CN114559956A

CN114559956A - Avoidance method, device and equipment for automatic driving vehicle and computer storage medium

Info

Publication number: CN114559956A
Application number: CN202210167797.9A
Authority: CN
Inventors: 王星宇
Original assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Current assignee: Apollo Zhilian Beijing Technology Co Ltd; Apollo Zhixing Technology Guangzhou Co Ltd
Priority date: 2022-02-23
Filing date: 2022-02-23
Publication date: 2022-05-31

Abstract

The disclosure provides an avoidance method and device for an automatic driving vehicle, electronic equipment and a computer storage medium, and relates to the field of artificial intelligence, in particular to the technical field of automatic driving and intelligent traffic. The specific implementation scheme is as follows: generating an avoidance decision representing that the target vehicle avoids the obstacle according to the original control track of the target vehicle and the first prediction track of the obstacle; generating at least one first planned trajectory of the target vehicle based on the current driving information of the target vehicle; the first planned trajectory is a trajectory which accords with a preset speed change rule and conflicts with the avoidance decision; and executing invalidation operation on the first planned track so as to refuse to control the target vehicle according to the control operation corresponding to the first planned track in the avoidance range of the target vehicle to the obstacle. The embodiment of the disclosure can generate a stable avoidance strategy, and improves riding experience and safety.

Description

Avoidance method, device and equipment for automatic driving vehicle and computer storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence technology, and more particularly, to the field of automatic driving and intelligent transportation technology.

Background

With the development of computer technology, computers are more and more closely connected with various aspects of people's clothes and eating habits. For example, in the scenes of intelligent transportation, automatic driving, unmanned driving and the like, the vehicle and the transportation facility can be controlled through the computer model, and the control suggestions or control instructions are generated according to specific situations in an auxiliary or main mode, so that manual operation is reduced.

Under the scenes of automatic driving, unmanned driving or intelligent traffic and the like, the situation that overtaking or avoiding needs to be judged when vehicles meet exists, how to enable unmanned vehicles to safely game with obstacles and generate stable overtaking decision is a key problem of unmanned driving technology and a technical problem in the field.

Disclosure of Invention

The present disclosure provides an avoidance method, apparatus, electronic device, and computer storage medium for an autonomous vehicle.

According to an aspect of the present disclosure, there is provided an avoidance method of an autonomous vehicle, including:

generating an avoidance decision representing that the target vehicle avoids the obstacle according to the original control track of the target vehicle and the first prediction track of the obstacle;

generating at least one first planned trajectory of the target vehicle based on current driving information of the target vehicle; the first planned track is a track which accords with a preset speed change rule and conflicts with an avoidance decision;

and executing invalidation operation on the first planned track so as to refuse to control the target vehicle according to the control operation corresponding to the first planned track within the avoidance range of the target vehicle to the obstacle.

According to another aspect of the present disclosure, there is provided an avoidance apparatus of an autonomous vehicle, including:

the avoidance decision module is used for generating an avoidance decision which represents that the target vehicle avoids the barrier according to the original control track of the target vehicle and the first prediction track of the barrier;

the first planning track module is used for generating at least one first planning track of the target vehicle based on the current running information of the target vehicle; the first planned trajectory is a trajectory which accords with a preset speed change rule and conflicts with an avoidance decision;

a failure operation execution module: and the control device is used for executing invalidation operation on the first planned track so as to refuse to control the target vehicle according to the control operation corresponding to the first planned track within the avoidance range of the target vehicle to the obstacle.

According to another aspect of the present disclosure, there is provided an electronic device including:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform a method according to any one of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a non-transitory computer readable storage medium having stored thereon computer instructions for causing a computer to perform a method in any of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is provided a computer program product comprising computer programs/instructions which, when executed by a processor, implement the method in any of the embodiments of the present disclosure.

According to the technology disclosed by the invention, at least one first planning track which is possibly executed by the target vehicle and is not in line with an avoidance decision can be determined according to the original control track of the target vehicle and the first prediction track of the barrier, and the failure operation is executed on the first planning track, so that the situation that emergency braking is needed due to the fact that the target vehicle runs according to the planning track which is not avoided after the avoidance decision for executing the avoidance operation is generated is avoided, and the riding experience of passengers in the target vehicle is reduced.

It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present disclosure, nor do they limit the scope of the present disclosure. Other features of the present disclosure will become apparent from the following description.

