception data acquired by one or more perception devices. Perception devices refer to a type of device specially designed to perceive the surrounding environment and convert the perception results into useful information. Perception devices include: Camera, Radar, LiDAR, etc.

[0073] Further, when it is determined that there is no second vehicle, the obstacle avoidance process for the obstacle is directly continued. Since there is no second vehicle, there is no oncoming vehicle affecting the obstacle avoidance process of the first smart car, so the obstacle avoidance process for the obstacle is directly continued.

[0074] S102: Obtain a first time based on a driving speed of the first smart car and a first distance.

[0075] Among them, the first time is the time when the first smart car completes the obstacle avoidance process.

[0076] Specifically, through the basic definition of speed, based on the driving speed of the first smart car and the first distance, the first time is obtained.

[0077] Exemplarily, the first time is obtained by formula (1).

[0078] T1=S1 / V1 (1)

[0079] Among them, T1 is the first time, S1 is the first distance, and V1 is the driving speed of the first smart car.

[0080] S103: Obtain a second distance based on the first time and the driving speed of the second vehicle.

[0081] The second distance is the travel distance of the second vehicle within the first time.

[0082] Specifically, through the basic definition of speed, the second distance is obtained based on the first time and the driving speed of the second vehicle.

[0083] Exemplarily, the second distance is obtained by formula (2).

[0084] S2=V2*T1 (2)

[0085] Wherein, S2 is the second distance, V2 is the travel speed of the second vehicle, and T1 is the first time.

[0086] S104: Detect whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position, and the second distance.

[0087] For ease of understanding, the following Figure 3 and Figure 4 How to detect whether there is a collision risk between the first smart car and the second vehicle is introduced in detail.

[0088] like Figure 3 As shown, S104 in the embodiment of the present application specifically includes the following steps:

[0089] S301. Obtain a third distance based on the real-time position of the first smart car and the obstacle avoidance end position; and calculate the sum of the third distance and the second distance to obtain a collision prediction distance.

[0090] The collision prediction distance is a condition for detecting whether there is a collision risk between the first smart car and the second vehicle. That is, the collision prediction distance is the shortest distance between the first smart car and the second vehicle estimated in advance without a collision.

[0091] S302: Obtain a real-time distance between the first smart car and the second vehicle according to the real-time position of the first smart car and the real-time position of the second vehicle.

[0092] The real-time distance is the distance in the driving direction between the first smart car and the second vehicle. For example, the first smart car is traveling eastward, and the second vehicle is traveling in the opposite direction to the first smart car, that is, the second vehicle is traveling westward, and the driving direction between the first smart car and the second vehicle is east-west, and the real-time distance is the east-west distance between the first smart car and the second vehicle.

[0093] It should be noted that the above S301 and S302 do not have a sequential order, and S301 may be executed first and then S302, or S302 may be executed first and then S301, or S301 and S302 may be executed simultaneously.

[0094] S303: Determine whether the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance.

[0095] When the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance, S304 is performed.

[0096] When the real-time distance between the first smart car and the second vehicle is not greater than the predicted collision distance, step S305 is continued.

[0097] S304: Determine that there is no collision risk between the first smart car and the second vehicle.

[0098] When the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance, it means that the real-time distance between the first smart car and the second vehicle is greater than the pre-estimated shortest distance without collision, so there is no collision risk between the first smart car and the second vehicle after the first smart car completes the obstacle avoidance process. It can also be understood that when the first smart car completes the obstacle avoidance process, the second vehicle has not yet reached the obstacle avoidance end position, so there is no collision risk between the first smart car and the second vehicle.

[0099] In a possible implementation, when it is determined that there is no collision risk between the first smart car and the second smart car, the obstacle avoidance process is directly executed.

[0100] S305: Determine whether there is a collision risk between the first smart car and the second smart car.

