Anti-collision method, device, computer device and storage medium for autonomous vehicles

Abstract

The present application provides an anti-collision method, device, computer device and storage medium for an autonomous vehicle. Obtain environmental information and the driving information of the vehicle itself; determine a plurality of potential collision objects existing in the current environment according to the environmental information; predict the movement trajectory of the vehicle itself within the first time period according to the driving information of the vehicle itself; determine the potential collision objects whose contours overlap with the movement trajectory among the plurality of potential collision objects as target collision objects; calculate the predicted collision time with the target collision objects; determine the target braking mode according to the predicted collision time, and execute the target braking mode. This method realizes the flexible and reasonable selection of the braking mode, and improves the riding experience on the basis of ensuring safety.

Description

Technical Field

[0001] This application relates to the technical field of data annotation, and in particular, to an anti-collision method, device, computer device, and storage medium for autonomous vehicles. Background Art

[0002] With the rapid development of autonomous driving technology, the application fields of autonomous vehicles are expanding day by day, and many R & D entities have invested a lot of scientific research efforts in the research and development of autonomous driving technology. An autonomous vehicle is a comprehensive intelligent system integrating multiple functions such as navigation, environmental perception, decision-making and planning, and human-computer interaction. To ensure the safe driving of autonomous vehicles on the road, an anti-collision algorithm is configured in the autonomous vehicle. However, the traditional anti-collision algorithm has the technical problem that the brake selection is unreasonable, which in turn leads to a poor passenger experience. Summary of the Invention

[0003] The purpose of this application is to at least solve one of the above technical defects, especially the technical defect that the robustness test results in the prior art are not accurate enough.

[0004] In a first aspect, an embodiment of this application provides an anti-collision method for an autonomous vehicle, including:

[0005] Obtain environmental information and the driving information of the vehicle itself;

[0006] Determine multiple potential collision objects existing in the current environment according to the environmental information;

[0007] Predict the movement trajectory of the vehicle itself within a first time period according to the driving information of the vehicle itself;

[0008] Determine the potential collision objects whose contours overlap with the movement trajectory among the multiple potential collision objects as target collision objects;

[0009] Calculate the predicted collision time with the target collision object;

[0010] Determine the target braking method according to the predicted collision time, and execute the target braking method.

[0011] In one of the embodiments, predicting the movement trajectory of the vehicle itself within a first time period according to the driving information of the vehicle itself includes:

[0012] Set multiple prediction points at preset time intervals within the first time period;

[0013] Predict the positions of the vehicle itself at each prediction point according to the driving information of the vehicle itself;

[0014] Draw the movement trajectory according to the positions of the vehicle itself at each prediction point.

[0015] In one of the embodiments, calculating the predicted collision time with the target collision object includes:

[0016] Determine the predicted point closest to the target collision object as the target predicted point;

[0017] Calculate the predicted collision time according to the number of predicted points between the target predicted point and the starting position of the vehicle itself and the preset time interval.

[0018] In one embodiment, determining the target braking mode according to the predicted collision time includes:

[0019] Determine the time range to which the predicted collision time belongs as the target time range from a plurality of preset time ranges; wherein, the time range corresponds to the braking mode one by one, and the smaller the time within the time range, the greater the braking intensity of the braking mode corresponding to the time range;

[0020] Determine the braking mode corresponding to the target time range as the target braking mode.

[0021] In one embodiment, the driving information of the vehicle itself includes the vehicle speed information of the vehicle itself. Before determining the time range to which the predicted collision time belongs as the target time range from a plurality of preset time ranges, it further includes:

[0022] Divide the first time period evenly into a first time range, a second time range, and a third time range;

[0023] Wherein, the time within the first time range is less than the time within the second time range, and the time within the second time range is less than the time within the third time range;

[0024] Determine the first braking acceleration according to the vehicle speed information of the vehicle itself and the preset safe braking distance;

[0025] Set the braking mode corresponding to the first time range to brake with a fixed first braking acceleration so that the vehicle itself can stop within the preset safe braking distance;

[0026] Set the braking mode corresponding to the second time range to brake with a fixed second braking acceleration; wherein, the second braking acceleration is less than the first braking acceleration;

[0027] Set the braking mode corresponding to the third time range to not brake.

