CN116039675A

CN116039675A - Method and device for generating predicted running track of automatic driving vehicle and electronic equipment

Info

Publication number: CN116039675A
Application number: CN202310070469.1A
Authority: CN
Inventors: 易梦龙
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2023-01-12
Filing date: 2023-01-12
Publication date: 2023-05-02

Abstract

The disclosure provides a method and a device for generating a predicted running track of an automatic driving vehicle and electronic equipment, and relates to the field of artificial intelligence, in particular to the fields of automatic driving, computer, map data processing and the like. The specific implementation scheme is as follows: acquiring at least one predicted running track of the automatic driving vehicle; determining at least one first predicted running track conforming to a target running rule in at least one predicted running track, wherein the target running rule is used for guiding an automatic driving vehicle to run on a road section in a normal running state; determining a target lane corresponding to the first predicted running track on the road section based on the track point on the first predicted running track, wherein the target lane is a lane which is to be driven by the automatic driving vehicle and accords with the target running rule; and generating a second predicted running track of the automatic driving vehicle based on the track point and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane.

Description

Method and device for generating predicted running track of automatic driving vehicle and electronic equipment

Technical Field

The disclosure relates to the technical field of artificial intelligence, in particular to a method and a device for generating a predicted running track of an automatic driving vehicle and electronic equipment in the fields of automatic driving, computers and map data processing.

Background

At present, all automatic driving vehicles on the market directly generate track points through a track prediction model so as to complete the prediction of the running track, however, the running track predicted by the method is often obviously and incorrectly matched, and the automatic driving vehicles cannot be accurately controlled, so that potential safety hazards exist in the running process of the automatic driving vehicles.

Disclosure of Invention

The disclosure provides a method and a device for generating a predicted running track of an automatic driving vehicle and electronic equipment.

According to another aspect of the present disclosure, a predicted travel track generation method of an autonomous vehicle is provided. The method may include: acquiring at least one predicted running track of the automatic driving vehicle; determining at least one first predicted running track conforming to a target running rule in at least one predicted running track, wherein the target running rule is used for guiding an automatic driving vehicle to run on a road section in a normal running state; determining a target lane corresponding to the first predicted running track on the road section based on the track point on the first predicted running track, wherein the target lane is a lane which is to be driven by the automatic driving vehicle and accords with the target running rule; and generating a second predicted running track of the automatic driving vehicle based on the track point and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane.

According to another aspect of the present disclosure, another method of generating a predicted travel track of an autonomous vehicle is also provided. The method may include: displaying at least one predicted running track output by a track prediction model on an operation interface, wherein the track prediction model is used for predicting the running track of the automatic driving vehicle; displaying at least one first predicted running track conforming to a target running rule in at least one predicted running track on an operation interface, wherein the target running rule is used for guiding an automatic driving vehicle to run on a road section in a normal running state; and responding to a track generation instruction acted on the operation interface, displaying a second predicted running track in at least one first predicted running track on the operation interface, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to a target lane, the track point on the first predicted running track and the target lane are generated, the target lane is a lane to which the automatic driving vehicle is to run and accords with a target running rule, and the target lane is determined on a road section based on the track point on the first predicted running track.

According to another aspect of the present disclosure, there is also provided a predicted travel track generation device of an autonomous vehicle. The apparatus may include: an acquisition unit for acquiring at least one predicted travel track of the autonomous vehicle; the first determining unit is used for determining at least one first predicted running track which accords with a target running rule in the at least one predicted running track, wherein the target running rule is used for guiding the automatic driving vehicle to run on a road section in a normal running state; the second determining unit is used for determining a target lane corresponding to the first predicted running track on the road section based on the track point on the first predicted running track, wherein the target lane is a lane which is to be driven by the automatic driving vehicle and accords with the target running rule; and the generation unit is used for generating a second predicted running track of the automatic driving vehicle based on the track point and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane.