[0101] When the real-time distance between the first smart car and the second vehicle is not greater than the predicted collision distance, it means that the real-time distance between the first smart car and the second vehicle is not greater than the pre-estimated shortest distance without collision. Specifically, when the real-time distance between the first smart car and the second vehicle is less than the predicted collision distance, the real-time distance between the first smart car and the second vehicle cannot support the completion of the obstacle avoidance process without collision, that is, there is a risk of collision; when the real-time distance between the first smart car and the second vehicle is equal to the predicted collision distance, the real-time distance between the first smart car and the second vehicle barely supports the completion of the obstacle avoidance process without collision, but there is still the possibility of a minor collision. It can also be understood that when the first smart car completes the obstacle avoidance process, the second vehicle has already reached the obstacle avoidance end position, that is, the first smart car has not completed the obstacle avoidance process, and the second vehicle has reached the obstacle avoidance end position. If the first smart car continues to execute the obstacle avoidance process, it will collide with the second vehicle.

[0102] For ease of understanding, the following Figure 4 , an example is given to introduce the relationship between the real-time distance between the first smart car and the second vehicle and the collision prediction distance.

[0103] like Figure 4 As shown, vehicle 401 is a first smart car, vehicle 402 is a second vehicle, and there is an obstacle 403. The first distance in the driving direction corresponding to the obstacle avoidance process of vehicle 401 for obstacle 403 is S1, and the obstacle avoidance end position 404; the first time corresponding to the obstacle avoidance process is obtained according to the driving speed of vehicle 401 and the first distance S1, and the second distance S2 traveled by vehicle 402 during the obstacle avoidance process of vehicle 401 is calculated according to the driving speed of vehicle 402 and the first time; the distance between the real-time position of vehicle 401 and the obstacle avoidance end position 404 is the third distance S3; therefore, the shortest distance between vehicle 401 and vehicle 402 without collision during the obstacle avoidance process is S4, that is, S4 is the collision prediction distance. When the real-time distance d between vehicle 401 and vehicle 402 is less than or equal to S4, it means that vehicle 401 and vehicle 402 overlap or contact at a certain position, and there is a risk of collision, that is, when vehicle 401 is in the process of circumventing obstacles, vehicle 402 has reached the obstacle circumvention end position 404, and vehicle 401 will collide with vehicle 402 if it continues to execute the obstacle circumvention process; when the real-time distance d between vehicle 401 and vehicle 402 is greater than S4, it means that vehicle 401 will not overlap or contact with vehicle 402 during the obstacle circumvention process, and there is no risk of collision, that is, when vehicle 401 has completed the obstacle circumvention process, vehicle 402 has not reached the obstacle circumvention end position 404, and there will be no collision between vehicle 401 and vehicle 402.

[0104] In a possible implementation, when it is determined that there is a risk of collision between the first smart car and the second vehicle, the obstacle avoidance process is terminated, the vehicle is decelerated and reversed back to the original lane and parked. The original lane is the lane where the first smart car was located before the obstacle avoidance process was started. Exemplary: when analyzing that there is a risk of collision between the first smart car and the second vehicle, the distance that the first smart car needs to reverse is calculated so that the first smart car can control itself to reverse automatically.

[0105] Further, after the second vehicle contacts the first smart car with a collision risk, the obstacle avoidance process is automatically restarted. For example, when the second vehicle has passed the position where the first smart car is parked, the first smart car automatically restarts its own obstacle avoidance process.

[0106] In a possible implementation, when it is determined that there is a risk of collision between the first smart car and the second vehicle, the user is prompted to the risk of collision between the first smart car and the second vehicle through one or more methods of the display, voice and signal light of the first smart car. Exemplarily, the first smart car displays a prompt sign on the vehicle display screen to prompt the user that there is a collision between the first smart car and the second vehicle; the first smart car directly broadcasts the prompt information (such as: there is a risk of collision ahead) by voice to prompt the user that there is a collision between the first smart car and the second vehicle; the signal light of the first smart car is turned on and is in a double flash state to prompt the user that there is a collision between the first smart car and the second vehicle.

[0107] The embodiment of the present application provides a collision detection method, including: in response to the first smart car starting to execute the obstacle avoidance process for the obstacle, obtaining the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second vehicle; based on the driving speed and first distance of the first smart car, obtaining the first time; based on the first time and the driving speed of the second vehicle, obtaining the second distance; based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance, detecting whether there is a collision risk between the first smart car and the second vehicle. The embodiment of the present application can detect the collision risk of the first smart car with the oncoming vehicle (i.e., the second vehicle) in the adjacent lane during the obstacle avoidance process through the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance, so as to avoid the collision of the smart driving car with the oncoming vehicle during the obstacle avoidance process, thereby improving the driving safety of the smart driving car.