[0028] In one embodiment, after predicting the movement trajectory of the vehicle itself within the first time period according to the driving information of the vehicle itself, it further includes:

[0029] Dye the movement trajectory with the first color and then display it;

[0030] After determining the time range to which the predicted collision time belongs as the target time range from a plurality of preset time ranges, it further includes:

[0031] When the target time range is the first time range, change the color of the motion trajectory to the second color;

[0032] When the target time range is the second time range, change the color of the motion trajectory to the third color;

[0033] When the target time range is the third time range, keep the color of the motion trajectory as the first color.

[0034] In one embodiment, changing the color of the motion trajectory to the second color further includes: issuing an alarm prompt.

[0035] In a second aspect, an embodiment of the present application provides an anti-collision device for an autonomous driving vehicle, including:

[0036] An information acquisition module, configured to acquire environmental information and the driving information of the vehicle itself;

[0037] A potential collision object determination module, configured to determine a plurality of potential collision objects existing in the current environment according to the environmental information;

[0038] A trajectory prediction module, configured to predict the motion trajectory of the vehicle itself within the first time period according to the driving information of the vehicle itself;

[0039] A target collision object determination module, configured to determine a potential collision object whose contour overlaps with the motion trajectory among the plurality of potential collision objects as the target collision object;

[0040] An estimated collision time calculation module, configured to calculate the estimated collision time with the target collision object;

[0041] A braking module, configured to determine a target braking method according to the estimated collision time and execute the target braking method.

[0042] In a third aspect, an embodiment of the present application provides a computer device, including one or more processors and a memory. When the computer-readable instructions stored in the memory are executed by the one or more processors, the steps of the anti-collision method for an autonomous driving vehicle in any of the above embodiments are executed.

[0043] In a fourth aspect, an embodiment of the present application provides a storage medium, in which computer-readable instructions are stored. When the computer-readable instructions are executed by one or more processors, the one or more processors are caused to execute the steps of the anti-collision method for an autonomous driving vehicle in any of the above embodiments.

[0044] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0045] Based on any of the above embodiments, predict the movement trajectory of the vehicle within the first time in the future according to the driving information of the vehicle, model potential collision objects in the environment using the scenario information, and find target collision objects that overlap with the movement trajectory from the potential collision objects. Calculate the predicted collision time with the target collision object, and select a braking method with a braking intensity matching the predicted collision time as the target braking method to avoid collision with the target obstacle, achieving a flexible and reasonable selection of the braking method and improving the riding experience on the basis of ensuring safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 It is a schematic flowchart of an anti-collision method for an autonomous vehicle in an embodiment of the present application;

[0048] Figure 2 It is a schematic diagram of the scenario of the operation of an autonomous vehicle in an embodiment of the present application;

[0049] Figure 3 It is a schematic diagram of the principle of predicting the movement trajectory in an embodiment of the present application;

[0050] Figure 4 It is an internal structure diagram of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts belong to the scope of protection of the present application.

[0052] In a first aspect, the present application provides an anti-collision method for an autonomous vehicle. Please refer to Figure 1 , which includes steps S102 to S112.

[0053] S102, obtain environmental information and driving information of the vehicle.

[0054] It can be understood that the environmental information is the information collected by an autonomous vehicle through various sensors configured on the vehicle to perceive the surrounding environment, so as to realize the modeling of the surrounding environment. The scenario information includes road network information, traffic signal information, surrounding object information, etc. The vehicle driving information is the information collected by the autonomous vehicle to monitor the driving state of the vehicle itself, such as the vehicle speed information, the vehicle steering information, the vehicle position information, etc.

[0055] S104. Determine multiple potential collision objects existing in the current environment according to the environmental information.

[0056] It can be understood that the potential collision objects are the obstacles existing in the surrounding environment. For example, other vehicles on the road, road shoulders, isolation belts, etc. After modeling the surrounding environment according to the environmental information, all the identified obstacles can be regarded as potential collision objects by using the relevant algorithms for obstacle recognition configured in the autonomous vehicle. In order to speed up the processing speed, the relevant data of the scenario information will be stored in the KD-Tree data structure, which can greatly accelerate the speed of nearest neighbor search.

[0057] S106. Predict the movement trajectory of the vehicle within the first time period according to the vehicle driving information.

