Vehicle braking obstacle avoidance method, device and electronic equipment

Abstract

The present application provides a vehicle braking obstacle avoidance method, device and electronic equipment, which relates to the field of autonomous driving technology, including: predicting the minimum expected collision time between the vehicle and an obstacle with a collision risk at the current time node according to the vehicle's driving parameters; comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine the current collision risk level; determining the target braking strategy to be adopted at the current time node according to the current collision risk level, driving parameters, the historical braking strategy adopted at the previous time node and the driver's intervention status; controlling the vehicle to brake and avoid obstacles according to the target braking strategy. In this way, the braking deceleration is comprehensively determined by the collision risk level, driving parameters, the historical optimal braking strategy and the driver's intervention status, which can avoid the expected acceleration oscillation during braking, improve the comfort of the passenger compartment and the braking safety during braking, and improve the braking effect.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a vehicle braking obstacle avoidance method, device and electronic equipment. Background Art

[0002] Traffic safety issues have attracted widespread attention from the society, and how to reduce or avoid traffic accidents has become the focus of automotive technology research. In terms of autonomous driving technology, the vehicle's automatic emergency braking and obstacle avoidance system can effectively reduce the occurrence of accidental collisions.

[0003] At present, the existing braking obstacle avoidance algorithm has large fluctuations in braking deceleration during the braking obstacle avoidance process, poor riding comfort during the braking process, and difficulty in ensuring braking safety on curves. At the same time, the drastic changes in braking deceleration make it difficult and error-prone for the vehicle to follow the acceleration, reducing the collision avoidance effect. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a vehicle braking obstacle avoidance method, device and electronic equipment, which comprehensively determines the braking strategy to be adopted at the current time node through collision risk level, driving parameters, historical braking strategy adopted at the previous time node and driver intervention status, and can avoid expected acceleration oscillations during braking, improve passenger compartment comfort and braking safety during braking, and improve braking effect.

[0005] The present application provides a vehicle braking obstacle avoidance method, the method comprising:

[0006] Predicting, based on the driving parameters of the vehicle, a minimum expected collision time between the vehicle and an obstacle with a collision risk at a current time node;

[0007] Comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine the current collision risk level;

[0008] Determining a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state;

[0009] The vehicle is controlled to perform braking and obstacle avoidance according to the target braking strategy.

[0010] Further, according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node and the driver intervention state, determining the target braking strategy to be adopted at the current time node includes:

[0011] determining an obstacle avoidance state signal according to the current collision risk level and the driver intervention state;

[0012] If it is determined that the obstacle avoidance state signal indicates that the emergency braking obstacle avoidance function is turned on, determining the target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters and the historical braking strategy;

[0013] If it is determined that the obstacle avoidance state signal indicates that the emergency braking obstacle avoidance function is turned off, the target braking strategy is determined to be no braking.

[0014] Further, determining an obstacle avoidance state signal according to the current collision risk level and the driver intervention state includes:

[0015] When the driver intervention state is that the driver actively intervenes in obstacle avoidance and / or the vehicle travel speed is less than a preset threshold, determining that the obstacle avoidance state signal is a state signal indicating that an emergency braking obstacle avoidance function is turned off;

[0016] When the driver intervention status is that the driver does not actively intervene in obstacle avoidance, the obstacle avoidance status signal is determined to be a status signal indicating that the emergency braking obstacle avoidance function is turned on according to the current collision risk level; the status signal indicating that the emergency braking obstacle avoidance function is turned on includes: an obstacle avoidance function turn-on preparation signal, an obstacle avoidance warning signal, a comfort braking signal and an emergency braking signal.

[0017] Furthermore, the method further comprises:

[0018] When the obstacle avoidance status signal is the obstacle avoidance warning signal, the comfort braking signal or the emergency braking signal, and the strength of the obstacle avoidance warning signal is determined according to the current collision risk level, so as to control the warning device in the vehicle to issue a warning according to the strength of the obstacle avoidance warning signal.

[0019] Furthermore, the method further includes determining that the driver intervention state is the driver actively intervening in obstacle avoidance by any of the following methods:

[0020] In response to a configuration operation for an emergency braking obstacle avoidance function mode, when the emergency braking obstacle avoidance function is turned off, determining that the driver intervention state is a driver actively intervening in obstacle avoidance;

[0021] When the steering wheel angle is greater than a preset angle threshold, or the steering wheel angular velocity is greater than a preset angular velocity threshold, the emergency braking obstacle avoidance function is turned off, and the driver intervention state is determined to be the driver's active intervention obstacle avoidance;

[0022] When the turn signal lamp or the hazard warning flasher lamp is turned on, the emergency braking obstacle avoidance function is turned off, and the driver intervention state is determined to be the driver's active intervention obstacle avoidance.