[0108] Furthermore, when a collision risk is detected between the first smart car and the second vehicle, the first smart car itself is controlled to reverse and return to the original lane, thereby avoiding a collision with the second vehicle, thereby improving the driving safety and reliability of the smart driving car.

[0109] Embodiment 2:

[0110] Combine the following Figure 5 , a collision detection device provided in an embodiment of the present application is introduced in detail, and the collision detection device is applied to a first smart car.

[0111] like Figure 5 As shown, a collision detection device provided in an embodiment of the present application includes the following modules:

[0112] The data acquisition module 501 is used to acquire the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second smart car in response to the first smart car starting to perform the obstacle avoidance process for the obstacle;

[0113] The time determination module 502 is used to obtain a first time based on the driving speed of the first smart car and the first distance; wherein the first time is the time when the first smart car completes the obstacle avoidance process;

[0114] The distance determination module 503 is used to obtain a second distance based on the first time and the driving speed of the second vehicle; wherein the second distance is the driving distance of the second vehicle within the first time;

[0115] The collision detection module 504 is used to detect whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance.

[0116] In one possible implementation, the collision detection module 504 is specifically used to obtain a third distance based on the real-time position of the first smart car and the obstacle avoidance end position, and calculate the sum of the third distance and the second distance to obtain a collision prediction distance; obtain the real-time distance between the first smart car and the second vehicle according to the real-time position of the first smart car and the real-time position of the second vehicle; determine whether the real-time distance between the first smart car and the second vehicle is greater than the collision prediction distance; when the real-time distance between the first smart car and the second vehicle is greater than the collision prediction distance, determine that there is no collision risk between the first smart car and the second vehicle; when the real-time distance between the first smart car and the second vehicle is not greater than the collision prediction distance, determine that there is a collision risk between the first smart car and the second vehicle.

[0117] In a possible implementation, the collision detection device further includes: an execution module. The execution module is used to terminate the obstacle avoidance process for the obstacle, slow down and reverse back to the original lane and stop the vehicle when it is determined that there is a collision risk between the first smart car and the second vehicle.

[0118] In a possible implementation, the execution module is further configured to, when it is determined that there is no collision risk between the first smart car and the second vehicle, continue to execute the obstacle avoidance process for the obstacle.

[0119] In a possible implementation, the collision detection device further includes: a prompt module. The prompt module is used to prompt a user of the collision risk between the first smart car and the second vehicle through one or more of a display, voice, and signal light of the first smart car when determining that there is a collision risk between the first smart car and the second vehicle.

[0120] In one possible implementation, the data acquisition module 501 is specifically used to detect whether a second vehicle exists in response to the first smart car starting to execute an obstacle avoidance process; when it is determined that a second vehicle exists, the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, as well as the driving speed and real-time position of the second vehicle are obtained.

[0121] In a possible implementation, the execution module is further configured to directly continue executing the obstacle avoidance process for the obstacle when it is determined that the second vehicle does not exist.

[0122] The embodiment of the present application provides a collision detection device, including: a data acquisition module 501, which is used to obtain the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second vehicle in response to the first smart car starting to execute the obstacle avoidance process for the obstacle; a time determination module 502, which is used to obtain the first time based on the driving speed and the first distance of the first smart car; a distance determination module 503, which is used to obtain the second distance based on the first time and the driving speed of the second vehicle; a collision detection module 504, which is used to detect whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance. The embodiment of the present application can detect the collision risk between the first smart car and the oncoming vehicle (i.e., the second vehicle) in the adjacent lane during the obstacle avoidance process, so as to avoid the collision between the smart driving car and the oncoming vehicle during the obstacle avoidance process, thereby improving the driving safety of the smart driving car.

[0123] Furthermore, the contact detection device also includes an execution module. When a collision risk is detected between the first smart car and the second vehicle, it controls the first smart car to reverse, return to the original lane and stop, thereby avoiding a collision with the second vehicle, thereby improving the driving safety and reliability of the smart driving car.

[0124] Embodiment three:

[0125] Combine the following Figure 6 , a detailed introduction is given to the system structure of the first smart car provided in an embodiment of the present application.

[0126] like Figure 6 As shown, the first smart car provided in the embodiment of the present application includes: a perception and positioning unit 610, a control unit 620 and an execution unit 630.