Drawings

The drawings are included to provide a better understanding of the present solution and are not to be construed as limiting the present disclosure. Wherein:

FIG. 1 is a schematic flow diagram of a method for evasive avoidance of an autonomous vehicle according to an embodiment of the disclosure;

FIG. 2 is a schematic flow diagram of an avoidance method for an autonomous vehicle according to another embodiment of the present disclosure;

FIG. 3 is a flow chart diagram of a method for evasive avoidance of an autonomous vehicle according to yet another embodiment of the present disclosure;

FIG. 4 is a schematic flow diagram of an avoidance method for an autonomous vehicle according to an example of the present disclosure;

FIG. 5A is a schematic diagram of trajectory planning according to an example of the present disclosure;

FIG. 5B is a schematic diagram of a speed-time curve according to an example of the present disclosure;

FIG. 6 is a schematic diagram of trajectory planning according to another example of the present disclosure;

FIG. 7 is a schematic view of an avoidance device of an autonomous vehicle according to an embodiment of the present disclosure;

FIG. 8 is a schematic view of an avoidance device of an autonomous vehicle according to another embodiment of the present disclosure;

FIG. 9 is a schematic view of an avoidance device of an autonomous vehicle according to yet another embodiment of the present disclosure;

FIG. 10 is a schematic view of an avoidance apparatus of an autonomous vehicle according to yet another embodiment of the present disclosure;

FIG. 11 is a schematic view of an avoidance device of an autonomous vehicle according to yet another embodiment of the present disclosure;

FIG. 12 is a schematic view of an avoidance device of an autonomous vehicle according to yet another embodiment of the present disclosure;

fig. 13 is a block diagram of an electronic device for implementing an avoidance method of an autonomous vehicle according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below with reference to the accompanying drawings, in which various details of the embodiments of the disclosure are included to assist understanding, and which are to be considered as merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.

The embodiment of the disclosure provides an avoidance processing method for an autonomous vehicle, and fig. 1 is a flowchart of the avoidance processing method for the autonomous vehicle according to the embodiment of the disclosure, and the method may be applied to an electronic device that can execute a command by using a front end or a terminal, for example, the apparatus may be deployed in a terminal (including a vehicle-mounted terminal) or a server or other processing devices to execute, and may perform steps such as obtaining content of target information, determining stability, and the like. Among them, the terminal may be a User Equipment (UE), a mobile device, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle-mounted device, a wearable device, and so on. In some possible implementations, the method may also be implemented by a processor calling computer readable instructions stored in a memory. As shown in fig. 1, an avoidance method of an autonomous vehicle includes:

step S11: generating an avoidance decision which represents that the target vehicle avoids the obstacle according to the original control track of the target vehicle and the first prediction track of the obstacle;

step S12: generating at least one first planned trajectory of the target vehicle based on current driving information of the target vehicle; the first planned track is a track which accords with a preset speed change rule and conflicts with an avoidance decision;

step S13: and executing invalidation operation on the first planned track so as to refuse to control the target vehicle according to the control operation corresponding to the first planned track within the avoidance range of the target vehicle to the obstacle.

In a specific implementation manner, the avoidance method for the autonomous vehicle provided in fig. 1 and other embodiments of the present disclosure may be performed at a vehicle end, specifically, at a vehicle end of a target vehicle. The execution of steps S11-S13 may be started when an obstacle is present in the detectable range of the target vehicle, i.e., each time the target vehicle detects an obstacle.

In this embodiment, the original control trajectory of the target vehicle may be an original trajectory of the target vehicle, may be generated before the target vehicle departs from the destination, may be generated when the target vehicle starts an autonomous driving mode or an unmanned driving mode, or may be a control trajectory planned to be executed before the target vehicle detects an obstacle.

In another possible implementation, the original control trajectory of the target vehicle may be a trajectory that the target vehicle executes by default before making an adjustment according to the avoidance decision, i.e., a trajectory that is being executed when an obstacle is detected.

The first predicted trajectory of the obstacle may be a trajectory of the obstacle for a future period of time generated from information of the detected obstacle. Or a trajectory of the obstacle in a future period of time generated from the information of the detected obstacle and the current environment information. The current environmental information may include road surface information, congestion information, traffic flow information, climate information, and the like. The obstacle information may include real-time speed information of the obstacle, and may further include acceleration information of the obstacle, volume information of the obstacle, attribute information, and the like.

The avoidance decision for indicating the target vehicle to avoid the obstacle may include a speed control decision, an acceleration control decision, a direction control decision, and the like for the target vehicle. The method also can comprise decision-making for avoiding the obstacle, for example, after the target vehicle passes through a series of decision-making processes, an avoidance decision-making is generated for giving positive indication to avoidance or not.

The current traveling information of the target vehicle may include information such as a current speed, a current position, and a current acceleration of the target vehicle.

The method includes generating at least one first planned trajectory of the target vehicle based on current driving information of the target vehicle, which may be at least one possible trajectory of the target vehicle based on the current driving information of the target vehicle, and determining at least one first planned trajectory from the at least one possible trajectory.

In this embodiment, at least one first planned trajectory may be determined in an exhaustive manner, that is, all planned trajectories that conflict with an avoidance decision among all trajectories that may be traveled according to a preset speed change rule of the target vehicle are all taken as the first planned trajectory.