[0023] Further, the driving parameters include a current relative speed between the vehicle and the obstacle corresponding to the minimum expected collision time and a current deceleration of the vehicle;

[0024] Determining a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, and the historical braking strategy adopted at the previous time node, including:

[0025] When the current collision risk level is no collision risk, if the current relative vehicle speed is less than or equal to 0, the target braking strategy is determined to be no braking; if the relative vehicle speed is greater than 0, the historical braking strategy is determined to be the target braking strategy;

[0026] When the current collision risk level is that there is a slight collision risk, determining the historical braking strategy as the target braking strategy;

[0027] When the current collision risk level is that there is a moderate collision risk, the historical braking strategy is upgraded to obtain the target braking strategy; wherein the strategy upgrade method includes: if the historical braking strategy is no braking, the comfort braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is greater than or equal to the braking deceleration corresponding to the comfort braking strategy, the emergency braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is less than the braking deceleration corresponding to the comfort braking strategy, the historical braking strategy is determined as the target braking strategy; if the historical braking strategy is the emergency braking strategy, the emergency braking strategy is determined as the target braking strategy;

[0028] When the current collision risk level indicates that there is a severe collision risk, an emergency braking strategy is determined as the target braking strategy.

[0029] Further, each expected collision time threshold preset under different braking strategies includes at least one of the following items: the expected collision time threshold corresponding to the braking warning strategy is the warning collision time threshold; the expected collision time threshold corresponding to the comfort braking strategy is the comfort braking collision time threshold; the expected collision time threshold corresponding to the emergency braking strategy is the emergency braking collision time threshold;

[0030] Comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine the current collision risk level includes:

[0031] When the minimum expected collision time is less than 0 or greater than the warning collision time threshold, determining the current collision risk level as no collision risk;

[0032] When the minimum expected collision time is greater than or equal to the comfort braking collision time threshold and less than the warning collision time threshold, determining that the current collision risk level is a slight collision risk;

[0033] When the minimum expected collision time is greater than or equal to the emergency braking collision time threshold and less than the comfort braking collision time threshold, determining that the current collision risk level is a moderate collision risk;

[0034] When the minimum expected collision time is greater than or equal to 0 and less than the emergency braking collision time threshold, it is determined that the current collision risk level is that there is a severe collision risk.

[0035] Furthermore, predicting the minimum expected collision time between the vehicle and an obstacle with a collision risk based on the driving parameters of the vehicle includes:

[0036] Predicting a driving trajectory of the vehicle according to driving parameters of the vehicle; wherein the driving trajectory includes a plurality of trajectory points;

[0037] Based on the sensors installed in the vehicle, the obstacles around the vehicle are identified to form an original obstacle list;

[0038] Taking the driving trajectory as the center, expanding the lateral search range of obstacles;

[0039] Filtering the original obstacle list to obtain a first obstacle list according to the lateral search range and the lateral coordinates of each obstacle in the original obstacle list;

[0040] Based on a bounding box algorithm, a geometric collision check is performed on each obstacle in the first obstacle list and the vehicle, and a target obstacle with a collision risk with the vehicle is identified;

[0041] For each target obstacle, determining whether the target obstacle is in front of the vehicle based on the driving parameters of the vehicle;

[0042] If the target obstacle is in front of the vehicle, determining an expected collision time between the vehicle and the target obstacle;

[0043] The minimum expected collision time is determined from the expected collision times corresponding to each target obstacle.

[0044] The present application also provides a vehicle braking obstacle avoidance device, the device comprising:

[0045] A prediction module, used to predict the minimum expected collision time between the vehicle and an obstacle with a collision risk at a current time node based on the driving parameters of the vehicle;

[0046] A comparison module, used for comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine a current collision risk level;

[0047] A determination module, configured to determine a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state;

[0048] A control module is used to control the vehicle to brake and avoid obstacles according to the target braking strategy.

[0049] An embodiment of the present application also provides an electronic device, including: a processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and when the machine-readable instructions are executed by the processor, the steps of the vehicle braking obstacle avoidance method as described above are performed.

[0050] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the vehicle braking obstacle avoidance method as described above are executed.

[0051] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0053] Figure 1 One of the flow charts of a vehicle braking obstacle avoidance method provided in an embodiment of the present application is shown;

[0054] Figure 2 A schematic diagram showing a search range for obstacles provided in an embodiment of the present application;

[0055] Figure 3 A second flowchart of a vehicle braking obstacle avoidance method provided in an embodiment of the present application is shown;

[0056] Figure 4 A schematic structural diagram of a vehicle braking obstacle avoidance device provided in an embodiment of the present application is shown;

[0057] Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0058] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. The components of the embodiments of the present application usually described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, each other embodiment obtained by those skilled in the art without making creative work belongs to the scope of protection of the present application.

[0059] Research has found that traffic safety issues have attracted widespread attention from the society, and how to reduce or avoid traffic accidents has become the focus of automotive technology research. In terms of autonomous driving technology, the vehicle's automatic emergency braking and obstacle avoidance system can effectively reduce the occurrence of accidental collisions.

