A braking method, system, storage medium for an autonomous vehicle

Abstract

The application discloses a kind of braking method, system, storage medium for automatic driving vehicle, comprising S1: the data of target to be tested is obtained, the first deceleration when designing vehicle braking;S2: real-time perception surrounding environment, when sensing obstacle, detection parameter in the process of vehicle travel and the first deceleration are input into the deceleration optimization model constructed, and real-time deceleration is output;That is, guarantee that vehicle does not collide with obstacle at the same time, try to guarantee the comfort of target to be tested S3: according to the real-time deceleration in S2, vehicle is automatically decelerated and braked.The application can calculate braking deceleration in real time according to actual situation, can provide the braking scheme of highest comfort when there is no obstacle interference;When there is obstacle interference, the braking scheme of highest comfort can be provided while meeting passenger safety.

Description

Technical Field

[0001] The present invention relates to the field of vehicle autonomous driving technology, and in particular to a braking method, system, and storage medium for an autonomous driving vehicle. Background Art

[0002] Existing technologies for autonomous vehicles present several challenges, including understanding their surroundings, maintaining a safe distance from road obstacles, and complying with established and unwritten regulations. However, for autonomous city buses, the deceleration strategy is largely the same as that for small cars, with collision avoidance as the primary goal, followed by the passenger experience. Because small cars are equipped with seatbelts and airbags, higher deceleration rates pose no risk to passengers, and the ride is more comfortable than in city buses.

[0003] Because city buses lack airbags and seatbelts, avoiding collisions primarily can cause passengers to lose balance, exposing them to a greater risk than a collision itself. This is because the obstacle ahead could be an inanimate object, potentially presenting no personal injury even if a collision occurs. Standing passengers might not be able to hold onto the handrails, and excessive deceleration can degrade the passenger experience and even result in injury or death.

[0004] When there are no obstacles interfering with the autonomous vehicle, the deceleration strategy should focus on comfort. When an obstacle suddenly appears in front of the autonomous city bus, a safe braking and deceleration strategy is needed, that is, how to ensure the safety of passengers in the car and avoid collisions as much as possible without falling. Summary of the Invention

[0005] In response to the incompatibility between safety and comfort during the braking process of autonomous city buses in the existing technology, the present invention proposes a braking method, system, and storage medium for autonomous vehicles. By calculating the braking deceleration in real time, the braking process is optimized as much as possible, taking into account passenger comfort while ensuring the safety of passengers in the vehicle.

[0006] In order to achieve the above object, the present invention provides the following technical solutions:

[0007] A braking method for an autonomous driving vehicle, comprising the following steps:

[0008] S1: Obtain the data of the target to be tested and design the first deceleration of the vehicle during braking;

[0009] S2: Real-time perception of the surrounding environment. When an obstacle is detected, the real-time deceleration is calculated based on the detection parameters and the first deceleration during the vehicle's driving process;

[0010] S3: Automatically decelerate and brake the vehicle according to the real-time deceleration in S2.

[0011] Preferably, in said S1, the data of the target to be tested include the contact length s with the ground and the center of mass height h.

[0012] Preferably, in S1, the calculation formula of the first deceleration is:

[0013] Ac=g*s / h (1)

[0014] In formula (1), Ac represents the first deceleration; g represents the acceleration due to gravity; s represents the contact length between the target to be tested and the ground; and h represents the height of the center of mass of the target to be tested.

[0015] Preferably, in S2, the detection parameters include the current vehicle speed and the obstacle distance.

[0016] Preferably, in S2, the calculation formula of the real-time deceleration is as follows:

[0017]

[0018] In formula (2), w k Indicates the distance the vehicle passes the obstacle after it stops; s k represents the difference between the actual deceleration of the vehicle and the first deceleration Ac; N represents the total duration of the braking process of the autonomous driving vehicle, and k is the kth moment in the braking process; express The square of the difference between the speed of the autonomous driving vehicle at the moment and the speed before braking; represents the intermediate moment between moment k-1 and moment k; It represents the square of the difference between the speed of the autonomous driving vehicle at time k and the speed before braking; α, β, and γ are adjustment parameters.

[0019] Preferably, the actual deceleration of the vehicle should meet the following conditions:

[0020]

[0021] In formula (3), k represents any time from 0 to N-1; N-1 represents the last time the vehicle stopped; represents the actual deceleration of the vehicle at time k.

