Collision avoidance method and device and vehicle

Abstract

The invention relates to a collision avoidance method and device and a vehicle, and relates to the technical field of vehicles, and the method comprises the steps: determining the collision risk between the vehicle and a collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object; determining a plurality of candidate collision avoidance strategies based on the collision risk; wherein different collision risks correspond to different types of collision avoidance strategies, and the types of the collision avoidance strategies comprise an acceleration collision avoidance strategy, a braking collision avoidance strategy, a steering collision avoidance strategy and a braking and steering combined collision avoidance strategy; the type of the candidate collision avoidance strategy corresponds to the collision risk, and control parameters in different candidate collision avoidance strategies under the same type are different; based on the respective cost values of the plurality of candidate collision avoidance strategies, determining a collision avoidance strategy to be executed by the vehicle from the plurality of candidate collision avoidance strategies; and controlling the vehicle to run according to the collision avoidance strategy. Therefore, the vehicle can cope with various complex traffic scenes.

Description

Technical Field

[0001] This application relates to the technical field of vehicles, particularly to the technical field of vehicle control, and specifically to a collision avoidance method, device, and vehicle. Background Art

[0002] Traffic safety has always been a major global public safety challenge. Due to the complex and changeable traffic conditions at intersections, the current mainstream Autonomous Emergency Braking (AEB) systems are difficult to accurately predict potential collision risks, and the existing coping strategies mainly rely on braking to avoid or mitigate collisions, making it difficult to apply to the extremely complex collision scenarios at intersections.

[0003] Therefore, the traditional vehicle collision avoidance strategies can no longer meet the growing traffic safety needs. There is an urgent need for a practical and effective vehicle collision avoidance strategy to avoid or mitigate collisions and improve driving safety. Summary of the Invention

[0004] This application provides a collision avoidance method, device, and vehicle to at least solve the technical problem that the collision avoidance strategy in the related art is difficult to apply to the extremely complex collision scenarios at intersections. The technical solution of this application is as follows: According to the first aspect provided by this application, a collision avoidance method is provided, including: determining the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object; determining a plurality of candidate collision avoidance strategies based on the collision risk; where different collision risks correspond to different types of collision avoidance strategies, and the types of collision avoidance strategies include: acceleration collision avoidance strategy, braking collision avoidance strategy, steering collision avoidance strategy, and braking combined with steering collision avoidance strategy; the types of candidate collision avoidance strategies correspond to the collision risk, and the control parameters in different candidate collision avoidance strategies of the same type are different; determining the collision avoidance strategy to be executed by the vehicle from the plurality of candidate collision avoidance strategies based on the respective cost values of the plurality of candidate collision avoidance strategies; where the cost value is determined according to the evaluation parameters corresponding to the candidate collision avoidance strategy; the evaluation parameters include at least one of the following: collision probability, maneuver intensity, comfort level, and occupant injury value; controlling the vehicle to travel according to the collision avoidance strategy.

[0005] According to the above technical means, the present application can continuously monitor the motion information of the vehicle and the collision avoidance object, evaluate the collision risk in real time, generate multiple candidate collision avoidance strategies according to the collision risk. These strategies cover different types of collision avoidance actions (such as acceleration, braking, steering, etc.), and different strategies under the same type have different control parameters, ensuring that the vehicle has more options to deal with potential dangers when facing complex traffic scenarios. In addition, by introducing multiple evaluation parameters such as collision probability, maneuver intensity, comfort, and occupant injury value, comprehensively evaluate the advantages and disadvantages of candidate collision avoidance strategies from multiple dimensions, ensure that the selected strategy can reach a better level in multiple aspects, thereby improving the success rate of collision avoidance and minimizing the losses caused by collisions.

[0006] In a possible implementation manner, the collision risks are the first collision risk, the second collision risk, and the third collision risk in ascending order; the first collision risk corresponds to an acceleration collision avoidance strategy or a braking collision avoidance strategy; the second collision risk corresponds to a braking collision avoidance strategy or a steering collision avoidance strategy; the third collision risk corresponds to a braking combined with steering collision avoidance strategy.

[0007] According to the above technical means, the present application can classify the collision risks from low to high and respectively correspond to different collision avoidance strategies, so that the obstacle avoidance device can select the most effective response method according to the risk level, improving the success rate and efficiency of collision avoidance.

[0008] In a possible implementation manner, when the candidate collision avoidance strategy is an acceleration collision avoidance strategy, the control parameter is acceleration; when the candidate collision avoidance strategy is a braking collision avoidance strategy, the control parameter is deceleration; when the candidate collision avoidance strategy is a steering collision avoidance strategy, the control parameter is heading angular velocity; when the candidate collision avoidance strategy is a braking combined with steering collision avoidance strategy, the control parameters are heading angular velocity and deceleration.

[0009] According to the above technical means, for the acceleration collision avoidance strategy, the present application can use acceleration as the control parameter to precisely control the acceleration behavior of the vehicle, ensuring that the vehicle can quickly and smoothly avoid obstacles. For the braking collision avoidance strategy, using deceleration as the control parameter can precisely control the braking intensity of the vehicle, avoiding excessive braking or insufficient braking. For the steering collision avoidance strategy, using heading angular velocity as the control parameter can precisely control the steering angle and steering rate of the vehicle, ensuring that the vehicle can accurately avoid obstacles. For the braking combined with steering collision avoidance strategy, using both heading angular velocity and deceleration as control parameters can achieve comprehensive and precise control of the vehicle's motion state.

[0010] In a possible implementation manner, based on the evaluation parameters corresponding to the candidate collision avoidance strategy, determine the cost value of the candidate collision avoidance strategy, including: performing weighted summation on each evaluation parameter corresponding to the candidate collision avoidance strategy to obtain the cost value of the candidate collision avoidance strategy.

[0011] According to the above technical means, the present application can fuse multiple evaluation parameters such as collision probability, maneuver intensity, comfort, and occupant injury value into a single cost value through weighted summation, so as to comprehensively consider the performance of the collision avoidance strategy in all aspects and determine the optimal obstacle avoidance strategy.

[0012] In a possible implementation manner, the collision probability is determined based on the minimum collision time and the minimum relative distance calculated at the current moment.

[0013] According to the above technical means, the present application can comprehensively consider the minimum collision time and the minimum relative distance, accurately evaluate the collision probability, and provide a more reliable basis for the subsequent selection of collision avoidance strategies.

[0014] In a possible implementation manner, the maneuver intensity is determined based on the longitudinal acceleration and the lateral heading angular velocity.

[0015] According to the above technical means, the present application can evaluate the stability of the vehicle when implementing the collision avoidance strategy by considering the longitudinal acceleration and the lateral heading angular velocity, and reduce the risk of traffic accidents caused by improper strategy selection.

[0016] In a possible implementation manner, the comfort is determined based on the jerk and the angular acceleration.

[0017] According to the above technical means, the present application can accurately evaluate the comfort of passengers during the vehicle obstacle avoidance process by considering the jerk and the angular acceleration.

[0018] In a possible implementation manner, the occupant injury value is determined by the following method: predicting the collision information when a collision occurs between the vehicle and the collision avoidance object, where the collision information includes the collision position, the collision angle, and the collision speed; inputting the collision information into the occupant injury prediction model to obtain the occupant injury value.

[0019] According to the above technical means, the present application can determine the occupant injury value by predicting the collision position, the collision angle, and the collision speed, so as to select a collision avoidance strategy that can minimize the risk of occupant injury.

[0020] In a possible implementation manner, based on the motion information of the vehicle and the motion information of the collision avoidance object, the collision risk between the vehicle and the collision avoidance object is determined, including: based on the motion information of the vehicle and the motion information of the collision avoidance object, determining the latest collision avoidance moment; when the latest collision avoidance moment is greater than the preset threshold, determining the collision risk as the first collision risk; or, when the latest collision avoidance moment is greater than or equal to 0 and less than or equal to the preset threshold, determining the collision risk as the second collision risk; or, when the latest collision avoidance moment is less than 0, determining the collision risk as the third collision risk.

[0021] According to the above technical means, the present application can calculate the latest collision avoidance time by comprehensively considering the motion information of the vehicle and the collision avoidance object (such as speed, acceleration, position, etc.), that is, the latest time point when the vehicle takes collision avoidance measures to avoid collision, so as to determine the collision risk according to the latest collision avoidance time, and further adopt appropriate collision avoidance strategies for different risk levels, improve the success rate of collision avoidance, and reduce the occurrence of collisions.

[0022] In a possible implementation manner, determining the latest collision avoidance time based on the motion information of the vehicle and the motion information of the collision avoidance object includes: determining the latest steering time and the latest braking time based on the motion information of the vehicle and the motion information of the collision avoidance object; wherein, the latest steering time is the latest time to avoid collision by a steering operation; the latest braking time is the latest time to avoid collision by braking; and determining the minimum value of the latest steering time and the latest braking time as the latest collision avoidance time.