[0058] It can be understood that since the vehicle driving information reflects the driving state of the vehicle itself, after modeling the vehicle using the vehicle dynamics model and combining the vehicle driving information, the position that the vehicle will drive to in the future can be determined, so as to predict the movement trajectory of the vehicle. For example, according to the vehicle speed information and the vehicle steering information, the position change vector of the vehicle can be determined, and then combined with the vehicle position information, the new position information after passing through the position change vector can be predicted. In order to ensure the processing speed, the prediction time period can be reasonably set, that is, only predict the movement trajectory of the vehicle from the current moment to the moment after passing through the first time period, such as predicting the movement trajectory of the vehicle within 3s.

[0059] S108. Determine the potential collision objects whose contours overlap with the movement trajectory among the multiple potential collision objects as target collision objects.

[0060] It can be understood that considering the potential collision objects as static, since the predicted movement trajectory can reflect the position that the vehicle will reach in the future, if the contour of the potential collision object overlaps with the predicted movement trajectory, it means that the vehicle will collide with the potential collision object in the future. Therefore, determine the potential collision objects whose contours overlap with the movement trajectory as target collision objects. The target collision objects are the objects that the anti-collision algorithm in this application needs to handle specifically. For example Figure 2As shown, the vehicle is driving straight on the road. The dashed line in front of the vehicle represents the predicted motion trajectory. The vehicle identifies three potential collision objects around it, and among them, the potential collision object 1 overlaps with the motion trajectory, so the potential collision object 1 is determined as the target collision object.

[0061] S110, calculate the predicted collision time with the target collision object.

[0062] It can be understood that the predicted collision time is the time when the vehicle will collide with the target collision object assuming that the target collision object remains in place and the vehicle maintains its current driving state. That is, the vehicle continues to drive along the motion trajectory, and the duration required to collide with the target collision object.

[0063] S112, determine the target braking method according to the predicted collision time, and execute the target braking method.

[0064] It can be understood that the current anti-collision algorithm directly brakes the vehicle to a stop. Due to the sharp braking, passengers often feel a strong sense of jerk, and the riding experience is poor. In fact, the length of the predicted collision time reflects the urgency of braking. The shorter the predicted collision time, the more urgent the braking required is. For the case where the predicted collision time is longer, there is no need to directly brake the vehicle to a stop. Therefore, this application sets multiple braking methods with different braking intensities. Select the braking method that matches the current braking demand according to the predicted collision time as the target braking method and execute it. That is, more flexibly select the braking intensity. In the case of a shorter predicted collision time, the braking intensity will be greater to ensure that the vehicle speed drops rapidly and avoid collisions due to the inability of the autonomous driving algorithm to react in time. In the case of a longer predicted time, the braking intensity will be smaller, and the autonomous driving algorithm will have more time to avoid obstacles when the vehicle speed slows down, which not only ensures the riding experience of passengers but also achieves the purpose of anti-collision.

[0065] Based on the anti-collision method for autonomous driving vehicles in this embodiment, predict the motion trajectory of the vehicle within the first time in the future according to the driving information of the vehicle, and use the scenario information to model the potential collision objects in the environment, and find the target collision objects that overlap with the motion trajectory from the potential collision objects. Calculate the predicted collision time with the target collision object, and select the braking method with a matching braking intensity according to the length of the predicted collision time as the target braking method to avoid colliding with the target obstacle.

[0066] In one of the embodiments, predicting the motion trajectory of the vehicle within the first duration according to the driving information of the vehicle includes:

[0067] (1) Set multiple prediction points at preset time intervals within the first duration.

[0068] (2) Predict the position of the vehicle at each prediction point based on the driving information of the vehicle.

[0069] (3) Draw a motion trajectory based on the position of the vehicle at each prediction point.