According to another aspect of the present disclosure, there is also provided another predicted travel track generation device of an autonomous vehicle. The apparatus may include: the first display unit is used for displaying at least one predicted running track output by a track prediction model on an operation interface, wherein the track prediction model is used for predicting the running track of the automatic driving vehicle; the second display unit is used for displaying at least one first predicted running track which accords with a target running rule in the at least one predicted running track on the operation interface, wherein the target running rule is used for guiding the automatic driving vehicle to run on the road section in a normal running state; and the third display unit is used for responding to a track generation instruction acted on the operation interface, displaying a second predicted running track in at least one first predicted running track on the operation interface, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to a target lane, the second predicted running track is generated based on a track point on the first predicted running track and the target lane, the target lane is a lane to which the automatic driving vehicle is to run and accords with a target running rule, and the target lane is determined on a road section based on the track point on the first predicted running track.

According to an aspect of the present disclosure, there is also provided an electronic apparatus. The electronic device may include: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for generating a predicted travel track for an autonomous vehicle according to an embodiment of the present disclosure.

According to another aspect of the present disclosure, there is also provided a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the predicted travel track generation method of the autonomous vehicle of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is also provided a computer program product, which may include a computer program which, when executed by a processor, implements the method of generating a predicted travel track of an autonomous vehicle of the embodiments of the present disclosure.

According to another aspect of the present disclosure, there is also provided an autonomous vehicle, which may include the above-described electronic device.

It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the disclosure, nor is it intended to be used to limit the scope of the disclosure. Other features of the present disclosure will become apparent from the following specification.

Drawings

The drawings are intended to illustrate the present solution better and do not constitute a limitation of the present disclosure. Wherein:

FIG. 1 is a flow chart of a method of generating a predicted travel track for an autonomous vehicle according to an embodiment of the present disclosure;

FIG. 2a is a flow chart of another method of generating a predicted travel track for an autonomous vehicle according to an embodiment of the present disclosure;

FIG. 2b is a schematic diagram of an operator interface according to an embodiment of the present disclosure;

FIG. 3 is a flow chart of a travel track generation method according to an embodiment of the present disclosure;

FIG. 4 is a schematic illustration of a trajectory point outside an intersection, according to an embodiment of the present disclosure;

FIG. 5 is a schematic illustration of a track point crossing a boundary according to an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a trace point rollback in accordance with an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of a target lane selection according to an embodiment of the present disclosure;

FIG. 8 is a schematic illustration of an autonomous vehicle orientation according to an embodiment of the present disclosure;

FIG. 9 is a schematic diagram of a target lane selection according to an embodiment of the present disclosure;

FIG. 10 is a schematic illustration of a tie-point selection in accordance with an embodiment of the present disclosure;

FIG. 11a is a schematic diagram of a tie-back in accordance with an embodiment of the present disclosure;

FIG. 11b is a schematic illustration of the result of the generation of a trace line in accordance with an embodiment of the present disclosure;

FIG. 11c is a schematic illustration of post-processing results of a trace line according to an embodiment of the present disclosure;

FIG. 12 is a schematic diagram of a predicted travel track generation device of an autonomous vehicle according to an embodiment of the present disclosure;

FIG. 13 is a schematic diagram of another predicted travel track generation device for an autonomous vehicle according to an embodiment of the disclosure;

fig. 14 is a block diagram of an electronic device of a predicted travel track generation method of an autonomous vehicle according to an embodiment of the present disclosure.

Detailed Description

Exemplary embodiments of the present disclosure are described below in conjunction with the accompanying drawings, which include various details of the embodiments of the present disclosure to facilitate understanding, and should be considered as merely exemplary. Accordingly, one 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 present disclosure provides a method for generating a predicted driving trajectory of an autonomous vehicle, and fig. 1 is a flowchart of a method for generating a predicted driving trajectory of an autonomous vehicle according to an embodiment of the present disclosure, and as shown in fig. 1, an implementation of the method for generating a predicted driving trajectory of an autonomous vehicle may include at least the following implementation steps:

Step S102, at least one predicted driving track of the automatic driving vehicle is obtained.

In the technical solution provided in step S102, at least one predicted driving track of the autonomous vehicle may be obtained, where the predicted driving track may be a predicted driving track of the autonomous vehicle and may be a driving path of the autonomous vehicle.

For example, the embodiment may predict the driving track of the autonomous vehicle by using the track prediction model to obtain at least one predicted driving track. The track prediction model may be used to predict a track of an autonomous vehicle, and it should be noted that at least one predicted driving track may be obtained by using the track prediction model, which is merely exemplary herein, and the method for obtaining the predicted driving track is not specifically limited.