[0023] According to the above technical means, the present application can determine the latest steering time and the latest braking time respectively, comprehensively consider the possibilities of these two collision avoidance methods, and determine the minimum value of the latest steering time and the latest braking time as the latest collision avoidance time, so as to select the collision avoidance method that can optimally avoid collision, improve the success rate of collision avoidance.

[0024] In a possible implementation manner, before determining the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object, the method includes: predicting the collision time when a collision occurs between the vehicle and the target object based on the motion information of the vehicle and the motion information of the target object; and when the collision time is less than a preset collision time threshold, determining the target object as the collision avoidance object.

[0025] According to the above technical means, the present application can predict the collision time based on the motion information of the vehicle and the motion information of the target object before determining the collision risk based on the motion information of the vehicle and the motion information of the collision avoidance object, and determine the target object as the collision avoidance object when the collision time is less than the preset collision time threshold, so as to accurately determine the collision avoidance object in a timely manner, thereby efficiently and accurately determining the collision avoidance strategy, reducing the collision risk, and protecting the safety of passengers.

[0026] In a possible implementation manner, controlling the vehicle to travel according to the collision avoidance strategy includes: when the control parameter of the collision avoidance strategy includes the course angular velocity, adjusting the course angular velocity of the vehicle based on a smooth transition strategy.

[0027] According to the above technical means, the present application can adjust the course angular velocity based on the smooth transition strategy, make the change of the vehicle's traveling direction smoother, reduce the discomfort of passengers, and improve the riding comfort.

[0028] According to a second aspect provided by the present application, a collision avoidance device is provided, including: a determination unit and a control unit; the determination unit is configured to determine the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object; the determination unit is further configured to determine a plurality of candidate collision avoidance strategies based on the collision risk; wherein, different collision risks correspond to different types of collision avoidance strategies, and the types of collision avoidance strategies include: an acceleration collision avoidance strategy, a braking collision avoidance strategy, a steering collision avoidance strategy, and a braking combined with steering collision avoidance strategy; the type of the candidate collision avoidance strategy corresponds to the collision risk, and the control parameters in different candidate collision avoidance strategies of the same type are different; the determination unit is further configured to determine the collision avoidance strategy to be executed by the vehicle from the plurality of candidate collision avoidance strategies based on the cost values of the respective candidate collision avoidance strategies; wherein, the cost value is determined according to the evaluation parameters corresponding to the candidate collision avoidance strategy; the evaluation parameters include at least one of the following: collision probability, maneuver intensity, comfort, and occupant injury value; the control unit is configured to control the vehicle to travel according to the collision avoidance strategy.

[0029] In a possible implementation manner, the determination unit is specifically configured to: perform weighted summation on each evaluation parameter corresponding to the candidate collision avoidance strategy to obtain the cost value of the candidate collision avoidance strategy.

[0030] In a possible implementation manner, the determination unit is further configured to: predict the collision information when a collision occurs between the vehicle and the collision avoidance object, where the collision information includes the collision position, collision angle, and collision speed; input the collision information into the occupant injury prediction model to obtain the occupant injury value.

[0031] In a possible implementation manner, the determination unit is specifically configured to: determine the latest collision avoidance time based on the motion information of the vehicle and the motion information of the collision avoidance object; in the case where the latest collision avoidance time is greater than a preset threshold, determine the collision risk as the first collision risk; or, in the case where the latest collision avoidance time is greater than or equal to 0 and less than or equal to the preset threshold, determine the collision risk as the second collision risk; or, in the case where the latest collision avoidance time is less than 0, determine the collision risk as the third collision risk.

[0032] In a possible implementation manner, the determination unit is specifically configured to: determine the latest steering time and the latest braking time based on the motion information of the vehicle and the motion information of the collision avoidance object; wherein, the latest steering time is the latest time to avoid a collision by a steering operation; the latest braking time is the latest time to avoid a collision by braking; determine the minimum value of the latest steering time and the latest braking time as the latest collision avoidance time.

[0033] In a possible implementation manner, the determination unit is further configured to: predict the collision time of a collision between the vehicle and the target object based on the motion information of the vehicle and the motion information of the target object; and determine the target object as a collision avoidance object when the collision time is less than a preset collision time threshold.

[0034] In a possible implementation manner, the control unit is specifically configured to: when the control parameter of the collision avoidance strategy includes the heading angular velocity, adjust the heading angular velocity of the vehicle based on the smooth transition strategy.

[0035] According to a third aspect provided by the present application, a vehicle is provided, including: a processor; and a memory for storing processor-executable instructions; wherein, the processor is configured to execute the instructions to implement the method according to the first aspect and any possible implementation manner thereof.

[0036] According to a fourth aspect provided by the present application, a computer-readable storage medium is provided. When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device can execute the method according to the first aspect and any possible implementation manner thereof.

[0037] According to a fifth aspect provided by the present application, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions run on the electronic device, the electronic device executes the method according to the first aspect and any possible implementation manner thereof.

[0038] It should be noted that the technical effects brought by any implementation manner in the second aspect to the fifth aspect can refer to the technical effects brought by the corresponding implementation manner in the first aspect, which will not be elaborated here.

[0039] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The accompanying drawings herein are incorporated into the specification and constitute a part of this specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application, and do not constitute an improper limitation to the present application.

[0041] Figure 1 is a schematic diagram showing the distribution of traffic accident forms according to an exemplary embodiment; Figure 2 is a distribution diagram of a side collision scene according to an exemplary embodiment; Figure 3 is a schematic structural diagram of a collision avoidance system according to an exemplary embodiment; Figure 4It is a flowchart of a collision avoidance method shown according to an exemplary embodiment; Figure 5 It is a schematic diagram of an application scenario of a braking obstacle avoidance strategy shown according to an exemplary embodiment; Figure 6 It is a schematic diagram of an application scenario of a steering obstacle avoidance strategy shown according to an exemplary embodiment; Figure 7 It is a schematic diagram of an application scenario of an acceleration obstacle avoidance strategy shown according to an exemplary embodiment; Figure 8 It is a schematic diagram of an application scenario of a collision avoidance strategy combining braking and steering shown according to an exemplary embodiment; Figure 9 It is a schematic diagram of an application scenario of another collision avoidance strategy combining braking and steering shown according to an exemplary embodiment; Figure 10 It is a schematic diagram of a collision risk determination process shown according to an exemplary embodiment; Figure 11 It is a schematic diagram of the structure of a collision avoidance device shown according to an exemplary embodiment; Figure 12 It is a schematic diagram of the structure of a trajectory prediction module shown according to an exemplary embodiment; Figure 13 It is a schematic diagram of the structure of a multi-strategy collision avoidance decision module shown according to an exemplary embodiment; Figure 14 It is a block diagram of a collision avoidance device shown according to an exemplary embodiment; Figure 15 It is a block diagram of an electronic device shown according to an exemplary embodiment; Figure 16 It is a block diagram of another electronic device shown according to an exemplary embodiment. Detailed implementation manners

[0042] In order to enable those of ordinary skill in the art to better understand the technical solutions of the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0043] It should be noted that the terms "first", "second", etc. in the description, claims and the above-mentioned drawings of this application are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of this application described here can be implemented in an order other than those illustrated or described here. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. On the contrary, they are merely examples of devices and methods consistent with some aspects of this application as detailed in the appended claims.

[0044] In the embodiments of this application, words such as "exemplary", "such as", or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "exemplary", "such as" or "for example" in the embodiments of this application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Rather, the use of words such as "exemplary", "such as" or "for example" is intended to present relevant concepts in a specific way.

[0045] First, the related technologies involved in this application are explained to facilitate the understanding of those skilled in the art.

[0046] Exemplarily, as Figure 1 shown, Figure 1 is a schematic diagram showing the distribution of traffic accident patterns according to an exemplary embodiment. Figure 1 It shows that among all traffic accident types, the probability of frontal collision is 3.27%, the probability of side collision is 37.81%, the probability of rear-end collision is 13.30%, the probability of same-direction rubbing is 1.51%, the probability of oncoming rubbing is 0.53%, the probability of other-angle collision is 14.86%, the probability of colliding with a stationary vehicle is 5.58%, the probability of collision between other vehicles is 0.51%, the probability of scraping a pedestrian is 5.25%, the probability of running over a pedestrian is 0.15%, the probability of running over a pedestrian after a collision is 0.16%, the probability of other collisions with pedestrians is 0.12%, the probability of rollover is 1.88%, the probability of tumbling is 0.17%, the probability of falling off a vehicle is 0.14%, the probability of fire is 0.02%, the probability of hitting a fixed object is 10.25%, the probability of hitting a non-fixed object is 1.10%, the probability of self-folding is 0.18%, the probability of an occupant falling or being thrown out is 0.08%, and the probability of others is 3.14%. Among them, the proportion of side collisions is particularly prominent, reaching 37.81%, which is one of the main patterns in traffic accidents.