[0070] It can be understood that the motion trajectory prediction method adopted in this embodiment is to set a prediction point at each preset time interval within the first time period. For example, within 3 s, a prediction point is set every 0.1 s, and a total of 30 prediction points are set. Use the driving information of the vehicle to predict the position that the vehicle will reach after each preset time interval starting from the current position, that is, predict the position of the vehicle at each prediction point. Specifically, the driving information of the vehicle may include the vehicle position information, the vehicle speed information, and the vehicle steering information. According to the vehicle speed information, the vehicle steering information, and the vehicle dynamics model, the translation vector of the vehicle after passing through the preset time interval can be determined, and the vehicle is translated according to the translation vector and the vehicle position information. Predictions are sequentially performed according to this process between each prediction point, and the position of the vehicle at each prediction point can be obtained. After determining the position of the vehicle at each prediction point, the trajectory points corresponding to each prediction point can be drawn according to the model of the vehicle. The trajectory points reflect the area occupied by the vehicle at each prediction point. Connecting the trajectory points in chronological order can obtain the motion trajectory. As Figure 3 shown, the black squares represent the positions of the vehicle at each prediction point, and the rectangle formed by the black solid line represents the area occupied by the vehicle. The trajectory points can be selected as the positions of each wheel of the vehicle. Connecting the trajectory points on both sides of each prediction point can obtain the motion trajectory.

[0071] In one of the embodiments, calculating the predicted collision time with the target collision object includes:

[0072] (1) Determine the prediction point closest to the target collision object as the target prediction point.

[0073] (2) Calculate the predicted collision time according to the number of prediction points between the target prediction point and the starting position of the vehicle and the preset time interval.

[0074] It can be understood that the starting position of the vehicle refers to the starting position of the motion trajectory. That is, since the prediction points are set at preset time intervals, the target collision object will be closest to one of them, and the position of the prediction point is the position reached by the vehicle after several preset time intervals. According to the number of prediction points between the target prediction point and the starting position of the vehicle, the number of preset time intervals required for the vehicle to reach the target prediction point can be determined. Based on the number of preset time intervals and the magnitude of the preset time interval, the predicted collision time can be calculated. Expressed by a mathematical formula, it is T = (n + 1) * t, where T is the predicted collision time, n is the number of prediction points between the target prediction point and the starting position of the vehicle, and t is the preset time interval. For example, if there are 5 prediction points between the target prediction point and the starting position of the vehicle, then the target prediction point is the 6th prediction point. Assuming the preset time interval is 0.1 s, the predicted collision time is 0.6 s.

[0075] In one of the embodiments, determining the target braking mode according to the predicted collision time includes:

[0076] (1) From a plurality of preset time ranges, determine the time range to which the predicted collision time belongs as the target time range. Among them, the time range corresponds to the braking mode one by one, and the smaller the time within the time range, the greater the braking intensity of the braking mode corresponding to the time range.

[0077] (2) Determine the braking mode corresponding to the target time range as the target braking mode.

[0078] It can be understood that in this embodiment, the first time is divided into multiple time ranges, and each time range corresponds to a braking mode. The braking intensities used by the braking modes corresponding to different time ranges are also different. If the time within one time range is less than the time within another time range, it means that the predicted collision is more urgent when it belongs to this time range and stronger braking is required. Therefore, the braking intensity of the braking mode corresponding to this time range will be greater.

[0079] In one of the embodiments, the driving information of the vehicle includes the vehicle speed information, and the vehicle speed information reflects the speed magnitude of the vehicle. Before determining the time range to which the predicted collision time belongs as the target time range from a plurality of preset time ranges, it further includes:

[0080] (1) Evenly divide the first duration into the first time range, the second time range, and the third time range. Among them, the time within the first time range is less than the time within the second time range, and the time within the second time range is less than the time within the third time range.

[0081] It can be understood that the division method adopted in this embodiment is an average division, that is, the span of each time range is the same. For example, if the first duration is 3s, the span of each time range is 1s. The first time range is 0 - 1s, the second time range is 1 - 2s, and the third time range is 2 - 3s. The braking intensity from the first time range to the third time range decreases from large to small.

[0082] (2) Determine the first braking acceleration according to the vehicle speed information of the vehicle and the preset safe braking distance.

[0083] (3) Set the braking method corresponding to the first time range to brake with a fixed first braking acceleration, so that the vehicle can stop within the preset safe braking distance.