The preset speed change rule may be a speed change rule for controlling the speed of the target vehicle, and includes a speed change range, a speed change step range, a speed range, and the like. The preset speed change rule may be determined according to a specific driving position and a driving road section, for example, if the speed limit of the road a is X, the speed change range may be 0-X. As another example, if road B is currently congested, the speed of the target vehicle may be set to a speed value that does not exceed the average speed of the traffic flow on road B.

In one possible implementation manner, the preset speed change rule may be determined according to the default rule of the target vehicle, the performance of the target vehicle and the speed limit information of the current driving road section. For example, if the speed range set in the target vehicle is the Y range and the acceleration range set in the target vehicle is the Z range, the preset speed change rule is determined according to the Y range and the Z range.

In another possible implementation manner, the preset speed change rule may be a speed change rule in a non-hard brake state. Therefore, bad riding experience brought to passengers in the target vehicle due to sudden braking is avoided, and smooth parking is achieved.

In this embodiment, the first planned trajectory is a trajectory that meets a preset speed change rule and conflicts with an avoidance decision, that is, the first planned trajectory is generated according to the preset speed change rule, and for the target vehicle, the first planned trajectory can be executed at the current speed and position, but will collide with an obstacle or does not avoid the obstacle.

In one possible implementation, in the case of generating an avoidance decision, any planned trajectory involved in an avoidance maneuver to accelerate the target vehicle within the avoidance envelope may be considered the first planned trajectory to conflict with the avoidance decision. Therefore, when the parking operation is required to be executed finally, a certain speed reduction transition stage is achieved, and the passengers in the automobile can experience the riding more stably.

In another possible implementation, a trajectory that does not comply with driving habits, driving regulations, may also be determined as the first planned trajectory.

The performing of the invalidation operation on the first planned trajectory may include performing a temporary deletion operation on the first planned trajectory, or a direct deletion operation. The temporary deletion operation may be a deletion operation that invalidates the planned trajectory in a time frame in which the target vehicle may collide with the obstacle.

Performing a disabling operation on the first planned trajectory may further include performing a marking operation on the first planned trajectory such that the first planned trajectory is disabled within a time frame in which the disabling is desired.

The avoidance range of the target vehicle may be a time range or a distance range in which the target vehicle is likely to collide with the obstacle. The determination may be performed according to the detection information of the target vehicle on the obstacle, or a time range or a distance range in which the target vehicle can detect the obstacle may be used as the avoidance range. Therefore, the avoidance range may be generated based on the original control trajectory of the target vehicle, the first predicted trajectory of the obstacle.

In a possible implementation manner, the avoidance range may also be a default distance range or a default time range, and the avoidance range may be determined according to the current position of the target vehicle and the default distance range. In this case, if there is still a risk of collision between the obstacle and the target vehicle after the target vehicle has traveled the avoidance range, the operations of steps S11-S13 may be performed again.

In this embodiment, at least one first planned trajectory which is possibly executed by the target vehicle and is not in accordance with the avoidance decision can be determined according to the original control trajectory of the target vehicle and the first predicted trajectory of the obstacle, and the invalidation operation is executed on the first planned trajectory, so that a situation that emergency braking is needed due to the fact that the target vehicle runs according to the planned trajectory which is not avoided after the avoidance decision for executing the avoidance operation is generated is avoided, and riding experience of passengers in the target vehicle is reduced.

In one embodiment, the first predicted trajectory comprises a plurality, and the method of avoidance for an autonomous vehicle further comprises:

acquiring barrier speed information corresponding to each planning time at a first set number of continuous planning times;

and generating a first predicted track corresponding to each planning time according to the obstacle speed information corresponding to each planning time.

In this embodiment, each planning instant may generate a first predicted trajectory for the detected obstacle. At each planning time, speed information for real-time speed detection of the obstacle can be obtained, and the speed information specifically comprises linear speed information and speed direction information.

The first set number may be any integer number, such as 1-20.

In a possible implementation manner, the first set number may be a specific positive integer, or an integer range composed of positive integers, such as [1,20], which indicates that any data between 1 and 20 may be selected as the number of planning times according to the information of the driving needs of the current target vehicle, the specific situation of the obstacle, and the like, and then the corresponding first predicted trajectory is generated.

In this embodiment, the planning time may be determined according to a set planning interval. The planning interval may also be determined according to road conditions, the specific driving state of the target vehicle. For example, when the road is relatively tortuous and difficult to run, or the vehicle speed is high in an urban area, the planning interval can be shortened.

In this embodiment, corresponding obstacle speed information is acquired at a plurality of continuous planning times, which is helpful for generating an accurate avoidance decision.

In one embodiment, generating an avoidance decision representing an avoidance of a target vehicle based on an original control trajectory of the target vehicle and a first predicted trajectory of an obstacle comprises:

and generating an avoidance decision under the condition that the first predicted tracks with the first set number have collision risks with the original control tracks.

In this embodiment, the decision to avoid may be generated when there is a collision risk between the first predicted trajectories of the first set number that are consecutive and the original control trajectories.