[0047] Exemplarily, as Figure 2 shown, Figure 2It is a side collision scenario distribution diagram shown according to an exemplary embodiment. Among them, the probability of colliding with an object coming from the right is 27.55%, the probability of colliding with an object coming from the left is 24.49%, the probability of a vehicle turning left and colliding with an object coming from the opposite direction is 16.33%, the probability of a U-turn vehicle colliding with other vehicles is 7.14%, the probability of being rear-ended by a straight-ahead object from behind when changing lanes to the left (including when changing lanes) is 3.06%, the probability of colliding with an oncoming object when changing lanes to the left is 3.06%, the probability of a left-turn traffic accident is 2.04%, the probability of being rear-ended by a straight-ahead object from behind when changing lanes to the right (including when changing lanes) is 2.04%, the probability of encountering an oncoming object in the same lane is 2.04%, the probability of a vehicle turning right and colliding with an object coming from behind is 2.04%, the probability of a vehicle turning left and colliding with an object coming from behind is 2.04%, the probability of two vehicles turning simultaneously (in the same direction) and colliding is 2.04%, the probability of a collision when changing lanes to the left is 1.02%, the probability of colliding with a front object (the object changes lanes forcefully from the right) is 1.02%, the probability of colliding with a front object (the object changes lanes forcefully from the left) is 1.02%, the probability of colliding with an object when parking is 1.02%, the probability of a vehicle turning right and colliding with an object coming from the left is 1.02%, and the probability of a vehicle turning left and colliding with an object coming from the right is 1.02%.

[0048] Combined with Figure 2 , by deeply analyzing the scenarios of side collision accidents, it can be found that the vast majority of them occur at intersections, especially at crossroads. These areas have become high-incidence locations for side collision accidents due to factors such as complex traffic flows and limited visibility.

[0049] From the perspective of active safety technologies, although existing AEB systems and Advanced Emergency Steering Systems (AES) etc. have been widely applied in vehicles and effectively improved driving safety, the design and development of these systems often mainly focus on longitudinal driving scenarios, and their response capabilities for side collision risks in complex scenarios such as intersections are relatively limited. In intersection scenarios, due to large blind spots, it is often difficult for drivers to detect potential dangers in a timely manner, resulting in the fact that simple braking or steering measures are difficult to effectively avoid collisions.

[0050] From the perspective of passive safety technologies, side collisions pose a particularly serious threat to occupants. Compared with frontal collisions, the survival space for occupants during side collisions is much smaller, and the deformation and intrusion of the vehicle body side are more likely to cause injuries to occupants. However, the current solutions of passive safety technologies in this regard are still insufficient and difficult to provide sufficient protection.

[0051] The technical solutions in the embodiments of the present application will be 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, rather than all of the embodiments.

[0052] The collision avoidance method provided in the embodiment of the present application can be applied in a vehicle. A vehicle can also be referred to as a vehicle, a mobile carrier, an electric vehicle (EV), a hybrid electric vehicle (HEV), a plug-in hybrid electric vehicle (PHEV), a fuel cell vehicle (FCV), an autonomous vehicle, an intelligent and connected vehicle (ICV), a driverless vehicle, etc.

[0053] In the embodiments of the present application, the vehicle may be a sedan, a sport utility vehicle (SUV), a truck, an electric vehicle, a motorcycle, a tricycle, a special vehicle (such as an ambulance, a fire truck, a police car, etc.), an unmanned taxi, an intelligent networked bus, an automatic driving logistics vehicle, an electric truck, etc. In addition, the method is also applicable to various special vehicles, such as agricultural vehicles, mining vehicles, forestry vehicles, airport vehicles, port vehicles, etc. The present application does not impose specific restrictions on this.

[0054] For example, Figure 3 As shown, Figure 3 The collision avoidance system 300 may include a collision avoidance device 301 and a data acquisition device 302 .

[0055] Optionally, Figure 3 A communication connection can be established between the collision avoidance device 301 and the data acquisition device 302.

[0056] In practical applications, the collision avoidance device 301 may be communicatively connected to one or more data acquisition devices 302 .

[0057] For ease of understanding, the present application takes the communication connection between a collision avoidance device 301 and a data acquisition device 302 as an example for explanation.

[0058] Optionally, Figure 3 The collision avoidance device 301 and the data acquisition device 302 may be functional modules integrated into the same device, or may be devices independently arranged from each other. This application does not impose any limitation on this.

[0059] It is easy to understand that when the collision avoidance device 301 and the data acquisition device 302 are functional modules integrated in the same device, the communication method between the collision avoidance device 301 and the data acquisition device 302 is the communication between internal modules of the device. In this case, the communication process between the two is the same as the "communication process when the collision avoidance device 301 and the data acquisition device 302 are independently arranged".

[0060] For the sake of easy understanding, this application mainly takes the case where the collision avoidance device 301 and the data acquisition device 302 are independently arranged as an example for description.

[0061] Figure 3 The data acquisition device 302 in can collect the motion information of the vehicle and the motion information of the collision avoidance object, and send the motion information of the vehicle and the motion information of the collision avoidance object to the collision avoidance device 301. The collision avoidance device 301 can determine the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object, and then determine the collision avoidance strategy to be executed by the vehicle based on the collision risk, so as to further control the vehicle to drive according to the collision avoidance strategy.

[0062] Optionally, Figure 3 The collision avoidance device 301 in can be a terminal, a server, or other types of electronic devices. Figure 1 What is shown in is only an example of the device form of the collision avoidance device 301, and does not constitute a limitation thereto.

[0063] When the collision avoidance device 301 is a terminal, the terminal can be a device that provides voice and / or data connectivity to the user, a handheld device with wireless connection function, or other processing devices connected to a wireless modem. The terminal can communicate with one or more core networks via a radio access network (RAN). The terminal can be a mobile terminal, such as a computer with a mobile terminal, or a mobile device built into the collision avoidance system 300, which exchange languages and / or data with the wireless access network. For example, mobile phones, tablets, laptops, netbooks, personal digital assistants (PDAs). This application does not make any restrictions on this.

[0064] When the collision avoidance device 301 is a server, the server can be a single server, or, alternatively, a server cluster composed of multiple servers. In some embodiments, the server cluster can also be a distributed cluster. This application does not make any restrictions on this.

[0065] It should be noted that the structure illustrated in the embodiments of the present application does not limit the collision avoidance system 300. It may include more or fewer components than those shown, or combine certain components, or split certain components, or have different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0067] For ease of understanding, the collision avoidance method provided in the present application will be specifically introduced below with reference to the accompanying drawings.

[0068] Figure 4 is a flowchart of a collision avoidance method shown according to an exemplary embodiment. As Figure 4 shown, the collision avoidance method includes the following steps: S401 - S404.

[0069] S401. Based on the motion information of the vehicle and the motion information of the collision avoidance object, determine the collision risk between the vehicle and the collision avoidance object.

[0070] Among them, the motion information may include longitudinal speed, longitudinal acceleration, heading angle, heading angular velocity, coordinates in a two - dimensional plane, etc. The collision avoidance object can be used to represent a target object that may collide with the vehicle. The target object may include other vehicles, pedestrians, obstacles, etc. The collision risks are, from low to high, the first collision risk, the second collision risk, and the third collision risk.

[0071] In a possible implementation manner, the collision avoidance device can directly or indirectly obtain the motion information of the vehicle and the motion information of the collision avoidance object through vehicle sensors.

[0072] Exemplarily, the vehicle sensor can be an Advanced Driver Assistance Systems (ADAS).

[0073] In a possible implementation manner, in order to determine the collision avoidance object, the collision avoidance device can predict the collision time between the vehicle and the target object based on the motion information of the vehicle and the motion information of the target object. The collision avoidance device can determine the target object as the collision avoidance object when the collision time is less than a preset collision time threshold.

[0074] Specifically, the collision avoidance device can respectively construct kinematic models of the vehicle and the target object based on the motion information of the vehicle and the motion information of the target object. The collision avoidance device can perform trajectory prediction on the vehicle and the target object based on the kinematic models of the vehicle and the target object, and determine the motion information of the vehicle and the motion information of the target object at multiple moments within a first time period. The collision avoidance device can predict the collision time between the vehicle and the target object based on the motion information of the vehicle and the motion information of the target object at multiple moments within the first time period.

[0075] Among them, the first time period can be set as the time interval corresponding to the preset collision time threshold starting from the current moment and moving backward.