In step S104, at least one first predicted travel track conforming to a target travel rule for guiding the autonomous vehicle to travel on the road segment in a normal travel state is determined from the at least one predicted travel track.

In the technical solution provided in step S104, at least one first predicted driving track conforming to the target driving rule may be determined in the at least one predicted driving track. The target driving rule may be priori knowledge and/or map information, and may be used to screen at least one predicted driving track, and may be used to guide the automatic driving vehicle to drive on the road section in a normal driving state. The priori knowledge may be expert priori knowledge, may be rules or experience that are easier to judge, for example, may be a track that needs to turn left on a left-turn lane, needs to slow down on a large probability when encountering a red light, and where a real obstacle cannot walk out of a track point to back, etc., which is only an example, and does not limit the content of the priori knowledge specifically. The map information may be information in each road section acquired in advance, for example, may include information of road boundaries in each road section, intermediate line information, and the like, and is given here by way of example only, without specific limitation to the manner of acquisition and content of the map information. The normal running state may refer to a running state in which traffic regulations are not violated such as driving violations, reverse running, etc., and is merely an example, and the normal running state is not particularly limited. The first predicted travel track may be a track line conforming to an automatic travel rule among at least one predicted travel track.

Optionally, at least one predicted running track is obtained, the at least one predicted running track may be screened based on the target running rule, and the predicted running track of the normal running state of the automatic driving vehicle is determined from the at least one predicted running track, so as to obtain at least one first predicted running track conforming to the target running rule.

For example, at least one predicted travel track in the road a is obtained, which is a predicted travel track B, a predicted travel track C, a predicted travel track D, a predicted travel track E, and a predicted travel track F, respectively. The obtained at least one predicted travel track may be determined based on the prior knowledge and the map information. The problem that the track point is outside the intersection is determined in the predicted running track B, but the vehicle cannot run outside the road in the running process, so that the predicted running track B is in an abnormal running state and does not accord with the target running rule.

Optionally, the predicted driving track C has a problem that a plurality of track points cross a yellow line of the road, and if the vehicle crosses the yellow line of the road during driving, there is a problem of driving violation, so the predicted driving track C is in an abnormal driving state and does not conform to the target driving rule. The problem of rollback of track points exists in the predicted running track D, and the problem of illegal driving exists in the running process of the vehicle, so that the predicted running track D is in an abnormal running state and does not accord with the target running rule. Optionally, if the predicted running track E and the predicted running track F conform to the target running rule, at least one first predicted running track may be determined as the predicted running track E and the predicted running track F.

In the embodiment of the disclosure, at least one predicted running track of the automatic driving vehicle is obtained, and at least one first predicted running track of the normal running state in the obtained at least one predicted running track is determined through the target running rule, that is, the predicted running track is screened through the target running rule, so that a reasonable (meeting the target running rule) running track is further determined, and normal running of the automatic driving vehicle is ensured.

Step S106, determining a target lane corresponding to the first predicted running track on the road section based on the track point on the first predicted running track, wherein the target lane is a lane which is to be driven by the automatic driving vehicle and accords with the target running rule.

In the technical solution provided in step S106, the target lane corresponding to the first predicted driving track may be determined on the road section based on the track point on the first predicted driving track. The track point on the first predicted running track may be a reasonable track point. The Target lane (Target Line) may be a lane to which the autonomous vehicle is to travel, for example, may be an exit lane of the autonomous vehicle, and may be a lane conforming to a Target travel rule.

For example, the direction of the last track point may be determined based on the track point on the first predicted driving track, the target lane corresponding to the first predicted driving track and meeting the target driving rule may be determined on the road section based on the direction of the last track point, and the autonomous vehicle may drive on the target lane.

It should be noted that the above method for determining the target lane is merely illustrative, and any method for determining the target lane based on the track point should be within the scope of the embodiments of the present disclosure.

Step S108, generating a second predicted running track of the automatic driving vehicle based on the track point and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane.

In the technical solution provided in step S108, the second predicted driving track of the autonomous vehicle may be generated based on the track point and the target lane. The second predicted driving track may be a driving track conforming to a target driving rule, and may be used to control the autonomous vehicle to travel onto the target lane.