In this embodiment, the avoidance decision may indicate that an affirmative determination is made with respect to the problem of avoidance, and it is determined that the target vehicle performs avoidance.

In this embodiment, by setting a number of first predicted trajectories at the planning time, the accuracy of the avoidance decision can be improved for determining whether to determine the avoidance setting condition.

In one embodiment, the avoidance method of an autonomous vehicle further comprises:

under the condition that collision risks exist between the continuous first predicted tracks with the second set number and the original control tracks, determining a deceleration time period based on the planning time corresponding to the first predicted tracks with the second set number;

a control instruction is generated to control the target vehicle to perform a deceleration operation during the deceleration period.

In this embodiment, the second set number may be 1 or more than 1.

When the second set number is 1, the consecutive first predicted trajectories of the second set number may indicate that there is no collision risk with the original control trajectory in the first predicted trajectories before and after the one first predicted trajectory having a collision risk and corresponding to the adjacent planning times.

In one possible implementation, the second set number is smaller than the first set number.

The condition that there is a collision risk between the first predicted trajectories of the second set number of consecutive first predicted trajectories and the original control trajectory may refer to that there is no collision risk between the first predicted trajectories corresponding to the adjacent planning times before and after the first predicted trajectories of the second set number of consecutive first predicted trajectories and the source control word trajectory.

The deceleration time period is determined based on planned times corresponding to a second set number of first predicted trajectories, which may be determined based on planned times corresponding to a last one of the second set number of first predicted trajectories.

For example, a third set number of planning times may be added to the planning times corresponding to the last first predicted trajectory in the second set number of first predicted trajectories to obtain a time period as the deceleration time period.

In this embodiment, the deceleration time period may also include a plurality of control times, an initial deceleration instruction is generated at a first control time of the deceleration time period, and the deceleration instruction is refreshed at each of the remaining control times, so that specific parameters of the deceleration instruction corresponding to each control time may be the same or different.

The control command for controlling the target vehicle to perform the deceleration operation during the deceleration time period may be generated when the deceleration time period is reached, or the control command for causing the target vehicle to perform the deceleration operation and the corresponding execution time may be generated in advance, and the execution time may be within the deceleration time period.

In this embodiment, when it is continuously determined that the number of the first predicted trajectories with collision risks is not less than the first set number and exceeds the second set number, a control command for controlling the target vehicle to decelerate within the deceleration time period can be generated, and poor riding experience caused by sudden and rapid deceleration to passengers in the vehicle when a subsequent avoidance demand exists is avoided.

In one embodiment, as shown in fig. 2, the current driving information includes a current speed, a current acceleration, a current position; generating at least one first planned trajectory of the target vehicle based on current driving information of the target vehicle, including:

step S21: generating at least one group of speed and acceleration planning values of the target vehicle according to the current speed, the current acceleration and a preset speed change rule; the speed and acceleration planning values comprise speeds and accelerations corresponding to the planning time;

step S22: generating at least one second planned trajectory based on the at least one set of velocity and acceleration planned values;

step S23: and selecting a planning track which conflicts with the avoidance decision from at least one second planning track as the first planning track.

In this embodiment, the preset speed variation rule may include a preset speed value plus-minus rule, such as plus-minus amplitude, maximum range of plus-minus, and the like. Preset acceleration value plus-minus rules can be further included, such as plus-minus amplitude of the acceleration, maximum plus-minus range of the acceleration and the like.

The velocity and acceleration corresponding to the at least one planning instant may indicate that each of the at least one planning instant corresponds to a velocity and acceleration. For example, at the first planning moment, the corresponding speed V1 corresponds to the acceleration a 1; at the second scheduled time, corresponding to velocity V2, acceleration A2 … …, and so on.

For each set of velocity and acceleration plan values, at least one position may be generated at a corresponding planning instant in conjunction with the current position, velocity, of the target vehicle. As the planning time increases, the number of locations where the corresponding target vehicle may be located increases. There may be more than two sets of velocity and acceleration projected values for each projected time. For example, the preset speed change rule includes: the speed variation range may be [ -v, + v ], the acceleration variation range may be [ -a, + a ], and the acceleration variation step may be Δ a. At the first planning time from the current time, under the condition that the speed and the acceleration do not exceed the preset range, two accelerations of a plus delta a and a minus delta a can exist according to the current acceleration value a, and further two speeds can exist at the first planning time. Similarly, at a subsequent second planning instant, third planning instant, etc., the corresponding speed values are more and more likely.

In this embodiment, generating at least one set of planned speed and acceleration values of the target vehicle according to the current speed, the current acceleration, and a preset speed change rule may include: and generating at least one group of speed and acceleration planning values corresponding to the planning time of the target vehicle according to the current speed, the current acceleration and a preset speed change rule.

In another possible implementation manner, an avoidance range may be determined first, and a plurality of avoidance moments are determined according to the avoidance range, where each avoidance moment is a moment within the avoidance range. At least two sets of velocity and acceleration planning values are generated for each avoidance time.