[0084] It can be understood that when the predicted collision time is within the first time range in this embodiment, the situation is the most urgent. To ensure safety, the measure taken is to stop the vehicle within the preset safe braking distance. However, to prevent skidding and for the riding experience, the braking intensity is not directly increased to the threshold, but a fixed first braking acceleration is used for braking, so that the vehicle decelerates quickly and evenly. At this time, the vehicle is equivalent to moving with a constant acceleration and the final speed is 0. According to the kinematic formula a1 = v^2 / 2s, where a1 is the critical braking acceleration, v is the vehicle speed, and s is the preset safe distance. Setting the first braking acceleration to be greater than or equal to a1 can ensure that the vehicle stops within the safe distance.

[0085] (4) Set the braking method corresponding to the second time range to brake with a fixed second braking acceleration. Among them, the second braking acceleration is less than the first braking acceleration.

[0086] It can be understood that when the predicted collision time is within the second time range in this embodiment, the situation is relatively urgent. A medium braking intensity can be adopted, that is, there is no need to stop the vehicle, just reduce the vehicle speed to give the autonomous vehicle more response time. For example, the safe vehicle speed can be set in this case, and the second braking acceleration can be calculated according to the vehicle speed information of the vehicle, the safe vehicle speed, and the preset safe distance.

[0087] (5) Set the braking method corresponding to the third time range to not brake.

[0088] It can be understood that when the predicted collision time is within the third time range in this embodiment, the target collision object is still far from the vehicle, and there is enough reaction time to keep the driving state of the vehicle unchanged, that is, do not brake when the predicted collision time is within the third time range in this embodiment.

[0089] In one embodiment, after predicting the movement trajectory of the vehicle within the first time period according to the vehicle's driving information, it further includes: dyeing the movement trajectory with a first color and then displaying it.

[0090] After determining that the time range to which the predicted collision time belongs is the target time range from a plurality of preset time ranges, it further includes:

[0091] (1) When the target time range is the first time range, changing the color of the movement trajectory to a second color.

[0092] (2) When the target time range is the second time range, changing the color of the movement trajectory to a third color.

[0093] (3) When the target time range is the third time range, keeping the color of the movement trajectory as the first color.

[0094] It can be understood that a display device is generally provided in an autonomous vehicle, and the autonomous vehicle can be taken over manually in an emergency. To facilitate the safety officer to take over the vehicle, the movement trajectory can be dyed and presented on the display device. When the predicted collision time is in different time ranges, different colors are used to prompt the safety officer. For example, according to the color design of traffic lights, the first color is selected as green, the second color is selected as yellow, and the third color is selected as red. Under normal conditions, the color of the movement trajectory remains green. When the algorithm in the embodiment of the present application is used to identify a target collision object, if the predicted collision time is in the third time range, the movement trajectory remains green. If the predicted collision time is in the second time range, the movement trajectory changes from green to yellow. If the predicted collision time is in the first time range, the movement trajectory changes from green to red. In some embodiments, when the predicted collision time is in the first time range, in addition to changing the color of the movement trajectory, an alarm prompt will also be issued to remind the safety officer to pay attention and take over the vehicle in an emergency.

[0095] In a second aspect, an anti-collision device for an autonomous vehicle provided by an embodiment of the present application includes an information acquisition module, a potential collision object determination module, a trajectory prediction module, a target collision object determination module, a predicted collision time calculation module, and a braking module.

[0096] The information acquisition module is used to acquire environmental information and the vehicle's driving information.

[0097] The potential collision object determination module is used to determine a plurality of potential collision objects existing in the current environment according to the environmental information.

[0098] The trajectory prediction module is used to predict the movement trajectory of the vehicle within the first time period according to the vehicle's driving information.

[0099] The target collision object determination module is used to determine the potential collision objects with overlapping contours and movement trajectories among multiple potential collision objects as target collision objects.

[0100] The predicted collision time calculation module is used to calculate the predicted collision time with the target collision object.

[0101] The braking module is used to determine the target braking method according to the predicted collision time and execute the target braking method.

[0102] In one embodiment, the trajectory prediction module is further used to set multiple prediction points at preset time intervals within the first time period; predict the position of the vehicle at each prediction point according to the driving information of the vehicle; draw the movement trajectory according to the position of the vehicle at each prediction point.

[0103] In one embodiment, the predicted collision time calculation module is further used to determine the prediction point closest to the target collision object as the target prediction point; calculate the predicted collision time according to the number of prediction points between the target prediction point and the starting position of the vehicle and the preset time interval.