[0060] At present, the existing braking obstacle avoidance algorithm has large fluctuations in braking deceleration during the braking obstacle avoidance process, poor riding comfort during the braking process, and difficulty in ensuring braking safety on curves. At the same time, the drastic changes in braking deceleration make it difficult and error-prone for the vehicle to follow the acceleration, reducing the collision avoidance effect.

[0061] Based on this, an embodiment of the present application provides a vehicle braking obstacle avoidance method to avoid expected acceleration oscillations during braking, improve passenger cabin comfort and braking safety during braking, and improve braking effect.

[0062] See also Figure 1 , Figure 1 This is one of the flow charts of a vehicle braking obstacle avoidance method provided in an embodiment of the present application. The braking obstacle avoidance method provided in an embodiment of the present application can be applied to a vehicle-mounted controller. Optionally, the embodiment of the present application adopts a hierarchical control method, in which the upper-layer controller performs target obstacle identification and obstacle avoidance decisions based on the information of the vehicle and obstacles obtained by the perception layer, and the lower-layer controller performs braking control on the vehicle based on the expected deceleration information output by the upper-layer controller to achieve obstacle avoidance.

[0063] like Figure 1 As shown in , the braking obstacle avoidance method includes:

[0064] S101. Predicting, based on driving parameters of a vehicle, a minimum expected collision time between the vehicle and an obstacle with a collision risk at a current time node.

[0065] In this step, the vehicle's driving parameters may include the vehicle's current position, longitudinal speed, heading angle, heading angular velocity, etc.; based on the driving parameters, a series of vehicle trajectory points can be predicted to form a driving trajectory, and then obstacles with potential collision risks with the vehicle can be determined based on the driving trajectory, and the minimum expected collision time between the vehicle and the obstacle can be determined. Among them, the expected collision time (Time To Collision, TTC) refers to the time required for the vehicle to collide with the obstacle in front when the current speed and direction remain unchanged. The minimum expected collision time refers to the shortest time required for the vehicle to collide with each obstacle in front. The minimum expected collision time can be used to measure the risk of collision of the vehicle and the most dangerous obstacle at the moment.

[0066] In a possible implementation, step S101 may include:

[0067] S1011. Predicting a driving trajectory of the vehicle based on the driving parameters of the vehicle.

[0068] It should be noted that when the vehicle speed is low (such as less than 0.1 km / h), the vehicle is considered stationary and no braking is continued, so no trajectory prediction is performed. When the vehicle has a certain speed, the position of the vehicle's trajectory point after the next time interval can be predicted based on the current driving parameters, and a predicted driving trajectory is formed through multiple trajectory points. For example, the following formula can be used to predict the first point in the vehicle's driving trajectory: Track points:

[0069]

[0070] In the formula, and Respectively represent the horizontal and vertical coordinates of the current trajectory point; and Respectively represent the longitudinal velocity and yaw rate of the vehicle at the current trajectory point; Indicates the preset trajectory prediction time interval; Indicates the heading angle of the current track point.

[0071] On the other hand, the length of the driving trajectory predicted backward at each time node in the embodiment of the present application has certain limitations. Specifically, the length of the predicted trajectory is limited by the preset time length of the trajectory prediction, such as 1.5s; in order to ensure sufficient longitudinal space for braking, the predicted trajectory length is also limited by the minimum generated path length, and the minimum path generated length is the longitudinal distance required for the vehicle to stop in an emergency at the current speed; if the predicted trajectory length is less than the minimum generated path length, it will continue to expand. The length of the predicted driving trajectory needs to meet both the time length limit and the minimum generated path length limit.

[0072] S1012: Based on sensors mounted on the vehicle, obstacles around the vehicle are identified to form an original obstacle list.

[0073] In this step, various sensors on the vehicle, such as LiDAR and surround view cameras, will continuously scan obstacles around the vehicle to form an original obstacle list. The scanned obstacles include obstacles in all directions around the vehicle. The original obstacle list records the point location information or point cloud location information of each obstacle.

[0074] S1013: Expand a lateral search range for obstacles with the driving trajectory as the center.

[0075] See also Figure 2 , Figure 2 A schematic diagram of a lateral search range for obstacles provided in an embodiment of the present application. Figure 2 As shown in the figure, with the predicted vehicle's driving trajectory as the center, a lateral search range is established along the lateral offset by a certain distance, that is, the range formed by the straight lines where the two dotted lines are located, so as to ignore obstacles in the original obstacle list whose reference points are outside the lateral search area.

[0076] S1014: Filter the original obstacle list to obtain a first obstacle list according to the lateral search range and the lateral coordinates of each obstacle in the original obstacle list.

[0077] In specific implementation, the lateral distance between any obstacle and the driving track can be determined based on the lateral coordinates of the obstacle; if the lateral distance exceeds the lateral search range, such as ±5m, the obstacle is determined to be out of the lateral search range and removed from the original obstacle list. In this way, the first obstacle list can be initially filtered.