In another possible implementation manner, when determining the first planning trajectory, the number of planning times may be determined according to a default value.

In another possible implementation manner, all the second planned trajectories that the target vehicle may execute according to the current speed and position information and the preset speed change rule can be generated in an exhaustive manner. And in the third track, selecting all planning tracks conflicting with the avoidance decision as the first planning track.

In this embodiment, the first planned trajectory can be determined, so that a failure operation can be subsequently performed on the first planned trajectory, and the target vehicle is prevented from running according to the first planned trajectory and colliding with the obstacle.

In one embodiment, generating at least one second planned trajectory based on at least one set of velocity and acceleration planned values includes:

generating at least one time-velocity curve according to at least one group of velocity and acceleration planning values and at least one future planning moment in a velocity time coordinate system;

performing integral operation on at least one time-velocity curve to obtain at least one planning position corresponding to at least one future planning time;

a second planned trajectory is generated based on the current position of the target vehicle and the at least one planned position.

In this embodiment, the second planned trajectory corresponding to each curve can be quickly determined by performing an integral calculation operation on the time-velocity curve.

In one embodiment, as shown in fig. 3, the avoidance decision is used to indicate that the target vehicle is to be avoided by stopping the vehicle, and the avoidance method for automatically driving the vehicle further includes:

step S31: generating at least one third planning track according to the first planning track and the avoidance decision; the third planning track is a track which is not in conflict with the avoidance decision in the first planning track;

step S32: determining a parking area according to the avoidance decision and the first prediction track;

step S33: in the third planned trajectory, a parking control instruction is set such that the target vehicle stops before reaching the parking area.

In this embodiment, the setting of the parking control command in the third planned trajectory may include setting the parking control command in all third planned trajectories.

In this embodiment, when the avoidance decision is used to indicate that the target vehicle is to be avoided by stopping, no acceleration operation is performed in the avoidance range in all the third planned trajectories.

In this embodiment, the parking control instruction is set in the third planned trajectory, so that a stable avoidance behavior can be generated, and poor riding experience and collision risk promotion caused by avoidance instability are avoided.

In one example of the present disclosure, an avoidance method for an autonomous vehicle includes the steps shown in fig. 4:

step S41: and (5) scene recognition. Information such as the recognition position, speed, and acceleration of the obstacle vehicle is provided by a host vehicle (corresponding to the target vehicle of the foregoing embodiment) sensing module; a travel trajectory of the obstacle vehicle over a future period of time is output by a host vehicle prediction module.

Step S42: and planning the speed of the main vehicle. The planned trajectory of the velocity of the host vehicle possible in a future period of time is given by sampling or the like, which corresponds to the second planned trajectory in the foregoing embodiment.

Step S43: and (5) pruning. Pruning is performed on the unreasonable speed planning trajectory, which is thought of as the first planning trajectory of the foregoing embodiment.

In particular implementations, the unreasonable speed planning may include: speed planning tracks which do not conform to human driving habits, speed planning tracks which do not conform to road regulations and the like.

Step S44: and setting a courtesy condition according to the prediction result. The conditions for giving a gift may correspond to the avoidance decisions in the previous embodiments. The host vehicle should give a gift if the obstacle is likely to arrive at a position ahead of the host vehicle at the same time as the host vehicle at a collision risk based on the result of the prediction of the first predicted trajectory of the obstacle. And simultaneously recording the obstacle information and the decision of courtesy.

Step S45: deceleration is performed. If the current frame (each frame is equivalent to the planning time in the previous embodiment) causes no collision risk of the calculated obstacle with the host vehicle due to predicted line shaking, but the previous frame meets the yield condition while the speed direction of the obstacle is still the cut-in trend, the host vehicle keeps decelerating and yielding by keeping the historical predicted line 8 frames of the converged frame according to the decision of yielding.

Step S46: and judging whether to yield according to the set threshold value. If the successive N frames find that the obstacles trigger the courtesy condition, a Stop mark is arranged in front of the junction to Stop the main vehicle for giving way.

Step S47: and ending the courtesy strategy until the barriers and the main vehicle track prediction line are not overlapped any more.

In another example of the present disclosure, the planning trajectory of the speed of the host vehicle that is possible in a future period of time is given by sampling and the like, as shown in fig. 5A, which may include:

step S51: the host vehicle current speed v0 is acquired.

Step S52: a fixed acceleration range and acceleration sampling resolution that are set in advance are determined. For example, the acceleration range is-2 m/s 2-2 m/s2, the acceleration sampling resolution is 0.1m/s2, and the velocity that the host vehicle can reach at the time t can be obtained through a calculation formula of vt-v 0+ at. The acceleration range is generally set to the maximum and minimum acceleration that the vehicle can take, in relation to the performance of the target vehicle or host vehicle, the requirements on the driving of the target vehicle or host vehicle. In this example, the acceleration sampling resolution may be an increase magnitude of the acceleration, and the acceleration range and the acceleration sampling resolution may be a speed change rule.