[0127] Among them, the perception and positioning unit 610 is an important part of the intelligent driving car, which provides the necessary information for the intelligent driving car to realize autonomous driving. The perception and positioning unit 610 includes two functions, positioning and perception, and is the basis for the intelligent driving car to realize autonomous driving. That is, the intelligent driving car obtains a variety of sensor data through the perception and positioning unit 610, integrates a variety of sensor data to realize a comprehensive understanding of its surrounding environment and accurate positioning of its own position, thereby providing a basis for the decision-making and control of the vehicle.

[0128] Specifically, the sensing and positioning unit 610 includes: a sensing unit 611 and a positioning unit 612 .

[0129] The perception module 611 is used to detect and identify the environment around the first smart car itself. That is, the perception module 611 can obtain the position, shape, speed, trajectory, lane width and driving boundary of obstacles, and transmit the above information to the control unit 620.

[0130] Exemplarily, the perception unit 611 includes but is not limited to: laser radar (LIDAR), front camera (FrontCamera, FCam), radar (Radar) and ultrasonic sensor (Ultrasonic Sensors System). Among them, laser radar is used to use laser pulses to create a three-dimensional model of the surrounding environment for accurate distance measurement; the front camera refers to a camera installed at the front of the vehicle to capture visual information in front of the vehicle; radar is used to detect the position, speed and other information of an object through radio waves; ultrasonic sensors are used to use ultrasound for short-distance detection.

[0131] The localization module 612 is used to determine the precise position of the first smart car in the geographic space, that is, the localization module 612 can obtain its own positioning coordinates, speed and heading, and the obstacle avoidance area judgment value of the track route.

[0132] Exemplarily, the positioning unit 612 includes but is not limited to a high-definition map (HDMap), a global positioning system (GPS), and an inertial measurement unit (IMU). Among them, the high-definition map is an important component for realizing accurate vehicle positioning and path planning. The high-precision map contains accurate geographic information required for autonomous driving, such as lane lines, traffic signs, etc.; the global positioning system is used to determine the location of the vehicle through signals provided by satellites; the inertial measurement unit is used to measure the motion state of the vehicle through accelerometers and gyroscopes, thereby assisting in the positioning of the vehicle.

[0133] Among them, the control unit 620 is one of the core components for realizing the automatic driving function of the first smart car. It is responsible for formulating appropriate driving strategies based on the perception data (e.g., environmental information and location information, etc.) provided by the perception and positioning unit 610, and controlling the execution unit 630 to implement these strategies. That is, the control unit 620 obtains the perception data from the perception and positioning unit 610, and after processing, generates control instructions to make the vehicle drive according to the predetermined target. In the embodiment of the present application, the control unit 620 is used to execute the collision detection method shown in the first embodiment.

[0134] Specifically, the control unit 620 sends a control instruction to the execution unit 630 via the CAN line. For example, when the control unit 620 determines that there is a collision risk between the first smart car and the second vehicle, it sends a reversing instruction to the execution unit 630 via the CAN line, and the execution unit 630 controls the first smart car to reverse back to the original lane.

[0135] Among them, the CAN line (Controller Area Network) is a serial communication protocol used for communication between electronic systems inside the vehicle. The CAN line is used for various electronic control units inside the vehicle to exchange information with each other, thereby achieving coordinated work inside the vehicle.

[0136] It should be noted that each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the method and device embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments. The method and device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components indicated as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0137] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application 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.

Claims

1. A collision detection method, characterized in that: Applied to a first smart car, the method includes: In response to the first smart car starting to perform an obstacle avoidance process for an obstacle, the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second vehicle are obtained; wherein the first distance is the driving distance of the first smart car after completing the obstacle avoidance process, and the obstacle avoidance end position is the position of the first smart car when completing the obstacle avoidance process; the second vehicle is a vehicle located in an adjacent lane of the first smart car and traveling in the opposite direction to the first smart car; Based on the driving speed and the first distance of the first smart car, a first time is obtained; wherein the first time is the time taken for the first smart car to complete the obstacle avoidance process; Based on the first time and the travel speed of the second vehicle, a second distance is obtained; wherein the second distance is the travel distance of the second vehicle within the first time; Based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance, detect whether there is a collision risk between the first smart car and the second vehicle.