[0078] S1015: Perform a geometric collision check on each obstacle in the first obstacle list and the vehicle based on a bounding box algorithm, and identify target obstacles that have a collision risk with the vehicle.

[0079] In this step, a bounding box of the main vehicle at each predicted trajectory point is generated based on the vehicle size information based on the bounding box algorithm, the main vehicle is regarded as a rectangular frame, the coordinates of the four vertices of the projection surface are calculated, and a convex polygon of the main vehicle outer contour is formed; then, a geometric collision check is performed on each obstacle in the first obstacle list and the main vehicle, obstacles with a risk of collision with the main vehicle are identified, and added to the target obstacle list.

[0080] In this way, through the combination of two filtering steps, the target obstacles that pose a risk of collision with the main vehicle can be accurately identified from the obstacle information in the perception layer, and a target obstacle list can be generated.

[0081] S1016. For each target obstacle, determine whether the target obstacle is in front of the vehicle based on the driving parameters of the vehicle.

[0082] It should be noted that the obstacle that needs to be considered when performing braking and obstacle avoidance should be located in front of the vehicle. In this step, it can be first determined whether the target obstacle is in front of the vehicle based on the heading angle, horizontal and vertical coordinates of the vehicle at the current time node and the horizontal and vertical coordinates of the target obstacle. In one example, when the heading angle is in the first and second quadrants, if the difference between the horizontal coordinate obtained by subtracting the horizontal coordinate of the vehicle from the horizontal coordinate of the target obstacle is greater than 0, then the target obstacle is determined to be in front of the vehicle; when the heading angle is in the third and fourth quadrants, if the difference between the horizontal coordinate obtained by subtracting the horizontal coordinate of the vehicle from the horizontal coordinate of the target obstacle is greater than 0, then the target obstacle is determined to be in front of the vehicle; when the heading angle coincides with the positive half axis of the y-axis, if the difference between the horizontal coordinate obtained by subtracting the horizontal coordinate of the vehicle from the horizontal coordinate of the target obstacle is greater than 0, then the target obstacle is determined to be in front of the vehicle; when the heading angle coincides with the negative half axis of the y-axis, if the difference between the horizontal coordinate obtained by subtracting the horizontal coordinate of the vehicle from the horizontal coordinate of the target obstacle is less than 0, then the target obstacle is determined to be in front of the vehicle.

[0083] S1017: If the target obstacle is in front of the vehicle, determine an expected collision time between the vehicle and the target obstacle.

[0084] S1018: Determine the minimum expected collision time from the expected collision times corresponding to each target obstacle.

[0085] With respect to steps S1017 and S1018, the expected collision time TTC between the host vehicle and the obstacle ahead is calculated, and the minimum expected collision time TTCmin among the expected collision times between the host vehicle and all obstacles is determined.

[0086] S102: Compare the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine a current collision risk level.

[0087] Specifically, the expected collision time thresholds preset under different braking strategies include at least one of the following items: the expected collision time threshold corresponding to the braking warning strategy is the warning collision time threshold; the expected collision time threshold corresponding to the comfort braking strategy is the comfort braking collision time threshold; the expected collision time threshold corresponding to the emergency braking strategy is the emergency braking collision time threshold.

[0088] In a possible implementation, step S102 may include:

[0089] When the minimum expected collision time is less than 0 or greater than the warning collision time threshold, it is determined that the current collision risk level is no collision risk, riskLevel=0.

[0090] When the minimum expected collision time is greater than or equal to the comfort braking collision time threshold and less than the warning collision time threshold, it is determined that the current collision risk level is a slight collision risk, riskLevel=1.

[0091] When the minimum expected collision time is greater than or equal to the emergency braking collision time threshold and less than the comfort braking collision time threshold, it is determined that the current collision risk level is a moderate collision risk, riskLevel=2.

[0092] When the minimum expected collision time is greater than or equal to 0 and less than the emergency braking collision time threshold, it is determined that the current collision risk level is a severe collision risk, riskLevel=3.

[0093] S103: Determine a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state.

[0094] In a possible implementation, step S103 may include:

[0095] S1031. Determine an obstacle avoidance state signal according to the current collision risk level and the driver intervention state.

[0096] In specific implementation, step S1031 may include:

[0097] Case 1: When the driver intervention state is that the driver actively intervenes in obstacle avoidance and / or the vehicle speed is less than a preset threshold (the vehicle speed is low, such as less than 0.1 km / h), it is determined that the obstacle avoidance state signal is a state signal indicating that the emergency braking obstacle avoidance function is turned off, that is, stateControl=0.

[0098] Case 2: when the driver intervention state is that the driver does not actively intervene in obstacle avoidance, the obstacle avoidance state signal is determined to be a state signal indicating that the emergency braking obstacle avoidance function is turned on according to the current collision risk level.