[0022] Preferably, the actual deceleration of the vehicle should also meet the following conditions:

[0023]

[0024] In formula (3), Ac represents the first deceleration Ac; represents the actual deceleration of the vehicle at time k; sk Indicates the difference between the actual vehicle deceleration and the first deceleration Ac.

[0025] Preferably, the speed limit condition of the autonomous driving vehicle is:

[0026]

[0027] In formula (4), The velocity represents the intermediate value between time k-1 and time k; Indicates the vehicle's speed before braking.

[0028] The present invention also provides a braking system for an autonomous driving vehicle, comprising:

[0029] The first acquisition module is used to acquire data of the target to be tested, including the contact length s between the target to be tested and the ground, and the center of mass height h;

[0030] a first determining module, configured to determine a first deceleration during vehicle braking according to the data of the target to be tested obtained by the first acquiring module;

[0031] The second acquisition module is used to obtain detection parameters of the vehicle during driving, including speed and obstacle distance;

[0032] a second determining module, configured to determine, based on the first deceleration of the first determining module and the detection parameter of the second acquiring module, a real-time deceleration rate that ensures safety and comfort when an obstacle is detected;

[0033] The control module is configured to brake and decelerate the vehicle according to the real-time deceleration determined by the second determining module.

[0034] A computer-readable storage medium stores a computer program, which implements the steps of the braking method when executed by a processor.

[0035] In summary, due to the adoption of the above technical solution, compared with the prior art, the present invention has at least the following beneficial effects:

[0036] The present invention can calculate the braking deceleration in real time according to actual conditions, and can provide the most comfortable braking solution when there is no obstacle interference; when there is obstacle interference, it can provide the most comfortable braking solution while ensuring the safety of passengers. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 1 is a flow chart of a braking method for an autonomous driving vehicle according to an exemplary embodiment of the present invention.

[0038] Figure 2FIG. 4 is a schematic diagram of the distance between vehicle braking and obstacles according to an exemplary embodiment of the present invention.

[0039] Figure 3 Schematic diagram of a braking system for an autonomous vehicle according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0040] The present invention will be further described in detail below with reference to the examples and specific implementation methods. However, this should not be understood as limiting the scope of the present invention to the following examples, as all technologies implemented based on the present invention fall within the scope of the present invention.

[0041] In the description of the present invention, it should be understood that the terms "longitudinal", "transverse", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention.

[0042] like Figure 1 As shown, the present invention provides a braking method for an autonomous driving vehicle, which can be used for an autonomous driving city bus, and specifically includes the following steps:

[0043] In this embodiment, a passenger standing on a vehicle without a handle is the most likely target to fall, and maintaining balance depends only on the contact force with the ground. The design is based on this type of target as an example.

[0044] S1: Obtain the data of the target to be tested and design the first deceleration to ensure the target comfort when the vehicle brakes.

[0045] In this embodiment, the target to be detected can be a human body model designed based on an adult (which can be obtained by averaging big data), including the contact length s with the ground and the center of mass height h. Preferably, s≈0.12m, center of mass height h≈1m, and gravity acceleration g≈9.8m / s 2 , then the first deceleration to ensure comfort is calculated as: Ac=g*s / h=1.23m / s 2 , exceeding the first deceleration, the passenger will begin to lose balance, but can repair the balance by adjusting the posture.

[0046] In this embodiment, when the deceleration exceeds the second deceleration Amax=3.70m / s 2 When the vehicle is in a state of shock, the passenger may fall even if the posture is adjusted.

[0047] S2: The vehicle perceives the surrounding environment in real time while driving. When an obstacle is detected, the detection parameters during the vehicle driving process are input into the constructed deceleration optimization model to output the real-time deceleration.

[0048] In this embodiment, the autonomous vehicle controls various modules and exchanges information with the server through the onboard terminal during driving. It can sense the surrounding environment through the perception module (lidar, ultrasonic radar, millimeter-wave radar, camera and other sensors) and obtain information about the relative position changes between obstacles and the autonomous vehicle.