Step S53: and obtaining a v-t curve in a period of time according to the current speed v0, the acceleration range and the acceleration sampling resolution, and integrating the v-t curve to obtain the position s of the main car at each moment in a future period of time.

Step S54: by performing integral calculation on the v-t curve, a plurality of behavior tracks of the host vehicle (i.e., the second planned track in the foregoing embodiment) are obtained. Including the velocity v, acceleration a and position s of the host vehicle at each moment (e.g. 1 st s, 2 nd s …) over a period of time (e.g. 8 s).

According to fig. 5B, the planned speed trajectory of the target vehicle or the host vehicle which is possible in a future period of time is given by sampling or the like, that is, by predicting the speed and the acceleration, a plurality of speed-time curves of the target vehicle or the host vehicle are given, and different speed-time curves are integrated to obtain a plurality of planned speed trajectories, that is, the planned speed trajectories correspond to the second planned trajectory in the foregoing embodiment.

In one example of the present disclosure, a first planned trajectory of an obstacle is shown in fig. 6. At three times t1, t2 and t3, three first predicted trajectories are generated for the obstacle obs respectively, the direction of the first predicted trajectory may be consistent with the speed direction of the obstacle obs, and the length of the first predicted trajectory may be the product of the real-time speed of the obstacle obs and the predicted time, as shown in fig. 6 by three dotted lines corresponding to t1, t2 and t 3.

Referring to fig. 6, at time t1, when the first predicted trajectory of the obstacle obs is relatively long, that is, the driving speed of the obstacle obs is predicted to be relatively high, the predicted line of the obstacle obs and the host adc have a risk of intersection, and after the host adc makes a yielding decision, key information and decision information of the obstacle obs in the frame are recorded;

still referring to fig. 6, if at time t2, the prediction line of the obstacle obs is shortened, the prediction is made that the obstacle obs has a deceleration trend, whether the obstacle overtaking intention is unclear but the trend of entering the intersection area is still remained, and the main vehicle is made to keep deceleration and decision making by keeping 8 frames of the history prediction line of the intersection frame;

in the example shown in fig. 6, the intention of the obstacle is continuously checked through the time when the current prediction line passes through the intersection, and if an obstacle obs triggers a yielding strategy for 5 consecutive frames, that is, a yielding decision is triggered at 5 consecutive planning times, a stop flag is established before the intersection area. And meanwhile, continuously checking whether the obstacle obs is separated from the intersection scene, and clearing the stop mark after the obstacle obs drives away. After the safety of the master vehicle adc is ensured, the master vehicle adc can normally pass through.

In the disclosed example, when a main vehicle (target vehicle) meets a vehicle needing to yield in a game process with an obstacle vehicle, stable yielding decisions and behaviors can be generated, and collision risks cannot be caused if the yield is too high for the change of prediction intentions; in the process of the main car playing with the obstacle, for the yielding vehicles meeting the conditions, sudden braking can not be caused due to interframe change of the length of the prediction line, and the body feeling of passengers is optimized.

The embodiment of the present disclosure further provides an avoidance apparatus for an autonomous vehicle, as shown in fig. 7, including:

the avoidance decision module 71 is configured to generate an avoidance decision indicating that the target vehicle avoids the obstacle according to the original control trajectory of the target vehicle and the first predicted trajectory of the obstacle;

a first planned trajectory module 72 for generating at least one first planned trajectory of the target vehicle based on current driving information of the target vehicle; the first planned track is a track which accords with a preset speed change rule and conflicts with an avoidance decision;

the disabling operation performing module 73: and the control device is used for executing invalidation operation on the first planned track so as to refuse to control the target vehicle according to the control operation corresponding to the first planned track within the avoidance range of the target vehicle to the obstacle.

In one embodiment, the first predicted trajectory includes a plurality of trajectories, and as shown in fig. 8, the avoidance apparatus for an autonomous vehicle further includes:

the obstacle speed information module 81 is configured to obtain obstacle speed information corresponding to each planning time at a first set number of continuous planning times;

and a first predicted trajectory generation module 82, configured to generate a first predicted trajectory corresponding to each planning time according to the obstacle speed information corresponding to each planning time.

In one embodiment, as shown in fig. 9, the avoidance decision module includes:

the decision unit 91 is configured to generate an avoidance decision when there is a collision risk between the first predicted trajectories of the first set number and the original control trajectories.

In one embodiment, as shown in fig. 10, the avoidance apparatus of an autonomous vehicle further includes:

a deceleration time period module 101, configured to determine a deceleration time period based on planning times corresponding to a second set number of first predicted trajectories when there is a collision risk between consecutive second set number of first predicted trajectories and the original control trajectory;

the deceleration control module 102 is configured to generate a control instruction for controlling the target vehicle to perform a deceleration operation during a deceleration period.