[0076] Optionally, the preset collision time threshold can be set according to actual needs. For example, the preset collision avoidance time threshold can be 2.6 seconds or 3 seconds. This application does not make specific restrictions on this.

[0077] Exemplarily, the motion information of the vehicle at the current moment satisfies the following first formula. First formula:

[0078] Among them, can be used to represent the state vector of the vehicle at the current moment, that is, the motion information of the vehicle at the current moment. 、 can be used to represent the coordinates of the vehicle in the two-dimensional plane at the current moment. can be used to represent the longitudinal speed of the vehicle at the current moment. can be used to represent the longitudinal acceleration of the vehicle at the current moment. can be used to represent the heading angle of the vehicle at the current moment. can be used to represent the heading angular velocity of the vehicle at the current moment.

[0079] The motion information of the target object at the current moment satisfies the following second formula. Second formula:

[0080] Among them, can be used to represent the state vector of the target object at the current moment, that is, the motion information of the target object at the current moment. 、 can be used to represent the coordinates of the target object in the two-dimensional plane at the current moment. can be used to represent the longitudinal speed of the target object at the current moment. can be used to represent the longitudinal acceleration of the target object at the current moment. can be used to represent the heading angle of the target object at the current moment. can be used to represent the heading angular velocity of the target object at the current moment.

[0081] Exemplarily, in the case where the kinematic models of the vehicle and the target object are both constant turn rate and acceleration motion models, the motion information of the vehicle at the k+1 moment within the first time period (similarly for the motion information of the target object) can satisfy the following third formula. Third formula:

[0082] Among them, It can be used to characterize the state vector of the vehicle at the current moment, that is, the motion information of the vehicle at the current moment. It can be as shown in the first formula above. It can be used to characterize the state vector of the vehicle at the k+1 moment, that is, the motion information of the vehicle at the k+1 moment. 、 It can be used to characterize the coordinates of the vehicle in the two-dimensional plane at the k+1 moment. It can be used to characterize the longitudinal speed of the vehicle at the k+1 moment. It can be used to characterize the longitudinal acceleration of the vehicle at the k+1 moment. It can be used to characterize the heading angle of the vehicle at the k+1 moment. It can be used to characterize the heading angular velocity of the vehicle at the k+1 moment.

[0083] In a possible implementation manner, after determining the collision avoidance object, the collision avoidance device can determine the latest collision avoidance moment based on the motion information of the vehicle and the motion information of the collision avoidance object. The collision avoidance device can determine the collision risk between the vehicle and the collision avoidance object based on the latest collision avoidance moment. The specific implementation manner of the collision avoidance device to determine the collision risk between the vehicle and the collision avoidance object can refer to the following S501-S504. Details are not described herein again.

[0084] S402. Determine multiple candidate collision avoidance strategies based on the collision risk.

[0085] Among them, different collision risks can correspond to different types of collision avoidance strategies. The types of collision avoidance strategies can include: acceleration collision avoidance strategy, braking collision avoidance strategy, steering collision avoidance strategy, and braking combined with steering collision avoidance strategy. The types of candidate collision avoidance strategies can correspond to the collision risk, and the control parameters in different candidate collision avoidance strategies of the same type are different. The first collision risk can correspond to the acceleration collision avoidance strategy or the braking collision avoidance strategy. The second collision risk can correspond to the braking collision avoidance strategy or the steering collision avoidance strategy. The third collision risk can correspond to the braking combined with steering collision avoidance strategy.

[0086] Exemplarily, when the candidate collision avoidance strategy is the acceleration collision avoidance strategy, the control parameter can be the acceleration. When the candidate collision avoidance strategy is the braking collision avoidance strategy, the control parameter can be the deceleration. When the candidate collision avoidance strategy is the steering collision avoidance strategy, the control parameter can be the heading angular velocity. When the candidate collision avoidance strategy is the braking combined with steering collision avoidance strategy, the control parameters can be the heading angular velocity and the deceleration.

[0087] In a possible implementation manner, the goal of the braking collision avoidance strategy is to reduce the vehicle speed, increase the safety distance, and reduce the collision kinetic energy between the vehicle and the collision avoidance object. The braking deceleration corresponding to the braking collision avoidance strategy can satisfy the following fourth formula. Fourth formula:

[0088] Among them, can be used to characterize the braking deceleration corresponding to the braking collision avoidance strategy. can be used to characterize the deceleration distance, that is, the distance between the vehicle and the collision avoidance object. can be used to characterize the maximum braking deceleration that the vehicle can provide. V safe can be used to characterize the desired safe speed, such as 0. V can be used to characterize the relative speed between the vehicle and the collision avoidance object.

[0089] Exemplarily, as Figure 5 shown, Figure 5 the vehicle in only avoids collision by braking, and the collision avoidance object keeps going straight.

[0090] In a possible implementation manner, the goal of the steering collision avoidance strategy is to avoid the collision avoidance object by changing the driving direction of the vehicle. For example, if the collision avoidance object comes from the left, the vehicle turns right; if the collision avoidance object comes from the right, the vehicle turns left to better avoid the collision avoidance object. Even if the collision cannot be completely avoided, the collision angle can be changed to transform the standard large-angle side collision accident form into a small-angle side scrape, so as to reduce the loss and the injury to the occupants as much as possible. The minimum turning radius corresponding to the steering collision avoidance strategy satisfies the following fifth formula. Fifth formula:

[0091] Among them, can be used to characterize the minimum turning radius corresponding to the steering collision avoidance strategy. a lat_max can be used to characterize the maximum lateral acceleration allowed by the vehicle. V e can be used to characterize the speed of the vehicle.

[0092] Based on the fifth formula, the heading angular velocity corresponding to the steering collision avoidance strategy satisfies the following sixth formula. Sixth formula:

[0093] Among them, can be used to characterize the heading angular velocity corresponding to the steering collision avoidance strategy. can be used to characterize the minimum turning radius corresponding to the steering collision avoidance strategy. V e can be used to characterize the speed of the vehicle. can be used to characterize the weight of the vehicle. can be used to characterize the wheelbase of the vehicle. can be used to characterize the distance from the center of mass of the vehicle to the front axle. can be used to characterize the distance from the center of mass of the vehicle to the rear axle. can be used to characterize the effective cornering stiffness of the vehicle. It can be used to characterize the cornering stiffness of the front wheels of a vehicle. It can be used to characterize the cornering stiffness of the rear wheels of a vehicle.

[0094] In a possible implementation, considering the physical limits of the vehicle, it is necessary to limit the heading angular velocity corresponding to the steering collision avoidance strategy. The limited heading angular velocity satisfies the following seventh formula. Seventh formula:

[0095] Wherein, It can be used to characterize the heading angular velocity corresponding to the steering collision avoidance strategy. It can be used to characterize the minimum allowable heading angular velocity of the vehicle. It can be used to characterize the maximum allowable heading angular velocity of the vehicle.

[0096] In a possible implementation, based on the seventh formula, the heading angular velocity can be limited within { }, that is, the heading angular velocity cannot be less than , and cannot be greater than .

[0097] Exemplarily, as Figure 6 shown, Figure 6 the vehicle in

[0098] In a possible implementation, the goal of the acceleration collision avoidance strategy is that when it is detected that the collision avoidance object is far away and the vehicle speed is low, the vehicle accelerates in a timely manner through the potential collision area. The maximum longitudinal acceleration of the vehicle satisfies the following eighth formula. Eighth formula:

[0099] Wherein, a a_max It can be used to characterize the maximum longitudinal acceleration of the vehicle. It can be used to characterize the desired longitudinal vehicle speed of the acceleration collision avoidance strategy. V can be used to characterize the relative speed between the vehicle and the collision avoidance object. It can be used to characterize the distance that needs to be accelerated across, such as 5 m. a accel_max It can be used to characterize the maximum braking acceleration of the vehicle, such as 5 m / s 2 .

[0100] Exemplarily, as Figure 7 shown, Figure 7 the vehicle in

[0101] In a possible implementation, the collision avoidance strategy that combines braking and steering requires collision attitude optimization to minimize the damage to the occupants at the moment of collision in terms of the collision position and collision angle. The collision attitude optimization objective of the collision avoidance strategy that combines braking and steering satisfies the following ninth formula. Ninth formula:

[0102] Wherein, I can be used to represent the occupant damage prediction model. pos can be used to represent the collision position. angle can be used to represent the collision angle. can be used to represent the speed of the vehicle. can be used to represent the speed of the collision avoidance object. can be used to represent the constraint range within which the vehicle can steer in the current state, that is, the constraint range of the vehicle's heading angular velocity. can be used to represent the constraint space within which the vehicle can brake in the current state, that is, the constraint range of the vehicle's deceleration.