[0099] Among them, the state signal indicating that the emergency braking obstacle avoidance function is turned on includes: obstacle avoidance function turn-on preparation signal, obstacle avoidance warning signal, comfort braking and emergency braking signal. Specifically, the current collision risk level riskLevel=0, the obstacle avoidance state signal is the obstacle avoidance function turn-on preparation signal, that is, stateControl=Standby; the current collision risk level riskLevel=1, the obstacle avoidance state signal is the obstacle avoidance warning signal, that is, stateControl=Warning1; the current collision risk level riskLevel=2, the obstacle avoidance state signal is the comfort braking signal, that is, stateControl=Warning2; the front collision risk level riskLevel=3, the obstacle avoidance state signal is the emergency braking signal, that is, stateControl=Warning3.

[0100] The driver intervention state may be determined as the driver actively intervening in obstacle avoidance by any of the following methods:

[0101] Method 1: In response to the configuration operation for the emergency braking obstacle avoidance function mode, the emergency braking obstacle avoidance function is turned off, and the driver intervention state is determined to be the driver actively intervening in obstacle avoidance.

[0102] Here, the driver can pre-configure the emergency braking obstacle avoidance function mode through the application on the vehicle side, the physical buttons set in the vehicle, etc., such as turning on or off the automatic emergency obstacle avoidance function; when the automatic emergency braking obstacle avoidance function is turned off through the configuration operation, the driver intervention status is determined to be the driver actively intervenes in obstacle avoidance.

[0103] Method 2: When the steering wheel angle is greater than a preset angle threshold, or the steering wheel angular velocity is greater than a preset angular velocity threshold, the emergency braking obstacle avoidance function is turned off, and the driver intervention state is determined to be the driver's active intervention obstacle avoidance.

[0104] Autonomous driving vehicles are sometimes equipped with drivers. When the driver turns at a large angle (steering wheel angle is greater than a preset angle threshold, such as 30 degrees) or turns the steering wheel suddenly (steering wheel angular velocity is greater than a preset angular velocity threshold, such as 20 degrees per second), the emergency braking obstacle avoidance function is turned off, the driver intervention status is determined to be the driver actively intervening in obstacle avoidance, and the emergency braking obstacle avoidance function is turned off; when the driver's active intervention in obstacle avoidance ends, the emergency braking obstacle avoidance function is automatically restored.

[0105] Method three: when the turn signal or the hazard warning flasher is turned on, the emergency braking obstacle avoidance function is turned off, and the driver intervention state is determined to be the driver's active intervention obstacle avoidance.

[0106] When the driver turns on the turn signal to prepare for a turn or the hazard warning flashers, the driver intervention state is determined to be the driver actively intervening in obstacle avoidance, and the emergency braking obstacle avoidance function is turned off; when the turn signal or the hazard warning flashers are turned off, the emergency braking obstacle avoidance function is automatically restored.

[0107] S1032: If it is determined that the obstacle avoidance status signal indicates that the emergency braking obstacle avoidance function is turned on, determine the target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters and the historical braking strategy.

[0108] In this step, when the emergency braking obstacle avoidance function is turned on, through semi-empirical hierarchical control decision-making, based on the current collision risk level riskLevel, driving parameters, historical braking strategies, and combined with the subjective experience of human drivers, the optimal target braking strategy for the current host vehicle can be determined.

[0109] The driving parameters include a current relative speed between the vehicle and the obstacle corresponding to the minimum expected collision time and a current deceleration of the vehicle.

[0110] In specific implementation, step S1032 may include:

[0111] When the current collision risk level is no collision risk, if the current relative vehicle speed is less than or equal to 0, the target braking strategy is determined to be no braking; if the relative vehicle speed is greater than 0, the historical braking strategy is determined to be the target braking strategy.

[0112] When the current collision risk level indicates that there is a slight collision risk, the historical optimal braking strategy is determined as the target braking strategy.

[0113] When the current collision risk level is that there is a moderate collision risk, the historical braking strategy is upgraded to obtain the target braking strategy; wherein, the strategy upgrade method includes: if the historical braking strategy is no braking, the comfort braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is greater than or equal to the braking deceleration corresponding to the comfort braking strategy, the emergency braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is less than the braking deceleration corresponding to the comfort braking strategy, the historical braking strategy is determined as the target braking strategy; if the historical braking strategy is the emergency braking strategy, the emergency braking strategy is determined as the target braking strategy.

[0114] When the current collision risk level indicates that there is a severe collision risk, an emergency braking strategy is determined as the target braking strategy.

[0115] In this way, by combining historical braking strategies to determine the current target braking strategy of the main vehicle, acceleration oscillation can be avoided and the comfort of the passenger compartment and braking safety during braking can be improved. At the same time, if the braking effect is judged to be poor, the braking strategy can be upgraded in time to achieve the purpose of improving the braking effect.