[0104] In one embodiment, the braking module is used to determine the time range to which the predicted collision time belongs as the target time range from a plurality of preset time ranges; wherein, the time range corresponds to the braking method one by one, and the smaller the time within the time range, the greater the braking intensity of the braking method corresponding to the time range; determine the braking method corresponding to the target time range as the target braking method.

[0105] In one embodiment, the anti-collision device for autonomous vehicles further includes a braking method setting module. The braking method setting module is used to evenly divide the first time period into a first time range, a second time range, and a third time range; wherein, the time within the first time range is less than the time within the second time range, and the time within the second time range is less than the time within the third time range; determine the first braking acceleration according to the vehicle speed information of the vehicle and the preset safe braking distance; set the braking method corresponding to the first time range to brake with a fixed first braking acceleration so that the vehicle can stop within the preset safe braking distance; set the braking method corresponding to the second time range to brake with a fixed second braking acceleration; wherein, the second braking acceleration is less than the first braking acceleration; set the braking method corresponding to the third time range to not brake.

[0106] In one of the real-time examples, the anti-collision device for autonomous vehicles further includes a display module. The display module is used to display the motion trajectory after coloring it with a first color. And when the target time range is the first time range, change the color of the motion trajectory to a second color; when the target time range is the second time range, change the color of the motion trajectory to a third color; when the target time range is the third time range, keep the color of the motion trajectory as the first color.

[0107] In one of the real-time examples, the anti-collision device for autonomous vehicles further includes an alarm module. The alarm module is used to issue an alarm prompt when the target time range is the second time range.

[0108] In a third aspect, an embodiment of the present application provides a computer device, including one or more processors, and a memory. Computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by one or more processors, the steps of the anti-collision method for autonomous vehicles in any of the above embodiments are executed.

[0109] Schematically, as Figure 4 shown, Figure 4 is an internal structural schematic diagram of a computer device provided by an embodiment of the present application. The computer device 300 can be provided as a server. Referring to Figure 4 , the computer device 300 includes a processing component 302, which further includes one or more processors, and memory resources represented by the memory 301 for storing instructions executable by the processing component 302, such as application programs. The application programs stored in the memory 301 may include one or more modules each corresponding to a set of instructions. In addition, the processing component 302 is configured to execute instructions to perform the anti-collision method for autonomous vehicles in any of the above embodiments.

[0110] The computer device 300 may further include a power supply component 303 configured to perform power management of the computer device 300, a wired or wireless network interface 304 configured to connect the computer device 300 to a network, and an input / output (I / O) interface 305. The computer device 300 may operate based on an operating system stored in the memory 301, such as WindowsServer TM, Mac OS XTM, Unix TM, Linux TM, Free BSDTM or the like.

[0111] Those skilled in the art can understand, Figure 4The structure shown is only a block diagram of some of the structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different component layout.

[0112] In a fourth aspect, an embodiment of the present application provides a storage medium storing computer-readable instructions that, when executed by one or more processors, cause the one or more processors to execute the steps of the anti-collision method for an autonomous vehicle in any of the above embodiments.

[0113] Finally, it should also be noted that in this text, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the presence of additional identical elements in the process, method, article or device including the said element.

[0114] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can be referred to each other.

[0115] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An anti-collision method for an autonomous vehicle, characterized in that, including: Obtaining environmental information and the driving information of the vehicle itself; The driving information of the vehicle itself includes the vehicle speed information; Determining a plurality of potential collision objects existing in the current environment according to the environmental information; Predicting the movement trajectory of the vehicle itself within the first time period according to the driving information of the vehicle itself; Determining the potential collision objects among the plurality of potential collision objects whose contours overlap with the movement trajectory as target collision objects; Calculating the predicted collision time with the target collision object; Determining the target braking mode according to the predicted collision time, and executing the target braking mode; The determining the target braking mode according to the predicted collision time includes: Evenly dividing the first time period into a first time range, a second time range and a third time range; wherein, the time within the first time range is less than the time within the second time range, and the time within the second time range is less than the time within the third time range; According to the vehicle speed information and the preset safe braking distance, determining the critical braking acceleration when the speed is reduced to 0 within the preset safe braking distance, and setting the first braking acceleration to be greater than or equal to the critical braking acceleration; Setting the braking mode corresponding to the first time range to brake at a fixed first braking acceleration, so that the vehicle itself stops within the preset safe braking distance; Setting the braking mode corresponding to the second time range to brake at a fixed second braking acceleration; wherein, the second braking acceleration is less than the first braking acceleration, and is determined according to the vehicle speed information, the safe vehicle speed and the preset safe braking distance; Setting the braking mode corresponding to the third time range to not brake; Determining, from a plurality of preset time ranges, the time range to which the predicted collision time belongs as the target time range; Determining the braking mode corresponding to the target time range as the target braking mode.