Alternatively, the embodiment may determine the first predicted travel track according to the target travel rule, may determine the target lane of the autonomous vehicle based on the track point of the first predicted travel rule, may generate the second predicted travel track of the autonomous vehicle based on the target lane and the track point, and may precisely control the autonomous vehicle to travel onto the target lane through the second predicted travel track.

Because the embodiment of the disclosure considers that different road segments have different running requirements and the running conditions of the different road segments are different, the reasonable first predicted running track is determined by using the target running rule, so that the rationality of the predicted running track is improved. And the target lane is determined based on the track point of the first predicted running track, and the second predicted running track is determined based on the track point and the target lane, so that the suitability of the predicted running track and the target lane is improved, and the driving safety of the vehicle is further ensured.

Through the steps S102 to S108, at least one predicted driving track of the autonomous vehicle is obtained; determining at least one first predicted running track conforming to a target running rule in at least one predicted running track, wherein the target running rule is used for guiding an automatic driving vehicle to run on a road section in a normal running state; determining a target lane corresponding to the first predicted running track on the road section based on the track point on the first predicted running track, wherein the target lane is a lane which is to be driven by the automatic driving vehicle and accords with the target running rule; and generating a second predicted running track of the automatic driving vehicle based on the track point and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane. That is, the embodiment of the disclosure determines a reasonable first predicted travel track conforming to the target travel rule from at least one predicted travel track of the autonomous vehicle, determines a corresponding target lane (exit lane) based on a reasonable track point on the first predicted travel track, and generates a second predicted travel track conforming to the target travel rule based on the reasonable track point and the target lane, thereby achieving the technical effect of effectively generating the travel track of the autonomous vehicle and solving the technical problem that the travel track of the autonomous vehicle cannot be effectively generated.

The above-described method of this embodiment is described in further detail below.

As an optional embodiment, step S104, the target driving rule is determined by map information of the road segment, and determining at least one first predicted driving track conforming to the target driving rule in the at least one predicted driving track includes: and determining the predicted running track matched with the map information of the road section as a first predicted running track in at least one predicted running track.

In this embodiment, the target travel rule may be determined from map information of the road section, and in at least one predicted travel track, a predicted shape that matches the map information of the road section may be determined as the first predicted travel track. The map information may be information in each road section acquired in advance, for example, may include information of a road boundary in each road section, intermediate line information, and the like, which are only examples herein, and the acquisition mode and content of the map information are not particularly limited.

Alternatively, at least one predicted travel track may be screened based on map information of the road section, a predicted travel track matching the map information of the road section may be determined from the at least one predicted travel track, and the predicted travel track may be determined as the first predicted travel track.

For example, map information of each road section may be acquired in advance and stored. And obtaining at least one predicted running track, determining map information of road sections of the at least one predicted running track to obtain a target running rule, and processing the at least one predicted running track based on the target running rule to determine a predicted running track matched with the target running rule in the at least one predicted running track so as to obtain a first predicted running track.

In the embodiment of the disclosure, by matching at least one predicted running track obtained by prediction by using the map information of the road section, the technical problem of low running property of the predicted running track caused by mismatching of the predicted running track and the map information in the related technology is solved, and the technical effect of improving the running property of the predicted running track is realized.

As an optional embodiment, step S104, the target driving rule is determined by a priori driving information of the autonomous vehicle, and determining at least one first predicted driving track conforming to the target driving rule in the at least one predicted driving track includes: and determining the predicted running track matched with the prior running information as a first predicted running track in at least one predicted running track.

In this embodiment, the target travel rule may be determined from a priori travel information of the autonomous vehicle. Among the at least one predicted travel locus, a predicted travel locus that matches the prior travel information may be determined, and the predicted travel locus that matches the prior travel information may be determined as the first predicted travel locus. The prior driving information may refer to rules or experiences that are easier for human beings to judge, for example, the prior driving information may be a track that needs to turn left on a special lane for turning left, needs to slow down when encountering a red light with a high probability, and cannot be taken out of a track point to fall back by a real obstacle, which is only an example, and the content of the prior driving information is not limited specifically. The a priori travel information may also be referred to as a priori knowledge (or a priori information).

Alternatively, a priori driving information may be acquired, where the a priori driving information may be information of driving experiences obtained in advance. At least one predicted travel track may be screened based on the prior travel information, a predicted travel track matching the prior travel information may be determined from the at least one predicted travel track, and the predicted travel track may be determined as a first predicted travel track.