[0116] S1033: If it is determined that the obstacle avoidance state signal indicates that the emergency braking obstacle avoidance function is turned off, the target braking strategy is determined to be no braking.

[0117] Furthermore, the method further comprises:

[0118] When the obstacle avoidance status signal is the obstacle avoidance warning signal, the comfort braking signal or the emergency braking signal, an obstacle avoidance warning signal is generated, and the strength of the obstacle avoidance warning signal is determined according to the current collision risk level, so as to control the warning device in the vehicle to issue a warning according to the strength of the obstacle avoidance warning signal.

[0119] Among them, when the status signal is "obstacle avoidance function is ready to start", although the obstacle avoidance function has been turned on, that is, the obstacle avoidance preparation is ready, there is no collision risk for the time being, so no obstacle avoidance warning signal is generated; when the status signal is "obstacle avoidance warning", "comfort braking" and "emergency braking", there is already a collision risk, so an obstacle avoidance warning signal needs to be generated to provide warning prompts in an intuitive and perceptible way. Warning equipment includes players, lights and vibration buttons in the car. The warning equipment uses sound, light and vibration to warn users of obstacle avoidance. The greater the intensity of the obstacle avoidance warning signal, the greater the intensity of the warning, such as louder volume, more eye-catching lights and stronger vibrations.

[0120] S104: Control the vehicle to perform braking to avoid obstacles according to the target braking strategy.

[0121] In this step, there is a mapping relationship between the braking strategy and the braking deceleration. For example, the comfort braking strategy corresponds to a braking deceleration of -4, and the emergency braking strategy corresponds to a braking deceleration of -8. Therefore, after obtaining the target braking strategy, it can be mapped to the target braking deceleration, and then the underlying controller controls the accelerator pedal opening and the brake pedal opening according to the target braking deceleration through the PID algorithm to control the vehicle to brake and avoid obstacles.

[0122] A vehicle braking obstacle avoidance method provided in an embodiment of the present application takes the subjective experience of the human driver into consideration in the decision-making process, effectively avoiding the expected acceleration oscillation during the hierarchical control emergency obstacle avoidance process, improving the passenger compartment comfort and braking safety during the braking process, and improving the collision avoidance effect; the initial vehicle speed for effective collision avoidance can be increased by reasonably adjusting the algorithm parameters.

[0123] See also Figure 3 , Figure 3This is a second flow chart of a vehicle braking obstacle avoidance method provided in an embodiment of the present application. The braking obstacle avoidance method is used to control the main vehicle to brake to achieve the purpose of obstacle avoidance, such as Figure 3 As shown in , the method includes:

[0124] The trajectory of the main vehicle is predicted from the current trajectory point position to generate the main vehicle predicted trajectory; the main vehicle bounding box of the main vehicle outer contour convex polygon is generated according to the bounding box algorithm; according to the main vehicle predicted trajectory, the target obstacles existing in the surrounding area identified by the onboard sensor are roughly filtered to obtain a target obstacle list; the target obstacles in the target obstacle list are collided according to the main vehicle bounding box, and the target obstacle list with collision risk is finely filtered, and the minimum expected collision time TTCmin is determined; the collision risk level is evaluated according to the minimum expected collision time to determine the current collision risk level; on the one hand, according to the risk level, the optimal braking strategy of the current main vehicle can be determined through semi-empirical hierarchical control decision; on the other hand, according to the current collision risk level and the driver intervention state, the obstacle avoidance state control is performed to determine the obstacle avoidance state signal; then, the obstacle avoidance state signal and the current optimal braking strategy of the main vehicle are combined, and then the obstacle avoidance action is controlled to obtain the current target braking strategy to be adopted; the vehicle is braked by adjusting the accelerator pedal opening and the brake pedal opening through the PID algorithm according to the expected deceleration corresponding to the target braking strategy; in addition, an obstacle avoidance warning signal is generated according to the obstacle avoidance state signal for warning. The lower-level controller adjusts the accelerator pedal opening and the brake pedal opening through the PID algorithm according to the expected deceleration corresponding to the target braking strategy to control the vehicle braking.

[0125] See also Figure 4 , Figure 4 This is a schematic diagram of the structure of a vehicle braking obstacle avoidance device provided in an embodiment of the present application. Figure 4 As shown in , the braking obstacle avoidance device 300 includes:

[0126] A prediction module 310, configured to predict a minimum expected collision time between the vehicle and an obstacle with a collision risk at a current time point according to the driving parameters of the vehicle;

[0127] A comparison module 320, for comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine a current collision risk level;

[0128] A determination module 330, configured to determine a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state;

[0129] The control module 340 is used to control the vehicle to brake and avoid obstacles according to the target braking strategy.

[0130] See also Figure 5 , Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. Figure 5 As shown in , the electronic device 400 includes a processor 410 , a memory 420 and a bus 430 .