[0103] Exemplarily, as Figure 8 shown, Figure 8 in the vehicle, through the collision avoidance strategy that combines braking and steering, the inevitable collision is transformed into a graze, reducing the collision angle and the force direction between the vehicle and the collision avoidance object, and reducing the damage to the occupants in the vehicle and the collision avoidance object.

[0104] Exemplarily, as Figure 9 shown, Figure 9 in the vehicle, through the collision avoidance strategy that combines braking and steering, the inevitable collision where the collision avoidance object is directly facing the vehicle occupants is transformed into the collision avoidance object hitting the right rear wing of the vehicle, making the force direction of the vehicle away from the occupants, and reducing the damage to the occupants in the vehicle and the collision avoidance object.

[0105] S403. Determine the collision avoidance strategy to be executed by the vehicle from multiple candidate collision avoidance strategies based on the respective cost values of the multiple candidate collision avoidance strategies.

[0106] In a possible implementation, the collision avoidance device can determine the respective cost values of multiple candidate collision avoidance strategies.

[0107] Wherein, the cost value can be used to reflect the cost that may be brought about by executing the candidate collision avoidance strategy. The cost value can be determined according to the evaluation parameters corresponding to the candidate collision avoidance strategy. For the specific implementation of the collision avoidance device to determine the respective cost values of multiple candidate collision avoidance strategies, reference can be made to S601 - S602 below. Details are not elaborated here.

[0108] In a possible implementation, the collision avoidance device can, based on the respective cost values of multiple candidate collision avoidance strategies, determine the candidate collision avoidance strategy with the lowest cost value among the multiple candidate collision avoidance strategies as the collision avoidance strategy to be executed by the vehicle.

[0109] Exemplarily, multiple candidate collision avoidance strategies are all steering collision avoidance strategies. The steering paths corresponding to different steering collision avoidance strategies are different. The collision avoidance device can calculate the cost value corresponding to each steering collision avoidance strategy. The collision avoidance device can determine the steering collision avoidance strategy with the lowest cost value as the collision avoidance strategy to be executed by the vehicle.

[0110] Exemplarily, in the case where the collision risk is the third collision risk, the collision avoidance device can be based on the heading angular velocity constraint range and the deceleration constraint range

[0111] to determine multiple collision avoidance strategies combining braking and steering. The steering and braking paths corresponding to different collision avoidance strategies combining braking and steering are different. The collision avoidance device can calculate the cost value corresponding to each collision avoidance strategy combining braking and steering. The collision avoidance device can use the collision avoidance strategy combining braking and steering with the smallest cost value as the collision avoidance strategy to be executed by the vehicle.

[0112] In a possible implementation manner, when the control parameter of the collision avoidance strategy includes the heading angular velocity, the collision avoidance device can adjust the heading angular velocity of the vehicle based on the smooth transition strategy.

[0113] Among them, the smooth transition strategy can include gradually adjusting the current heading angular velocity to the heading angular velocity of the collision avoidance strategy through a smooth transition function.

[0114] Exemplarily, the smooth transition function can satisfy the following tenth formula. Tenth formula:

[0115] Among them, can be used to characterize the control quantity of the heading angular acceleration at time t. can be used to characterize the control quantity of the heading angular acceleration at time t + 1. can be used to characterize the smooth weight factor, which decreases exponentially. can be used to characterize the heading angle at time t. can be used for the time interval, that is, the time interval between time t + 1 and time t. τ is the smooth time constant (for example, 0.5 seconds).

[0116] Based on this, the present application makes the heading angular velocity change gradually through the smooth transition strategy, enabling the steering system of the vehicle to have sufficient time to adapt and adjust, ensuring the vehicle remains stable during the steering process, and reducing the possibility of losing control.

[0117] Based on the above technical solutions, the present application can continuously monitor the motion information of the vehicle and the collision avoidance object, evaluate the collision risk in real time, and select the most appropriate collision avoidance strategy according to different collision risks, such as accelerating collision avoidance, braking collision avoidance, steering collision avoidance, or a collision avoidance strategy combining braking and steering. This flexible collision avoidance strategy enables the vehicle to handle various complex traffic scenarios and improve the success rate of collision avoidance.

[0118] In some embodiments, in order to determine the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object, the collision avoidance method provided by the embodiments of the present application further includes the following steps: S501 - S504.

[0119] S501. Based on the motion information of the vehicle and the motion information of the collision avoidance object, determine the latest collision avoidance moment.

[0120] Among them, the latest collision avoidance moment can be the minimum value of the latest steering moment and the latest braking moment. The latest steering moment can be the latest moment to avoid collision through a steering operation. The latest braking moment can be the latest moment to avoid collision through braking. The latest steering moment and the latest braking moment can be determined based on the motion information of the vehicle and the motion information of the collision avoidance object.

[0121] In a possible implementation manner, the latest collision avoidance moment can also be the sum of the minimum value of the latest steering moment and the latest braking moment and the time compensation.

[0122] Among them, the time compensation can be used to include transmission delay, calculation delay, and execution delay. The transmission delay can be the time required for the collision avoidance device to collect motion information to start calculating the latest collision avoidance moment. The calculation delay can be the time required for the collision avoidance device to start calculating the latest collision avoidance moment to the completion of the calculation. The execution delay can be the time required for the collision avoidance device to complete the calculation to start executing the collision avoidance strategy.

[0123] Exemplarily, the transmission delay is 0.1 second, the calculation delay is 0.2 second, and the execution delay is 0.1 second. The collision avoidance device can determine the time compensation to be 0.6 seconds. In a possible implementation manner, the collision avoidance device can determine the relative speed and relative distance between the vehicle and the collision avoidance object at multiple future moments. The collision avoidance device can determine the collision time at multiple future moments based on the relative speed and relative distance between the vehicle and the collision avoidance object at multiple future moments to determine the relative distance corresponding to the minimum collision time and the minimum relative time. The collision avoidance device can determine the latest braking moment and the latest steering moment based on the relative distance corresponding to the minimum collision time and the minimum relative time.

[0124] In an example, the relative speed between the vehicle and the collision avoidance object at the k moment satisfies the following Eleventh Formula. Eleventh Formula:

[0125] It can satisfy the following Twelfth Formula. Twelfth Formula:

[0126] It can satisfy the following Thirteenth Formula. Thirteenth Formula:

[0127] Among them, in the Eleventh Formula to the Thirteenth Formula, can be used to characterize the relative speed between the vehicle and the collision avoidance object at time k. can be used to characterize the relative speed in the horizontal (X) direction between the vehicle and the collision avoidance object in the two-dimensional plane at time k. can be used to characterize the relative speed in the vertical (Y) direction between the vehicle and the collision avoidance object in the two-dimensional plane at time k. can be used to characterize the longitudinal speed of the collision avoidance object at time k. can be used to characterize the longitudinal speed of the vehicle at time k. can be used to characterize the heading angle of the collision avoidance object at time k. can be used to characterize the heading angle of the vehicle at time k.

[0128] In yet another example, the relative distance between the vehicle and the collision avoidance object at time k satisfies the following Fourteenth Formula. Fourteenth Formula:

[0129] Among them, can be used to characterize the relative distance between the vehicle and the collision avoidance object at time k. can be used to characterize the relative position in the X direction between the vehicle and the collision avoidance object in the two-dimensional plane at time k. can be used to characterize the relative position in the Y direction between the vehicle and the collision avoidance object in the two-dimensional plane at time k.

[0130] In a possible implementation manner, the time to collision at time k can be the ratio of the relative distance between the vehicle and the collision avoidance object at time k to the relative speed between the vehicle and the collision avoidance object at time k. Based on the Thirteenth Formula and the Fourteenth Formula, it can be determined that the time to collision at time k satisfies the following Fifteenth Formula. Fifteenth Formula:

[0131] Among them, can be used to characterize the determination of the time to collision at time k. can be used to characterize the relative distance between the vehicle and the collision avoidance object at time k. can be used to characterize the relative speed between the vehicle and the collision avoidance object at time k.

[0132] In a possible implementation manner, based on the fifteenth formula, the minimum collision time can be determined to satisfy the following sixteenth formula. Sixteenth formula:

[0133] wherein, can be used to represent the minimum collision time among multiple future moments. can be used to represent the collision time at the k-th moment, and the value of k is .

[0134] The relative distance corresponding to the minimum collision time satisfies the following seventeenth formula. Seventeenth formula:

[0135] wherein, can be used to represent the relative distance between the vehicle and the collision avoidance object at the k-th moment. can be used to represent the minimum collision distance among multiple future moments, that is, the relative distance corresponding to the minimum collision time.

[0136] In a possible implementation manner, the latest braking moment satisfies the following eighteenth formula. Eighteenth formula:

[0137] wherein, can be used to represent the latest braking moment. can be used to represent the minimum collision time. can be used to represent the braking duration. can be used to represent the maximum braking deceleration of the vehicle. ) can be used to represent the speed of the vehicle at the current moment.