In one embodiment, the current driving information includes a current speed, a current acceleration, a current position; as shown in fig. 11, the first planned trajectory module includes:

a speed and acceleration unit 111 for generating at least one set of speed and acceleration planned values of the target vehicle according to the current speed, the current acceleration and a preset speed change rule; the speed and acceleration planning values comprise speeds and accelerations corresponding to the planning time;

a second planned trajectory unit 112 for generating at least one second planned trajectory based on at least one set of velocity and acceleration planned values;

a selecting unit 113, configured to select, from the at least one second planned trajectory, a planned trajectory that conflicts with the avoidance decision as the first planned trajectory.

In one embodiment, the second planned trajectory unit is further configured to:

generating at least one time-velocity curve in a velocity-time coordinate system based on at least one set of velocity and acceleration planning values and at least one future planning time;

In one embodiment, the avoidance decision is used to indicate that the target vehicle is to be avoided by stopping the vehicle, and as shown in fig. 12, the avoidance apparatus for an autonomous vehicle further includes:

a third planned trajectory module 121, configured to generate at least one third planned trajectory according to the first planned trajectory and the avoidance decision; the third planning track is a track which is not conflicted in avoidance decision in the first planning track;

a parking area module 122, configured to determine a parking area according to the avoidance decision and the first predicted trajectory;

and the parking control module 123 is configured to set a parking control instruction in the third planned trajectory so that the target vehicle stops before reaching the parking area.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the personal information of the related user all accord with the regulations of related laws and regulations, and do not violate the good customs of the public order.

The present disclosure also provides an electronic device, a readable storage medium, and a computer program product according to embodiments of the present disclosure.

FIG. 13 shows a schematic block diagram of an example electronic device 130 that may be used to implement embodiments of the present disclosure. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 13, the apparatus 130 includes a computing unit 131 that can perform various appropriate actions and processes in accordance with a computer program stored in a Read Only Memory (ROM)132 or a computer program loaded from a storage unit 138 into a Random Access Memory (RAM) 133. In the RAM 133, various programs and data necessary for the operation of the device 130 can also be stored. The calculation unit 131, the ROM 132, and the RAM 133 are connected to each other via a bus 134. An input/output (I/O) interface 135 is also connected to bus 134.

Various components in the device 130 are connected to the I/O interface 135, including: an input unit 136 such as a keyboard, a mouse, or the like; an output unit 137 such as various types of displays, speakers, and the like; a storage unit 138 such as a magnetic disk, optical disk, or the like; and a communication unit 139 such as a network card, modem, wireless communication transceiver, etc. The communication unit 139 allows the device 130 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunication networks.

The computing unit 131 may be a variety of general purpose and/or special purpose processing components having processing and computing capabilities. Some examples of the computing unit 131 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various dedicated Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, and so forth. The calculation unit 131 executes the respective methods and processes described above, such as an avoidance method of an autonomous vehicle. For example, in some embodiments, the avoidance method for an autonomous vehicle may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the memory unit 138. In some embodiments, part or all of the computer program may be loaded and/or installed onto device 130 via ROM 132 and/or communication unit 139. When the computer program is loaded into RAM 133 and executed by the computing unit 131, one or more steps of the above described avoidance method of an autonomous vehicle may be performed. Alternatively, in other embodiments, the computing unit 131 may be configured to perform an avoidance method of the autonomous vehicle by any other suitable means (e.g., by means of firmware).

Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, Field Programmable Gate Arrays (FPGAs), Application Specific Integrated Circuits (ASICs), Application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for implementing the methods of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the program codes, when executed by the processor or controller, cause the functions/operations specified in the flowchart and/or block diagram to be performed. The program code may execute entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

In the context of this disclosure, a machine-readable medium may be a tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the computer. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.

The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), Wide Area Networks (WANs), and the Internet.

The computer system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server of a distributed system, or a server with a combined blockchain.

It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present disclosure may be executed in parallel, sequentially, or in different orders, as long as the desired results of the technical solutions disclosed in the present disclosure can be achieved, and the present disclosure is not limited herein.

The above detailed description should not be construed as limiting the scope of the disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present disclosure should be included in the scope of protection of the present disclosure.

Claims

1. An avoidance method of an autonomous vehicle, comprising:

generating at least one first planned trajectory of the target vehicle based on the current driving information of the target vehicle; the first planned trajectory is a trajectory which accords with a preset speed change rule and conflicts with the avoidance decision;

and executing invalidation operation on the first planned track so as to refuse to control the target vehicle according to the control operation corresponding to the first planned track in the avoidance range of the target vehicle to the obstacle.

2. The method of claim 1, wherein the first predicted trajectory comprises a plurality, the method further comprising:

and generating the first predicted trajectory corresponding to each planning time according to the obstacle speed information corresponding to each planning time.