[0131] The memory 420 stores machine-readable instructions executable by the processor 410. When the electronic device 400 is running, the processor 410 communicates with the memory 420 via the bus 430. When the machine-readable instructions are executed by the processor 410, the above-mentioned Figure 1 The specific implementation of the steps of the vehicle braking obstacle avoidance method in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0132] The present application also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the computer program can execute the above-mentioned Figure 1 The specific implementation of the steps of the vehicle braking obstacle avoidance method in the method embodiment shown can be found in the method embodiment, which will not be repeated here.

[0133] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0134] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0135] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0136] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0137] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0138] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A vehicle braking obstacle avoidance method, characterized in that: The method comprises: Predicting, based on the driving parameters of the vehicle, a minimum expected collision time between the vehicle and an obstacle with a collision risk at a current time node; Comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine the current collision risk level; Determining a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state; Controlling the vehicle to perform braking obstacle avoidance according to the target braking deceleration mapped by the target braking strategy; Determining a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state, including: determining an obstacle avoidance state signal according to the current collision risk level and the driver intervention state; If it is determined that the obstacle avoidance state signal indicates that the emergency braking obstacle avoidance function is turned on, determining the target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters and the historical braking strategy; The driving parameters include a current relative speed between the vehicle and the obstacle corresponding to the minimum expected collision time and a current deceleration of the vehicle; Determining a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, and the historical braking strategy adopted at the previous time node, including: When the current collision risk level is no collision risk, if the current relative vehicle speed is less than or equal to 0, the target braking strategy is determined to be no braking; if the relative vehicle speed is greater than 0, the historical braking strategy is determined to be the target braking strategy; When the current collision risk level is that there is a slight collision risk, determining the historical braking strategy as the target braking strategy; When the current collision risk level is that there is a moderate collision risk, the historical braking strategy is upgraded to obtain the target braking strategy; wherein the strategy upgrade method includes: if the historical braking strategy is no braking, the comfort braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is greater than or equal to the braking deceleration corresponding to the comfort braking strategy, the emergency braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is less than the braking deceleration corresponding to the comfort braking strategy, the historical braking strategy is determined as the target braking strategy; if the historical braking strategy is the emergency braking strategy, the emergency braking strategy is determined as the target braking strategy; When the current collision risk level is that there is a severe collision risk, determining the emergency braking strategy as the target braking strategy; Predicting a minimum expected collision time between the vehicle and an obstacle with a collision risk according to the driving parameters of the vehicle, including: Predicting a driving trajectory of the vehicle according to driving parameters of the vehicle; wherein the driving trajectory includes a plurality of trajectory points; Based on the sensors installed in the vehicle, the obstacles around the vehicle are identified to form an original obstacle list; Taking the driving trajectory as the center, expanding the lateral search range of obstacles; Filtering the original obstacle list to obtain a first obstacle list according to the lateral search range and the lateral coordinates of each obstacle in the original obstacle list; Based on a bounding box algorithm, a geometric collision check is performed on each obstacle in the first obstacle list and the vehicle, and a target obstacle with a collision risk with the vehicle is identified; For each target obstacle, determining whether the target obstacle is in front of the vehicle based on the driving parameters of the vehicle; If the target obstacle is in front of the vehicle, determining an expected collision time between the vehicle and the target obstacle; The minimum expected collision time is determined from the expected collision times corresponding to each target obstacle.

2. The method according to claim 1, characterized in that: Determining a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state, further comprising: If it is determined that the obstacle avoidance state signal indicates that the emergency braking obstacle avoidance function is turned off, the target braking strategy is determined to be no braking.

3. The method according to claim 2, characterized in that Determining an obstacle avoidance state signal according to the current collision risk level and the driver intervention state includes: When the driver intervention state is that the driver actively intervenes in obstacle avoidance and / or the vehicle travel speed is less than a preset threshold, determining that the obstacle avoidance state signal is a state signal indicating that an emergency braking obstacle avoidance function is turned off; When the driver intervention status is that the driver does not actively intervene in obstacle avoidance, the obstacle avoidance status signal is determined to be a status signal indicating that the emergency braking obstacle avoidance function is turned on according to the current collision risk level; the status signal indicating that the emergency braking obstacle avoidance function is turned on includes: an obstacle avoidance function turn-on preparation signal, an obstacle avoidance warning signal, a comfort braking signal and an emergency braking signal.

4. The method according to claim 3, characterized in that The method further comprises: When the obstacle avoidance status signal is the obstacle avoidance warning signal, the comfort braking signal or the emergency braking signal, an obstacle avoidance warning signal is generated, and the strength of the obstacle avoidance warning signal is determined according to the current collision risk level, so as to control the warning device in the vehicle to issue a warning according to the strength of the obstacle avoidance warning signal.