[0138] Optionally, the maximum braking deceleration can be set according to actual requirements. For example, the maximum braking speed can be 10 meters per second squared (m / s 2 ), or it can be 8 m / s 2 . This application does not make specific limitations on this.

[0139] The latest steering moment satisfies the following nineteenth formula. Nineteenth formula:

[0140] wherein, can be used to represent the latest steering moment. can be used to represent the minimum collision time. can be used to represent the safety distance between the vehicle and the collision avoidance object. a lat_max can be used to represent the maximum lateral acceleration of the vehicle.

[0141] Optionally, the safety distance between the vehicle and the collision avoidance object can be set according to actual requirements. For example, it can be 2 meters or 3 meters. This application does not make specific restrictions on this.

[0142] Optionally, the maximum lateral acceleration can be set according to actual requirements. For example, the maximum lateral acceleration can be 5 m / s 2 , or it can be 4 m / s 2 . This application does not make specific restrictions on this.

[0143] Based on the eighteenth formula and the nineteenth formula, the latest collision avoidance time satisfies the following twentieth formula:

[0144] wherein, can be used to represent the latest collision avoidance time. can be used to represent the latest braking time. can be used to represent the latest steering time.

[0145] S502. When the latest collision avoidance time is greater than the preset threshold, determine that the collision risk is the first collision risk.

[0146] Optionally, the preset threshold can be set according to actual requirements. For example, the preset threshold can be 2.6 seconds or 3 seconds. This application does not make specific restrictions on this.

[0147] S503. When the latest collision avoidance time is greater than or equal to 0 and less than or equal to the preset threshold, determine that the collision risk is the second collision risk.

[0148] S504. When the latest collision avoidance time is less than 0, determine that the collision risk is the third collision risk.

[0149] In a possible implementation manner, when the latest collision avoidance time is less than 0, the collision between the vehicle and the collision avoidance object is inevitable, and it is necessary to minimize the cost of the collision.

[0150] Based on this, this application can calculate the latest collision avoidance time by comprehensively considering the motion information (such as speed, acceleration, position, etc.) of the vehicle and the collision avoidance object, that is, the latest time point when the vehicle takes collision avoidance measures to avoid collision, so as to determine the collision risk according to the latest collision avoidance time, and further adopt appropriate collision avoidance strategies for different risk levels to improve the success rate of collision avoidance and reduce the occurrence of collisions.

[0151] In some embodiments, in order to determine the cost values of multiple candidate collision avoidance strategies, the collision avoidance method provided by the embodiments of this application further includes the following steps: S601-S602.

[0152] S601. Determine the evaluation parameters corresponding to the candidate collision avoidance strategies.

[0153] Among them, the evaluation parameters include at least one of the following: collision probability, maneuver intensity, comfort level, and occupant injury value. The collision probability can be used to characterize the probability of the vehicle colliding with the collision avoidance object. The maneuver intensity can be used to characterize the severity of the transient change in the dynamic state of the vehicle when executing the collision avoidance strategy, that is, the stability of the vehicle when executing the collision avoidance strategy. The higher the maneuver intensity, the closer the vehicle is to the dynamic stability limit, and the greater the risk of instability. The comfort level can be used to characterize the comfort level of the vehicle occupants when executing the candidate collision avoidance strategy. The occupant injury value is used to characterize the degree of physical injury that the occupants may suffer when executing the candidate collision avoidance strategy.

[0154] In a possible implementation manner, the collision avoidance device can determine the collision probability based on the calculated minimum collision time and minimum relative distance at the current moment. The collision probability satisfies the following twenty-first formula. Twenty-first formula:

[0155] Among them, can be used to characterize the collision probability corresponding to the i-th candidate collision avoidance strategy. can be used to characterize the minimum collision distance at the current moment. can be used to characterize the minimum collision time at the current moment. can be used to characterize the weight corresponding to the minimum collision distance. can be used to characterize the weight corresponding to the minimum collision time. can be used to characterize the distance threshold. can be used to characterize the time threshold.

[0156] Optionally, the distance threshold can be set according to actual needs. For example, the distance threshold can be 5 meters or 6 meters. This application does not make specific restrictions on this.

[0157] Optionally, the time threshold can be set according to actual needs. For example, the time threshold can be 2 seconds or 1 second. This application does not make specific restrictions on this.

[0158] Optionally, and can be set according to actual needs. For example, and can be 0.7 and 0.3 respectively, or can be 0.5 and 0.5 respectively. This application does not make specific restrictions on this.

[0159] In a possible implementation, the collision avoidance device can determine the maneuver intensity based on the longitudinal acceleration and the lateral heading angular velocity of the vehicle. The maneuver intensity can satisfy the following twenty-second formula. Twenty-second formula:

[0160] where, can be used to represent the maneuver intensity corresponding to the i-th candidate collision avoidance strategy. can be used to represent the longitudinal acceleration in the i-th candidate collision avoidance strategy. can be used to represent the lateral heading angular acceleration in the i-th candidate collision avoidance strategy. can be used to represent the maximum longitudinal acceleration of the vehicle. can be used to represent the maximum heading angular velocity of the vehicle. and The larger the value of, the more unstable the vehicle is. can be used to represent the weight corresponding to the longitudinal acceleration of the vehicle. can be used to represent the weight corresponding to the lateral heading angular velocity of the vehicle.

[0161] Optionally, and can be set according to actual needs. For example, and can be 0.6 and 0.4 respectively, or can be 0.8 and 0.2 respectively. This application does not make specific restrictions on this.

[0162] In a possible implementation, the collision avoidance device can determine the comfort level based on the acceleration and angular acceleration of the vehicle. The comfort level satisfies the following twenty-third formula. Twenty-third formula:

[0163] where, can be used to represent the comfort level corresponding to the i-th candidate collision avoidance strategy. can be used to represent the jerk in the i-th candidate collision avoidance strategy, that is, the rate of change of acceleration with time in the i-th candidate collision avoidance strategy. can be used to represent the angular acceleration in the i-th candidate collision avoidance strategy. can be used for the maximum angular acceleration of the vehicle. can be used to represent the maximum jerk of the vehicle. and can be determined by calibration. and The larger the value of, the worse the comfort level. can be used to represent the weight corresponding to the longitudinal acceleration of the vehicle. can be used to represent the weight corresponding to the angular acceleration.

[0164] Optionally, and can be set according to actual requirements. For example, and can be 0.6 and 0.4 respectively, or can be 0.9 and 0.1 respectively. This application does not make specific restrictions on this.

[0165] Satisfy the following twenty-fourth formula. Twenty-fourth formula:

[0166] Wherein, can be used to characterize the angular acceleration in the i-th candidate collision avoidance strategy. is the change rate of the angular velocity in the i-th candidate collision avoidance strategy. can be used to characterize the time interval.

[0167] Satisfy the following twenty-fifth formula. Twenty-fifth formula:

[0168] Wherein, can be used to characterize the jerk in the i-th candidate collision avoidance strategy, that is, the change rate of the acceleration with time in the i-th candidate collision avoidance strategy. can be used to characterize the change rate of the jerk in the i-th candidate collision avoidance strategy. can be used to characterize the time interval.

[0169] In a possible implementation manner, the collision avoidance device can predict the collision information when a collision occurs between the vehicle and the collision avoidance object. The collision avoidance device can input the collision information into the occupant injury prediction model to obtain the occupant injury value.

[0170] Wherein, the collision information includes the collision position, collision angle, and collision speed. The collision speed can be the relative speed between the vehicle and the collision avoidance object. The occupant injury prediction model can be obtained by training according to a training set. The training set can include the occupant injury value and the input sample corresponding to the occupant injury value. The input sample can include: the collision position, collision angle, and collision speed.

[0171] Optionally, the training set can be obtained according to finite element simulation or can be measured parameters. This application does not make specific restrictions on this.

[0172] In a possible implementation manner, the collision avoidance device can update the model parameters of the initial prediction model multiple times until the updated initial prediction model meets the preset conditions to obtain the occupant injury prediction model.

[0173] Among them, in the process of each update, the input sample is input into the initial prediction model to obtain the predicted centroid sideslip angle; based on the difference between the predicted centroid sideslip angle and the centroid sideslip angle of the first sample, the model parameters of the initial prediction model are updated.

[0174] S602. Determine the cost value of the candidate collision avoidance strategy based on the evaluation parameters corresponding to the candidate collision avoidance strategy.