For example, prior travel information may be obtained in advance and stored. The method comprises the steps of obtaining at least one predicted running track, determining a target running rule based on prior running information, processing the at least one predicted running track based on the target running rule, and determining a predicted running track matched with the target running rule in the at least one predicted running track to obtain a first predicted running track.

In the related art, only one predicted travel track is selected from at least one predicted travel track directly, and the automatic driving vehicle can travel according to the selected predicted travel, but the matching degree between the predicted travel track determined by the method and the road section is low, so that the vehicle cannot be effectively controlled. In the embodiment of the disclosure, the target running rule is determined based on the map information and the prior running information of the road section, the obtained at least one predicted running track is screened based on the target running rule to obtain the first predicted running track, and the final running track of the vehicle is determined based on the first predicted running track, so that the matching performance of the predicted running track and the road section is improved, and the safety in the running process of the vehicle is improved.

As an optional embodiment, step S106, determining, based on the track point on the first predicted travel track, the target lane corresponding to the first predicted travel track includes: and determining the target lane at least based on the last track point on the first predicted running track, wherein a plurality of track points on the first predicted running track are arranged according to the corresponding track direction.

In this embodiment, the first predicted travel track may be formed of a plurality of track points, and tracks obtained by arranging the plurality of track points in the corresponding track directions may be used. The target lane may be determined based at least on a last track point on the first predicted travel track.

Alternatively, a track point on the first predicted travel track may be determined, a last track point on the first predicted travel track point may be determined based on the track point, and the target lane may be determined based on the last track point.

As an alternative embodiment, determining the target lane based at least on the end trajectory point on the first predicted travel trajectory comprises: determining the candidate target lane as the target lane in response to the last track point being on the candidate target lane; alternatively, the target lane is determined based on a first orientation determined by the last two track points of the first predicted travel track and a second orientation of the last track point pointing to each of the at least one candidate target lane in response to the last track point not being in the candidate target lane.

In this embodiment, it is determined whether the last track point is on the candidate target lane. If it is determined that the last track point is on the candidate target lane, the candidate target lane may be determined as the target lane in response to the last track point being on the candidate target lane. If it is determined that the last track point is not located on the candidate target lane, determining a first orientation of a line segment formed by the last two track points of the first predicted driving track and a second orientation of the last track point pointing to each of the at least one candidate target lane in response to the last track point not being located on the candidate target lane. The target lane may be determined based on the first and second orientations. The candidate Target Lane may be an actual Target Lane (Target Lane), and there may be multiple candidate Target lanes. The first direction (obs_end_head) may be the direction of the last two track point links of the first predicted travel track. The second heading (pos_head) may be the heading of the exit point link where the last track point points to each candidate target lane.

In the disclosed embodiment, the target lane is determined based on the position where the last track point on the first predicted travel track is located. When the position of the last track point is on the candidate target lane, the candidate target lane can be determined as the target lane; when the position of the last track point is not on the candidate target lane, the target lane can be determined from the candidate target lane based on the second direction of the line of the exit point of the last track point pointing to the candidate target lane and the first direction of the line of the last two track points, so that the efficiency of path planning is improved, and the problem of low path planning efficiency caused by the fact that the planned path cannot run is solved.

Alternatively, when determining the target lane, if the last track point has stepped on the candidate target lane, the candidate target lane may be determined as the exit lane, and the candidate target lane may be determined as the target lane. If the last track point is not in the candidate target lane, a first orientation may be determined based on the last two track points of the first predicted travel track, a second orientation may be determined based on the last track point, and the target lane may be determined based on the first orientation and the second orientation.

For example, it may be determined whether the last track point of the predicted travel track is on the candidate target lane (may be the exit actual lane). If it is determined that the last track point is on the candidate Target Lane, the candidate Target Lane may be determined as a Target Lane. If it is determined that the last track point is not on the exit passage, a first orientation may be determined based on the last two track points of the predicted travel track, and a second orientation in which the last track point points to the candidate target lane may be determined based on the first orientation and the second orientation.

As an alternative embodiment, determining the target lane based on a first orientation determined by the last two track points of the first predicted travel track and a second orientation of the last track point pointing to each of the at least one candidate target lane comprises: determining a second heading having a smallest angle with the first heading in at least one candidate target lane; and determining the candidate target lane corresponding to the determined second direction as the target lane.