[0049] The detection parameters include the vehicle speed when it starts braking. The obstacle distance (the expected stopping distance, i.e. the distance between the current vehicle and the obstacle) is x obs ;w k Indicates the distance the vehicle passes the obstacle after it stops; s k Indicates the difference between the actual vehicle deceleration and the first deceleration Ac; α, β, and γ are adjustment parameters, with default values ​​set to 5.0, 5.0, and 1.5 respectively;

[0050] In this embodiment, the deceleration optimization model f(x) is expressed as follows:

[0051]

[0052] In formula (1), w k Indicates the distance the vehicle passes the obstacle after it stops; s k represents the difference between the actual deceleration of the vehicle and the first deceleration Ac; N represents the total duration of the braking process of the autonomous driving vehicle, and k is the kth moment in the braking process; express The square of the difference between the speed of the autonomous driving vehicle at the moment and the speed before braking; Represents the intermediate value between time k-1 and time k; represents the square of the difference between the speed of the autonomous vehicle at time k and the speed before braking; the optimal w can be obtained by minimizing the function f(x) under the constraints described below. k 、s k and curve; α, β, γ are adjustment parameters, which are used to adjust w k 、s k and The default values ​​of weights are set to 5.0, 5.0, and 1.5 respectively;

[0053] In this embodiment, the optimal deceleration is obtained under the current vehicle condition (when an obstacle is detected), that is, the deceleration and braking distance of the vehicle is ensured to be less than x obs, while ensuring that the vehicle's braking deceleration is less than Ac, which can ensure both safety and comfort, it is necessary to minimize the deceleration optimization model f(x).

[0054] The various parameters in the deceleration optimization model f(x) should meet the following conditions:

[0055] 1) To limit the maximum deceleration to prevent passengers from falling, the vehicle deceleration limit conditions are:

[0056]

[0057] Formula (2) indicates that at any moment during the braking process, the absolute value of the actual deceleration of the vehicle must be less than the second deceleration Amax; k represents any moment from 0 to N-1; N-1 represents the last moment when the vehicle just stopped; Indicates the actual deceleration of the vehicle;

[0058] 2) To ensure comfort, it is necessary to make That is, we need to minimize s k , the constraints are:

[0059]

[0060] In formula (3), when f(x) finds the optimal solution (minimum value), s is obtained. k value;

[0061] s k A value of 0 indicates that the vehicle's braking deceleration is the first deceleration, and passengers will not lose their balance, thus ensuring comfort.

[0062] 3) To ensure that the speed at each moment is within the range and does not overshoot, the speed limit conditions are:

[0063]

[0064] In formula (4), The velocity represents the intermediate value between time k-1 and time k; Indicates the vehicle's speed before braking;

[0065] 4) If Figure 2 As shown, the vehicle is moving from left to right. When decelerating and braking, in order to make the vehicle decelerating and braking distance less than x obs To avoid collision between the vehicle and the obstacle, it is necessary to k To minimize:

[0066]

[0067] In formula (5), x kIndicates the vehicle deceleration and braking distance, x obs Represents the distance between the vehicle and the obstacle; minimizing the function f(x) can get the optimal w k Value; w k A value of 0 indicates that the vehicle will not collide with obstacles and safety is guaranteed.

[0068] 5) After the braking and deceleration process is completed, the vehicle speed should be equal to 0 and the acceleration should be equal to 0.

[0069] 6) In this embodiment, in order to further improve comfort, the following conditions are also met:

[0070]

[0071] In formula (6), represents the speed at time k; Indicates the vehicle's speed before braking; represents the speed at time k and the speed before braking Minimizing this value can improve comfort, and minimizing the function f(x) can get the optimal The smaller k is, the greater the value of γ N-k The larger the value, the slower the speed changes. The smaller, The smaller it is.

[0072]

[0073] In formula (7), represents the speed of the intermediate value between time k-1 and time k; T represents the calculation period of the calculation unit (second determination module); represents the deceleration of the vehicle at time k; represents the deceleration at time k+1;

[0074] In this embodiment, after the deceleration optimization model f(x) is restricted by the conditions, w in the entire braking process is obtained. k 、s k and (the value at each moment in {0...N-1}), and then output the real-time deceleration value.

[0075] S3: Brake the vehicle according to the real-time deceleration in S2.