[0175] In a possible implementation manner, a weighted sum is performed on each evaluation parameter corresponding to the candidate collision avoidance strategy to obtain the cost value of the candidate collision avoidance strategy. Each evaluation parameter corresponding to the candidate collision avoidance strategy and the cost value of the candidate collision avoidance strategy satisfy the following twenty-fifth formula. Twenty-sixth formula:

[0176] Among them, can be used to represent the cost value of the i-th candidate collision avoidance strategy. can be used to represent the collision probability of the i-th candidate collision avoidance strategy. can be used to represent the maneuver intensity corresponding to the i-th candidate obstacle avoidance strategy. can be used to represent the comfort corresponding to the i-th candidate collision avoidance strategy. can be used to represent the occupant damage value corresponding to the i-th candidate obstacle avoidance strategy. can be used to represent the weight of the collision probability. can be used to represent the weight of the maneuver intensity. can be used to represent the weight of the comfort. can be used to represent the weight of the occupant damage value.

[0177] Optionally, 、 、 and can be set according to actual needs. For example, 、 、 、 can be 0.3, 0.1, 0.1, 0.5 respectively, or can be 0.4, 0.05, 0.05, 0.5. This application does not make specific restrictions on this.

[0178] Based on the above technical solutions, this application can comprehensively evaluate the advantages and disadvantages of candidate collision avoidance strategies from multiple dimensions by introducing multiple evaluation parameters such as collision probability, maneuver intensity, comfort, and occupant damage value, ensuring that the selected strategy can reach a better level in multiple aspects, thereby improving the success rate of collision avoidance.

[0179] In some embodiments, as Figure 10 shown, Figure 10It is a schematic diagram of a collision risk determination process shown according to an exemplary embodiment.

[0180] In a possible implementation manner, the collision avoidance device can calculate the time to collision. The collision avoidance device can determine the latest braking moment and the latest steering moment when the time to collision is less than a preset time to collision threshold; otherwise, calculate the time to collision. The collision avoidance device can determine the minimum value of the latest braking moment and the latest steering moment as the latest collision avoidance moment. The collision avoidance device can determine the collision risk as the first collision risk when the latest collision avoidance moment is greater than a preset threshold. The collision avoidance device can determine the collision risk as the second collision risk when the latest collision avoidance moment is greater than or equal to 0 and less than or equal to the preset threshold. The collision avoidance device can determine the collision risk as the third collision risk when the latest collision avoidance moment is less than 0.

[0181] Among them, the first collision risk corresponds to an acceleration collision avoidance strategy or a braking collision avoidance strategy. The second collision risk corresponds to a braking collision avoidance strategy or a steering collision avoidance strategy. The third collision risk corresponds to a braking combined with steering collision avoidance strategy.

[0182] The above mainly introduces the solution provided by the embodiments of the present application from the perspective of the method. To implement the above functions, the collision avoidance device or the electronic device includes the corresponding hardware structure and / or software module for executing each function. Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraint conditions of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0183] The embodiments of the present application can, according to the above method, exemplarily divide the functions of the collision avoidance device or the electronic device. For example, the collision avoidance device or the electronic device can include each functional module corresponding to each function division, or two or more functions can be integrated into one processing module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. It should be noted that the division of modules in the embodiments of the present application is schematic, only a logical function division, and there can be other division methods in actual implementation.

[0184] In some embodiments, as Figure 11 shown, Figure 11 It is a schematic structural diagram of a collision avoidance device shown according to an exemplary embodiment. The collision avoidance device includes a data acquisition module, a trajectory prediction module, a collision risk assessment module, a multi-strategy collision avoidance decision module, and a control execution module.

[0185] In a possible implementation, the data acquisition module can be used to acquire the motion information of the vehicle and the motion information of the collision avoidance object.

[0186] The trajectory prediction module can be used to predict the motion trajectory of the vehicle based on the motion information of the vehicle, and predict the motion trajectory of the collision avoidance object according to the motion information of the collision avoidance object.

[0187] The collision risk assessment module can be used to determine the collision risk between the vehicle and the collision avoidance object based on the motion trajectory of the vehicle and the motion trajectory of the collision avoidance object.

[0188] The multi-strategy collision avoidance decision-making module can be used to determine the collision avoidance strategy to be executed by the vehicle based on the collision risk.

[0189] The control execution module can be used to control the vehicle to drive according to the collision avoidance strategy.

[0190] It should be noted that for the specific implementation manners of the data acquisition module, the trajectory prediction module, the collision risk assessment module, the multi-strategy collision avoidance decision-making module, and the control execution module, reference can be made to the above S401-S404. Details are not described herein again.

[0191] In some embodiments, as Figure 12 shown, Figure 12 FIG. is a schematic structural diagram of a trajectory prediction module shown according to an exemplary embodiment. The trajectory prediction module may include a kinematic prediction unit and a collision form determination unit.

[0192] In a possible implementation, the kinematic prediction unit can be used to simplify the motions of the vehicle and the collision avoidance object into a kinematic model, and perform trajectory prediction based on the motion information of the vehicle and the collision avoidance object at the current moment.

[0193] The collision form determination unit can be used to calculate the collision position, collision angle, vehicle speed, and collision avoidance object speed between the vehicle and the collision avoidance object at a future moment.

[0194] In some embodiments, as Figure 13 shown, Figure 13 FIG. is a schematic structural diagram of a multi-strategy collision avoidance decision-making module shown according to an exemplary embodiment. The multi-strategy collision avoidance decision-making module may include a strategy generation module and a cost value calculation module.

[0195] In a possible implementation, the strategy generation module can be used to generate candidate collision avoidance strategies based on the predicted trajectory.

[0196] In a possible implementation manner, the cost value calculation module may include a collision probability calculation unit, a comfort calculation unit, a maneuver intensity calculation unit, and an occupant injury calculation unit. The collision probability calculation unit may be used to calculate the cost value corresponding to the collision probability. The comfort calculation unit may be used to calculate the cost value corresponding to the comfort. The maneuver intensity calculation unit may be used to calculate the cost value corresponding to the maneuver intensity. The occupant injury calculation unit may be used to calculate the cost value corresponding to the occupant injury.

[0197] Figure 14 is a block diagram of a collision avoidance device shown according to an exemplary embodiment. Referring to Figure 14 , the collision avoidance device includes: a determination unit 1401 and a control unit 1402.

[0198] In a possible implementation manner, the determination unit 1401 is configured to determine the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object.

[0199] In a possible implementation manner, the determination unit 1401 is further configured to determine a plurality of candidate collision avoidance strategies based on the collision risk.

[0200] In a possible implementation manner, the determination unit 1401 is further configured to determine the collision avoidance strategy to be executed by the vehicle from the plurality of candidate collision avoidance strategies based on the cost values of the respective candidate collision avoidance strategies.

[0201] In a possible implementation manner, the control unit 1402 is configured to control the vehicle to travel according to the collision avoidance strategy.

[0202] In a possible implementation manner, the determination unit 1401 is specifically configured to: perform weighted summation on each evaluation parameter corresponding to the candidate collision avoidance strategy to obtain the cost value of the candidate collision avoidance strategy In a possible implementation manner, the determination unit 1401 is further configured to: predict the collision information when a collision occurs between the vehicle and the collision avoidance object. Input the collision information into the occupant injury prediction model to obtain the occupant injury value.

[0203] In a possible implementation manner, the determination unit 1401 is specifically configured to: determine the latest collision avoidance moment based on the motion information of the vehicle and the motion information of the collision avoidance object. In the case where the latest collision avoidance moment is greater than the preset threshold, determine the collision risk as the first collision risk. Or, in the case where the latest collision avoidance moment is greater than or equal to 0 and less than or equal to the preset threshold, determine the collision risk as the second collision risk. Or, in the case where the latest collision avoidance moment is less than 0, determine the collision risk as the third collision risk.

[0204] In a possible implementation manner, the determining unit 1401 is specifically configured to: determine the latest steering moment and the latest braking moment based on the motion information of the vehicle and the motion information of the collision avoidance object. Determine the minimum value of the latest steering moment and the latest braking moment as the latest collision avoidance moment.

[0205] In a possible implementation manner, the determining unit 1401 is further configured to: predict the collision time when a collision occurs between the vehicle and the target object based on the motion information of the vehicle and the motion information of the target object. In the case where the collision time is less than a preset collision time threshold, determine the target object as the collision avoidance object.

[0206] In a possible implementation manner, the control unit 1402 is specifically configured to: when the control parameter of the collision avoidance strategy includes the heading angular velocity, adjust the heading angular velocity of the vehicle based on the smooth transition strategy.

[0207] Regarding the device in the above embodiments, the specific manners in which each module performs operations have been described in detail in the embodiments related to the method, and will not be elaborated herein.

[0208] Figure 15 is a block diagram of an electronic device shown according to an exemplary embodiment. As Figure 15 shown, the electronic device includes, but is not limited to: a processor 1501 and a memory 1502.

[0209] Among them, the above-mentioned memory 1502 is used to store the executable instructions of the above-mentioned processor 1501. It can be understood that the above-mentioned processor 1501 is configured to execute instructions to implement the collision avoidance method in the above embodiments.