3. The method of claim 2, wherein generating an avoidance decision representing the target vehicle to avoid the obstacle based on the original control trajectory of the target vehicle and the first predicted trajectory of the obstacle comprises:

and generating the avoidance decision under the condition that the first predicted tracks with the first set number have collision risks with the original control tracks.

4. The method of claim 2, further comprising:

determining a deceleration time period based on planning time corresponding to a second set number of first predicted tracks under the condition that the collision risk exists between the continuous second set number of first predicted tracks and the original control track;

and generating a control instruction for controlling the target vehicle to execute a deceleration operation in the deceleration time period.

5. The method of any of claims 1-4, wherein the current travel information includes a current speed, a current acceleration, a current location; generating at least one first planned trajectory of a target vehicle based on current driving information of the target vehicle, including:

generating at least one group of speed and acceleration planning values of the target vehicle according to the current speed, the current acceleration and a preset speed change rule; the speed and acceleration planning values comprise speeds and accelerations corresponding to planning moments;

generating at least one second planned trajectory based on the at least one set of velocity and acceleration planned values;

selecting a planned trajectory from the at least one second planned trajectory that conflicts with the avoidance decision as the first planned trajectory.

6. The method of claim 5, wherein said generating at least one second planned trajectory from said at least one set of velocity and acceleration planned values comprises:

generating at least one time-velocity curve according to the at least one group of velocity and acceleration planning values and the at least one planning moment in a velocity-time coordinate system;

performing integral operation on the at least one time-velocity curve to obtain at least one planning position corresponding to at least one planning moment;

generating the second planned trajectory according to the current position of the target vehicle and the at least one planned position.

7. The method of any of claims 1-6, wherein the avoidance decision is indicative of the target vehicle being avoided by parking, the method further comprising:

generating at least one third planning track according to the first planning track and the avoidance decision; the third planned trajectory is a trajectory which does not conflict with the avoidance decision in the first planned trajectory;

determining a parking area according to the avoidance decision and the first predicted track;

in the third planned trajectory, a parking control instruction is set such that the target vehicle stops before reaching the parking area.

8. An avoidance apparatus of an autonomous vehicle, comprising:

the avoidance decision module is used for generating an avoidance decision which represents that the target vehicle avoids the obstacle according to the original control track of the target vehicle and the first prediction track of the obstacle;

the first planned track module is used for generating at least one first planned track of the target vehicle based on the current running information of the target vehicle; the first planned trajectory is a trajectory which accords with a preset speed change rule and conflicts with the avoidance decision;

9. The apparatus of claim 8, wherein the first predicted trajectory comprises a plurality, the apparatus further comprising:

the obstacle speed information module is used for acquiring obstacle speed information corresponding to each planning time at a first set number of continuous planning times;

and a first predicted trajectory generation module configured to generate the first predicted trajectory corresponding to each of the planning times according to the obstacle speed information corresponding to each of the planning times.

10. The apparatus of claim 9, wherein the avoidance decision module comprises:

and the decision unit is used for generating the avoidance decision under the condition that the first set number of first predicted tracks and the original control track have collision risks.

11. The apparatus of claim 9, further comprising:

the deceleration time period module is used for determining a deceleration time period based on the planning time corresponding to a second set number of first predicted tracks under the condition that the collision risk exists between the continuous second set number of first predicted tracks and the original control track;

and the deceleration control module is used for generating a control instruction for controlling the target vehicle to execute deceleration operation in the deceleration time period.

12. The apparatus according to any one of claims 8-11, wherein the current travel information includes a current speed, a current acceleration, a current location; the first planned trajectory module includes:

the speed and acceleration unit is used for generating at least one group of speed and acceleration planning values of the target vehicle according to the current speed, the current acceleration and a preset speed change rule; the speed and acceleration planning values comprise speeds and accelerations corresponding to planning moments;

a second planned trajectory unit for generating at least one second planned trajectory based on the at least one set of velocity and acceleration planned values;

and the selection unit is used for selecting the planning track which conflicts with the avoidance decision from the at least one second planning track as the first planning track.

13. The apparatus of claim 12, wherein the second planned trajectory unit is further to:

14. The apparatus of any of claims 8-13, wherein the avoidance decision is indicative of the target vehicle being avoided by parking, the apparatus further comprising:

a third planned trajectory module for generating at least one third planned trajectory according to the first planned trajectory and the avoidance decision; the third planned trajectory is a trajectory in the first planned trajectory that does not conflict with the avoidance decision;

the parking area module is used for determining a parking area according to the avoidance decision and the first prediction track;

and the parking control module is used for setting a parking control instruction in the third planned track so that the target vehicle stops before reaching the parking area.

15. An electronic device, comprising:

at least one processor; and

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-7.

16. A non-transitory computer readable storage medium having stored thereon computer instructions for causing the computer to perform the method of any one of claims 1-7.

17. A computer program product comprising computer programs/instructions, characterized in that the computer programs/instructions, when executed by a processor, implement the steps of the method of any of claims 1-7.