[0076] Based on the above method, Figure 3 As shown, the present invention also provides a braking system for an autonomous driving vehicle, comprising:

[0077] The first acquisition module is used to obtain data of the target to be tested, including the contact length s between the target to be tested and the ground, the center of mass height h, etc.;

[0078] a first determining module, configured to determine a first deceleration for ensuring target comfort during vehicle braking based on the data of the target to be tested from the first acquiring module;

[0079] The second acquisition module is used to obtain detection parameters during vehicle driving, including speed, obstacle distance, etc.;

[0080] The second determination module is used to determine the optimal deceleration of the vehicle when an obstacle is detected based on the first deceleration of the first determination module and the detection parameters of the second acquisition module. That is, to ensure that the vehicle does not collide with the obstacle while trying to ensure the comfort of the target to be tested (will not lose balance, that is, the deceleration does not exceed the first deceleration), or the passenger can avoid falling through adjustment, that is, the deceleration does not exceed the second deceleration.

[0081] The control module is configured to brake and decelerate the vehicle according to the optimal deceleration determined by the second determination module.

[0082] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the braking method described in the above embodiment when executing the computer program.

[0083] The present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the braking method described in the above embodiment are implemented.

[0084] Those skilled in the art will appreciate that the above-mentioned embodiments are specific examples for implementing the present invention, and that in actual applications, various changes may be made thereto in form and detail without departing from the spirit and scope of the present invention.

Claims

1. A braking method for an autonomous driving vehicle, characterized in that: The specific steps include: S1: Obtain the data of the target to be tested and design the first deceleration of the vehicle during braking; S2: Real-time perception of the surrounding environment. When an obstacle is detected, the real-time deceleration is calculated based on the detection parameters and the first deceleration during the vehicle's driving process; S3: Automatically decelerate and brake the vehicle according to the real-time deceleration in S2; In S1, the calculation formula for the first deceleration is: Ac=g*s / h (1) In formula (1), Ac represents the first deceleration; g represents the acceleration due to gravity; s represents the contact length between the target to be tested and the ground; h represents the height of the center of mass of the target to be tested; In S2, the calculation formula for real-time deceleration is as follows: In formula (2), w k Indicates the distance the vehicle passes the obstacle after it stops; s k represents the difference between the actual deceleration of the vehicle and the first deceleration Ac; N represents the total duration of the braking process of the autonomous driving vehicle, and k is the kth moment in the braking process; express The square of the difference between the speed of the autonomous driving vehicle at the moment and the speed before braking; represents the intermediate moment between moment k-1 and moment k; represents the square of the difference between the speed of the autonomous driving vehicle at time k and the speed before braking; α, β, and γ are adjustment parameters; The actual vehicle deceleration should meet the following conditions: In formula (3), k represents any time from 0 to N-1; N-1 represents the last time the vehicle stopped; represents the actual deceleration of the vehicle at time k; Ac represents the first deceleration Ac; represents the actual deceleration of the vehicle at time k; s k Indicates the difference between the actual vehicle deceleration and the first deceleration Ac; When decelerating and braking, in order to make the vehicle decelerating and braking distance less than x obs To avoid collision between the vehicle and the obstacle, it is necessary to k To minimize: In formula (5), x k Indicates the vehicle deceleration and braking distance, x obs Represents the distance between the vehicle and the obstacle; minimizing the function f(x) can get the optimal w k value.

2. The braking method for an autonomous driving vehicle according to claim 1, wherein: The speed limit conditions of the autonomous driving vehicle are: In formula (4), The velocity represents the intermediate value between time k-1 and time k; Indicates the vehicle's speed before braking.

3. A braking system for an autonomous driving vehicle based on the method according to any one of claims 1-2, characterized in that: include: The first acquisition module is used to acquire data of the target to be tested, including the contact length s between the target to be tested and the ground, and the center of mass height h; a first determining module, configured to determine a first deceleration during vehicle braking according to the data of the target to be tested obtained by the first acquiring module; The second acquisition module is used to obtain detection parameters of the vehicle during driving, including speed and obstacle distance; a second determining module, configured to determine, based on the first deceleration of the first determining module and the detection parameter of the second acquiring module, a real-time deceleration rate that ensures safety and comfort when an obstacle is detected; The control module is configured to brake and decelerate the vehicle according to the real-time deceleration determined by the second determining module.

4. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the braking method according to any one of claims 1 to 2 are implemented.

Images