[0210] It should be noted that those skilled in the art can understand that Figure 15 the structure of the electronic device shown in Figure 15 does not constitute a limitation on the electronic device, and the electronic device may include more or fewer components than

[0211] The processor 1501 is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and circuits. By running or executing software programs and / or modules stored in the memory 1502, and by invoking the data stored in the memory 1502, it executes various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 1501 may include one or more processing units. Optionally, the processor 1501 may integrate an application processor and a modem processor. Among them, the application processor mainly processes the operating system, user interface, application programs, etc., and the modem processor mainly processes wireless communication. It can be understood that the above-mentioned modem processor may not be integrated into the processor 1501 either.

[0212] The memory 1502 can be used to store software programs and various data. The memory 1502 mainly includes a program storage area and a data storage area. Among them, the program storage area can store the operating system, application programs required by at least one functional module (such as a determination unit, a processing unit, etc.). In addition, the memory 1502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0213] In an exemplary embodiment, there is also provided a computer-readable storage medium including instructions, such as the memory 1502 including instructions. The above instructions can be executed by the processor 1501 of the electronic device 1500 to implement the method in the above embodiment.

[0214] In actual implementation, Figure 14 the functions of the determination unit 1401 and the control unit 1402 in Figure 15 can be implemented by the processor 1501 in

[0215] calling the computer program stored in the memory 1502. The specific execution process can refer to the description of the method part in the above embodiment, and will not be elaborated here.

[0216] In an exemplary embodiment, the embodiment of the present application also provides a computer program product including one or more instructions. The one or more instructions can be executed by the processor 1501 of the electronic device to complete the method in the above embodiment.

[0217] It should be noted that when one or more instructions in the above-mentioned computer-readable storage medium or in the computer program product are executed by the processor of the electronic device, the various processes of the above method embodiments are implemented, and the same technical effects as the above method can be achieved. To avoid repetition, it will not be elaborated here.

[0218] Through the description of the above embodiments, those skilled in the art can clearly understand that for the convenience and conciseness of description, only the above division of each functional module is used as an example. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0219] In several embodiments provided in the present application, it should be understood that the disclosed device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms.

[0220] The units described as separate components may or may not be physically separated. The components displayed as units may be one physical unit or multiple physical units, that is, they can be located in one place, or they can be distributed to multiple different places. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0221] In addition, in each embodiment of the present application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0222] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution can be embodied in the form of a software product. The software product is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, a chip, etc.) or a processor to execute all or part of the steps of the methods of the various embodiments of the present application. The aforementioned storage medium includes: USB flash drives, mobile hard disks, ROM, RAM, magnetic disks, optical discs, and other media that can store program codes.

[0223] In some embodiments, as Figure 16 shown, Figure 16 is a block diagram of another electronic device shown according to an exemplary embodiment. The electronic device includes a CAN bus, a processor, a storage device, and a communication interface. The processor is used to provide computing power and control capabilities, and can be a Graphics Processing Unit (GPU), a Central Processing Unit (CPU), a Neural Processing Unit (NPU), a Microcontroller Unit (MCU), a Field Programmable Gate Array (FPGA), etc. The storage device includes a memory module and a non-volatile storage medium. The non-volatile storage medium stores a computer program for implementing the above method. The memory module provides an environment for the program to start and run. The communication interface is used for wired or wireless communication with an external terminal.

[0224] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A collision avoidance method, characterized in that: The method comprises: Determining a collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object; Based on the collision risk, a plurality of candidate collision avoidance strategies are determined; wherein different collision risks correspond to different types of collision avoidance strategies, and the types of collision avoidance strategies include: acceleration collision avoidance strategy, braking collision avoidance strategy, steering collision avoidance strategy, and braking combined with steering collision avoidance strategy; the types of the candidate collision avoidance strategies correspond to the collision risks, and the control parameters of different candidate collision avoidance strategies of the same type are different; Based on the cost values ​​of the multiple candidate collision avoidance strategies, determine the collision avoidance strategy to be executed by the vehicle from the multiple candidate collision avoidance strategies; wherein the cost value is determined according to the evaluation parameters corresponding to the candidate collision avoidance strategies; the evaluation parameters include at least one of the following: collision probability, maneuverability, comfort, and occupant injury value; The vehicle is controlled to travel according to the collision avoidance strategy.

2. The method according to claim 1, characterized in that The collision risks are, from low to high, first collision risk, second collision risk and third collision risk; The first collision risk corresponds to the acceleration collision avoidance strategy or the braking collision avoidance strategy; The second collision risk corresponds to the braking collision avoidance strategy or the steering collision avoidance strategy; The third collision risk corresponds to the collision avoidance strategy of combining braking with steering.

3. The method according to claim 2, characterized in that When the candidate collision avoidance strategy is an acceleration collision avoidance strategy, the control parameter is acceleration; In the case where the candidate collision avoidance strategy is a braking collision avoidance strategy, the control parameter is a deceleration; In the case where the candidate collision avoidance strategy is a steering collision avoidance strategy, the control parameter is a heading angular velocity; When the candidate collision avoidance strategy is a braking combined with steering collision avoidance strategy, the control parameters are the heading angular velocity and the deceleration.

4. The method according to claim 1, characterized in that: The cost value of the candidate collision avoidance strategy is determined by: A weighted sum is performed on the evaluation parameters corresponding to the candidate collision avoidance strategy to obtain a cost value of the candidate collision avoidance strategy.

5. The method according to claim 1, characterized in that The collision probability is determined according to the minimum collision time and the minimum relative distance calculated at the current moment.

6. The method according to claim 1, characterized in that The maneuver intensity is determined based on the longitudinal acceleration and the lateral heading angular velocity.

7. The method according to claim 1, characterized in that The comfort level is determined based on jerk and angular acceleration.

8. The method according to claim 1, characterized in that The occupant damage value is determined in the following manner: Predicting collision information when a collision occurs between the vehicle and the collision avoidance object, the collision information including a collision position, a collision angle, and a collision speed; The collision information is input into an occupant injury prediction model to obtain the occupant injury value.

9. The method according to claim 2, characterized in that: The determining the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object comprises: Determining a latest collision avoidance time based on the motion information of the vehicle and the motion information of the collision avoidance object; When the latest collision avoidance time is greater than a preset threshold, determining the collision risk as a first collision risk; or, When the latest collision avoidance time is greater than or equal to 0 and less than or equal to a preset threshold, determining the collision risk as a second collision risk; or, When the latest collision avoidance time is less than 0, the collision risk is determined to be the third collision risk.

10. The method according to claim 9, characterized in that The determining of the latest collision avoidance time based on the motion information of the vehicle and the motion information of the collision avoidance object comprises: Based on the motion information of the vehicle and the motion information of the collision avoidance object, determining the latest turning time and the latest braking time; wherein the latest turning time is the latest time to avoid a collision by steering operation; the latest braking time is the latest time to avoid a collision by braking; A minimum value between the latest steering time and the latest braking time is determined as the latest collision avoidance time.

11. The method according to claim 1, characterized in that: Before determining the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object, the method includes: Predicting a collision time between the vehicle and the target object based on the motion information of the vehicle and the motion information of the target object; When the collision time is less than a preset collision time threshold, the target object is determined as the collision avoidance object.

12. The method according to claim 1, characterized in that The controlling the vehicle to travel according to the collision avoidance strategy includes: In a case where the control parameters of the collision avoidance strategy include the heading angular velocity, the heading angular velocity of the vehicle is adjusted based on a smooth transition strategy.

13. A collision avoidance device, characterized in that: The device comprises: a determination unit and a control unit; The determining unit is used to determine the collision risk between the vehicle and the collision avoidance object based on the motion information of the vehicle and the motion information of the collision avoidance object; The determination unit is further used to determine a plurality of candidate collision avoidance strategies based on the collision risk; wherein different collision risks correspond to different types of collision avoidance strategies, and the types of collision avoidance strategies include: acceleration collision avoidance strategy, braking collision avoidance strategy, steering collision avoidance strategy, and braking combined with steering collision avoidance strategy; the types of the candidate collision avoidance strategies correspond to the collision risks, and the control parameters of different candidate collision avoidance strategies of the same type are different; The determination unit is further configured to determine the collision avoidance strategy to be executed by the vehicle from the plurality of candidate collision avoidance strategies based on the cost values ​​of the plurality of candidate collision avoidance strategies; wherein the cost value is determined according to evaluation parameters corresponding to the candidate collision avoidance strategies; the evaluation parameters include at least one of the following: collision probability, maneuverability, comfort, and occupant injury value; The control unit is used to control the vehicle to travel according to the collision avoidance strategy.

14. A vehicle, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 12.

Images