2. The method according to claim 1, wherein The predicting the movement trajectory of the vehicle itself within the first time period according to the driving information of the vehicle itself includes: Setting a plurality of prediction points at preset time intervals within the first time period; Predicting the positions of the vehicle itself at each of the prediction points according to the driving information of the vehicle itself; Drawing the movement trajectory according to the positions of the vehicle itself at each of the prediction points.

3. The method according to claim 2, wherein The calculating the predicted collision time with the target collision object includes: Determining the prediction point closest to the target collision object as the target prediction point; Calculating the predicted collision time according to the number of prediction points between the target prediction point and the starting position of the vehicle itself and the preset time interval.

4. The method according to claim 1, wherein After predicting the movement trajectory of the vehicle itself within the first time period according to the driving information of the vehicle itself, it further includes: Dyeing the movement trajectory with a first color and then displaying it; After determining, from a plurality of preset time ranges, the time range to which the predicted collision time belongs as the target time range, it further includes: In the case where the target time range is the first time range, changing the color of the movement trajectory to a second color; In the case where the target time range is the second time range, changing the color of the movement trajectory to a third color; When the target time range is the third time range, keep the color of the movement trajectory as the first color.

5. The method according to claim 1, wherein Changing the color of the movement trajectory to the second color further includes: issuing an alarm prompt.

6. An anti-collision device for an autonomous vehicle, characterized in that, It includes: An information acquisition module for acquiring environmental information and the driving information of the vehicle itself; The driving information of the vehicle itself includes the vehicle speed information of the vehicle itself; A potential collision object determination module for determining a plurality of potential collision objects existing in the current environment according to the environmental information; A trajectory prediction module for predicting the movement trajectory of the vehicle itself within a first time period according to the driving information of the vehicle itself; A target collision object determination module for determining, as target collision objects, those potential collision objects among the plurality of potential collision objects whose contours overlap with the movement trajectory; An estimated collision time calculation module for calculating the estimated collision time with the target collision object; A braking module for determining a target braking method according to the estimated collision time and executing the target braking method; Determining the target braking method according to the estimated collision time includes: Evenly dividing the first time period into a first time range, a second time range, and a third time range; wherein, the time within the first time range is less than the time within the second time range, and the time within the second time range is less than the time within the third time range; According to the vehicle speed information of the vehicle itself and a preset safe braking distance, determining the critical braking acceleration when reducing the speed to 0 within the preset safe braking distance, and setting the first braking acceleration to be greater than or equal to the critical braking acceleration; Setting the braking method corresponding to the first time range to brake at a fixed first braking acceleration so that the vehicle itself stops within the preset safe braking distance; Setting the braking method corresponding to the second time range to brake at a fixed second braking acceleration; wherein, the second braking acceleration is less than the first braking acceleration and is determined according to the vehicle speed information of the vehicle itself, the safe vehicle speed, and the preset safe braking distance; Setting the braking method corresponding to the third time range to not brake; Determining, from a plurality of preset time ranges, the time range to which the estimated collision time belongs as the target time range; Determining the braking method corresponding to the target time range as the target braking method.

7. A computer device, characterized in that, It includes one or more processors and a memory, and computer-readable instructions are stored in the memory. When the computer-readable instructions are executed by the one or more processors, the steps of the anti-collision method for an autonomous driving vehicle according to any one of claims 1-5 are executed.

8. A storage medium, characterized in that, Computer-readable instructions are stored in the storage medium. When the computer-readable instructions are executed by one or more processors, one or more processors are caused to execute the steps of the anti-collision method for an autonomous driving vehicle according to any one of claims 1-5.

Images