5. The method according to claim 3, characterized in that: The method further includes determining that the driver intervention state is the driver actively intervening in obstacle avoidance by any of the following methods: In response to a configuration operation for an emergency braking obstacle avoidance function mode, when the emergency braking obstacle avoidance function is turned off, determining that the driver intervention state is a driver actively intervening in obstacle avoidance; When the steering wheel angle is greater than a preset angle threshold, or the steering wheel angular velocity is greater than a preset angular velocity threshold, the emergency braking obstacle avoidance function is turned off, and the driver intervention state is determined to be the driver's active intervention obstacle avoidance; When the turn signal lamp or the hazard warning flasher lamp is turned on, the emergency braking obstacle avoidance function is turned off, and the driver intervention state is determined to be the driver's active intervention obstacle avoidance.

6. The method according to claim 1, characterized in that The expected collision time thresholds preset under different braking strategies include at least one of the following items: the expected collision time threshold corresponding to the braking warning strategy is the warning collision time threshold; the expected collision time threshold corresponding to the comfort braking strategy is the comfort braking collision time threshold; the expected collision time threshold corresponding to the emergency braking strategy is the emergency braking collision time threshold; Comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine the current collision risk level includes: When the minimum expected collision time is less than 0 or greater than the warning collision time threshold, determining the current collision risk level as no collision risk; When the minimum expected collision time is greater than or equal to the comfort braking collision time threshold and less than the warning collision time threshold, determining that the current collision risk level is a slight collision risk; When the minimum expected collision time is greater than or equal to the emergency braking collision time threshold and less than the comfort braking collision time threshold, determining that the current collision risk level is a moderate collision risk; When the minimum expected collision time is greater than or equal to 0 and less than the emergency braking collision time threshold, it is determined that the current collision risk level is that there is a severe collision risk.

7. A vehicle braking obstacle avoidance device, characterized in that: The device comprises: A prediction module, used to predict the minimum expected collision time between the vehicle and an obstacle with a collision risk at a current time node based on the driving parameters of the vehicle; A comparison module, used for comparing the minimum expected collision time with each expected collision time threshold preset under different braking strategies to determine a current collision risk level; A determination module, configured to determine a target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state; A control module, configured to control the vehicle to perform braking and obstacle avoidance according to a target braking deceleration mapped by the target braking strategy; When the determination module is used to determine the target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters, the historical braking strategy adopted at the previous time node, and the driver intervention state, the determination module is used to: determining an obstacle avoidance state signal according to the current collision risk level and the driver intervention state; If it is determined that the obstacle avoidance state signal indicates that the emergency braking obstacle avoidance function is turned on, determining the target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters and the historical braking strategy; The driving parameters include a current relative speed between the vehicle and the obstacle corresponding to the minimum expected collision time and a current deceleration of the vehicle; When the determination module is used to determine the target braking strategy to be adopted at the current time node according to the current collision risk level, the driving parameters and the historical braking strategy adopted at the previous time node, the determination module is used to: When the current collision risk level is no collision risk, if the current relative vehicle speed is less than or equal to 0, the target braking strategy is determined to be no braking; if the relative vehicle speed is greater than 0, the historical braking strategy is determined to be the target braking strategy; When the current collision risk level is that there is a slight collision risk, determining the historical braking strategy as the target braking strategy; When the current collision risk level is that there is a moderate collision risk, the historical braking strategy is upgraded to obtain the target braking strategy; wherein the strategy upgrade method includes: if the historical braking strategy is no braking, the comfort braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is greater than or equal to the braking deceleration corresponding to the comfort braking strategy, the emergency braking strategy is determined as the target braking strategy; if the historical braking strategy is the comfort braking strategy, and the current deceleration is less than the braking deceleration corresponding to the comfort braking strategy, the historical braking strategy is determined as the target braking strategy; if the historical braking strategy is the emergency braking strategy, the emergency braking strategy is determined as the target braking strategy; When the current collision risk level is that there is a severe collision risk, determining the emergency braking strategy as the target braking strategy; When the prediction module is used to predict the minimum expected collision time between the vehicle and an obstacle with a collision risk at a current time node according to the driving parameters of the vehicle, the prediction module is used to: Predicting a driving trajectory of the vehicle according to driving parameters of the vehicle; wherein the driving trajectory includes a plurality of trajectory points; Based on the sensors installed in the vehicle, the obstacles around the vehicle are identified to form an original obstacle list; Taking the driving trajectory as the center, expanding the lateral search range of obstacles; Filtering the original obstacle list to obtain a first obstacle list according to the lateral search range and the lateral coordinates of each obstacle in the original obstacle list; Based on a bounding box algorithm, a geometric collision check is performed on each obstacle in the first obstacle list and the vehicle, and a target obstacle with a collision risk with the vehicle is identified; For each target obstacle, determining whether the target obstacle is in front of the vehicle based on the driving parameters of the vehicle; If the target obstacle is in front of the vehicle, determining an expected collision time between the vehicle and the target obstacle; The minimum expected collision time is determined from the expected collision times corresponding to each target obstacle.

8. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the vehicle braking obstacle avoidance method as described in any one of claims 1 to 6.

Images