2. The method according to claim 1, characterized in that The detecting whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance includes: Based on the real-time position of the first smart car and the obstacle avoidance end position, a third distance is obtained, and a sum of the third distance and the second distance is calculated to obtain a collision prediction distance; Obtaining a real-time distance between the first smart car and the second vehicle according to the real-time position of the first smart car and the real-time position of the second vehicle; Determining whether the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance; When the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance, it is determined that there is no collision risk between the first smart car and the second vehicle; When the real-time distance between the first smart car and the second vehicle is not greater than the predicted collision distance, it is determined that there is a collision risk between the first smart car and the second vehicle.

3. The method according to claim 2, characterized in that When it is determined that there is a collision risk between the first smart car and the second vehicle, the method further includes: The obstacle circumvention process for the obstacle is terminated, and the vehicle is decelerated, reversed, returned to the original lane, and parked; wherein the original lane is the lane where the first smart car was located before the obstacle circumvention process was started.

4. The method according to claim 2, characterized in that: When it is determined that there is a collision risk between the first smart car and the second vehicle, the method further includes: The user is prompted that there is a collision risk between the first smart car and the second vehicle by one or more of the display, voice and signal lights of the first smart car.

5. The method according to claim 2, characterized in that: When it is determined that there is no collision risk between the first smart car and the second vehicle, the method further includes: Continue to execute the obstacle avoidance process for the obstacle.

6. The method according to claim 1, characterized in that In response to the first smart car starting to execute the obstacle avoidance process for the obstacle, obtaining the driving speed, the first distance, the real-time position and the obstacle avoidance end position of the first smart car, and the driving speed and the real-time position of the second vehicle, including: In response to the first smart car starting to execute an obstacle avoidance process for the obstacle, detecting whether there is a second vehicle; When it is determined that there is a second vehicle, the driving speed, first distance, real-time position and obstacle avoidance end position of the first smart car, and the driving speed and real-time position of the second vehicle are obtained.

7. The method according to claim 6, characterized in that In response to the first smart car starting to execute the obstacle avoidance process for the obstacle, detecting whether there is a second vehicle includes: In response to the first smart car starting to execute an obstacle avoidance process, detecting whether a second vehicle exists based on perception data acquired by the first smart car; wherein the perception data includes perception data acquired by one or more perception devices.

8. The method according to claim 6, characterized in that The method further comprises: When it is determined that the second vehicle does not exist, the obstacle avoidance process for the obstacle is directly continued.

9. A collision detection device, characterized in that: Applied to a first smart car, the device comprises: a data acquisition module, configured to acquire, in response to the first smart car starting to perform an obstacle avoidance process for an obstacle, a driving speed, a first distance, a real-time position, and an obstacle avoidance end position of the first smart car, and a driving speed and a real-time position of a second vehicle; wherein the first distance is a driving distance of the first smart car after completing the obstacle avoidance process, and the obstacle avoidance end position is a position of the first smart car after completing the obstacle avoidance process; and the second vehicle is a vehicle located in an adjacent lane of the first smart car and traveling in an opposite direction to the first smart car; A time determination module, configured to obtain a first time based on the driving speed of the first smart car and the first distance; wherein the first time is the time taken for the first smart car to complete the obstacle avoidance process; A distance determination module, configured to obtain a second distance based on the first time and the travel speed of the second vehicle; wherein the second distance is a travel distance of the second vehicle within the first time; A collision detection module is used to detect whether there is a collision risk between the first smart car and the second vehicle based on the real-time position of the first smart car, the real-time position of the second vehicle, the obstacle avoidance end position and the second distance.

10. The device according to claim 9, characterized in that The collision detection module is specifically used for: Based on the real-time position of the first smart car and the obstacle avoidance end position, a third distance is obtained, and a sum of the third distance and the second distance is calculated to obtain a collision prediction distance; Obtaining a real-time distance between the first smart car and the second vehicle according to the real-time position of the first smart car and the real-time position of the second vehicle; Determining whether the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance; When the real-time distance between the first smart car and the second vehicle is greater than the predicted collision distance, it is determined that there is no collision risk between the first smart car and the second vehicle; When the real-time distance between the first smart car and the second vehicle is not greater than the predicted collision distance, it is determined that there is a collision risk between the first smart car and the second vehicle.

Images