In this embodiment, if the last track point is not in the candidate target lane, a first orientation of a line segment connecting the last two track points of the low first predicted driving track and a second orientation of the last track point to each of the at least one candidate target lane may be determined, resulting in at least one second orientation. And respectively determining an angle between the first direction and each second direction, determining a second direction with the smallest angle formed by the first direction from the angles, and determining a candidate target lane corresponding to the determined second direction as the target lane. Wherein the angle between the second orientation and the first orientation may be used to represent the difference between the first orientation and the second orientation.

Alternatively, if the last trajectory point is not in the candidate target lane, the first direction and the second direction may be determined, the second direction having the smallest angle with the first direction may be determined, the angle between the first direction and the second direction may be determined by the following formula, and the candidate target lane corresponding to the determined second direction angle may be determined as the target lane:

fabs(Obs_end_heading-pos_heading)

where obs_end_header may be used to represent a first orientation, pos_header may be used to represent a second orientation, and fabs () may be used to represent an absolute value of a difference between the first orientation and the second orientation.

As an optional embodiment, the road coordinate system on which the road segment is located includes a first coordinate axis and a second coordinate axis, and determining, based on the track point on the first predicted travel track, the target lane corresponding to the first predicted travel track includes: determining the time when a track point on the first predicted running track moves to each candidate target lane in at least one candidate target lane according to the first coordinate axis; determining the offset when the track point on the first predicted running track moves to the candidate target lane according to the second coordinate axis according to time; the target lane is determined based on the offset.

In this embodiment, the road coordinate system on which the road segment is located may include a first coordinate axis and a second coordinate axis. The time when the track point on the first predicted running track moves to each candidate target lane in the at least one candidate target lane according to the first coordinate axis is determined, the offset when the track point on the first predicted running track moves to the candidate target lane according to the second coordinate axis can be determined according to the time, and the target lane can be determined based on the offset. Wherein the first coordinate axis may be a road longitudinal coordinate axis (S). The second coordinate axis may be a lateral coordinate axis (L) of the road.

Alternatively, a first coordinate axis and a second coordinate axis in a road coordinate system on which the road section is located may be determined, a time when the track point on the first predicted travel track moves to each candidate target lane in the at least one candidate target lane according to the first coordinate axis may be determined, an arrival time may be obtained, an offset amount when the track point on the first predicted travel track moves to the candidate target lane according to the second coordinate axis may be determined based on the arrival time, and the target lane may be determined based on the offset amount.

For example, the arrival time of the autonomous vehicle longitudinally to the candidate target lane may be determined from the projection (v_s) of the speed of the autonomous vehicle on the road longitudinal coordinate axis and the road longitudinal coordinate (S). The offset of the autonomous vehicle in the lateral coordinate system may be determined from the projection (v_l) of the arrival time, velocity on the lateral coordinate axis of the road, and the target lane may be determined based on the offset.

As an alternative embodiment, determining the target lane based on the offset includes: and determining the candidate target lane corresponding to the minimum offset as the target lane in the at least one candidate target lane.

In this embodiment, the offset amount of each candidate target lane may be determined, and the candidate target lane corresponding to the minimum offset amount may be determined as the target lane among at least one candidate target lane.

In the embodiment of the disclosure, a road coordinate system is established, and the time for a track point on a first predicted running track to move to each candidate target lane in at least one candidate target lane according to a first coordinate axis in the road coordinate system is determined; determining the offset of a track point on the first predicted running track according to time when the track point moves to a candidate target lane according to a second coordinate axis in a road coordinate system; and determining the candidate target lane with the minimum offset as the target lane, so that the most suitable target channel is selected from a plurality of candidate target channels, and the effect of improving the accuracy of predicting the path is achieved.

For example, the arrival time of the autonomous vehicle longitudinal direction to the candidate target lane may be determined from the projection of the speed of the autonomous vehicle on the road longitudinal axis. The offset of the automatic driving vehicle on the transverse coordinate axis can be determined according to the projection of the arrival time and the speed on the transverse coordinate axis of the road, and the candidate target lane corresponding to the minimum offset can be determined as the target lane.

As an alternative embodiment, a third orientation of the autonomous vehicle and a fourth orientation of each of the at least one candidate target lane are obtained; in response to the angle between the third and fourth directions meeting the angle threshold and the coordinate value of the autonomous vehicle moving on the second coordinate axis meeting the coordinate threshold, determining the candidate target lane as the target lane for target steering of the autonomous vehicle.

In this embodiment, a third heading of the autonomous vehicle and a fourth heading of each of the at least one candidate target lane may be obtained. It may be determined whether the angle between the third and fourth orientations meets an angle threshold. If an angle (heading_diff) between the third direction and the fourth direction satisfies an angle threshold value and a coordinate value of the autonomous vehicle moving on the second coordinate axis satisfies a coordinate threshold value, it may be determined that the candidate target lane may be a target lane for target steering of the autonomous vehicle. Wherein the third orientation may be the head orientation (current orientation) of the autonomous vehicle. The fourth direction may be the direction of the candidate target lane (exit direction). The angle threshold value (may also be referred to as a difference threshold value) and the coordinate threshold value (may also be referred to as a lateral distance threshold value) may be values set empirically or practically in advance, and the determination method of the angle threshold value and the coordinate threshold value is not particularly limited here. The target steering may be a preset steering, for example, left or right steering, which is only an example, and the target steering is not particularly limited. The coordinate value of the autonomous vehicle on the second coordinate axis may be a lateral distance (L) of the road autonomous on the second coordinate axis.

Alternatively, on a track or a left turn lane where a part of curvature is small, it is a good choice to determine left turn by using a scene, but it is not possible to accurately judge whether or not to turn left by only the head direction (third direction) of the autonomous vehicle and the direction (fourth direction) of the candidate target lane. Under the situation, the embodiment of the disclosure determines the candidate target lane as the target lane for enabling the automatic driving vehicle to conduct target steering by judging the angle between the third direction and the fourth direction of the automatic driving vehicle, and responding to the fact that the angle between the third direction and the fourth direction meets the angle threshold and the coordinate value of the automatic driving vehicle moving on the second coordinate axis meets the coordinate threshold, thereby achieving the technical effect of improving the accuracy of predicting the road and solving the technical problem that the road cannot be accurately predicted in the prior art.

For example, a difference (heading_diff) between the current heading of the head of the autonomous vehicle and the exit heading (lane_heading) of the candidate target Lane may be determined, resulting in an angle between the third heading and the fourth heading. Whether to select left turn can be determined by a lateral distance (L) and a head_diff judgment on the second coordinate axis. The coordinate threshold (lateral distance threshold), angle threshold (difference threshold) and target steering to left may be preset. It may be determined whether the coordinate value (lateral distance) of the autonomous vehicle on the second coordinate axis satisfies a coordinate threshold, and whether the angle between the third direction and the fourth direction satisfies an angle threshold. In response to the lateral distance meeting the coordinate threshold and the angle between the third and fourth directions meeting the angle threshold, a determination may be made that a left turn is required at this time, and the left candidate target lane may be determined to be the target lane for target steering of the autonomous vehicle; if the lateral distance does not meet the coordinate threshold and/or the angle between the third and fourth directions does not meet the angle threshold, it may be determined that no left turn is required for the autonomous vehicle at this time.

As an alternative embodiment, generating the second predicted travel track of the autonomous vehicle based on the track point and the target lane comprises: determining a target track point at a second moment on the target lane based on the track point at the first moment, wherein the second moment is after the first moment; a second predicted travel path is generated based at least on the path point at the first time and the target path point.

In this embodiment, the track point at the first time and the target track point at the second time on the target lane may be determined, and the second predicted travel track of the autonomous vehicle may be generated based on the track point at the first time and the target track point. The track point at the first time may be referred to as a constraint point, and the first time and the second time may be moments determined according to experiments or experience, for example, may be 5 seconds, 8 seconds, or the like, which is only used as an example, and the size and the determining manner of the first time and the second time are not specifically limited. The second time is after the first time. The Target track point may be a Target point (Target point) of a Target Lane, which may also be referred to as a road center point (Lane point).

For example, the constraint point may be determined based on an empirical value, so that the trajectory point at the first time may be determined, for example, a trajectory point of 5 seconds (5S) may be determined as the trajectory point at the first time. A target trajectory point at a second time subsequent to the first time is determined on the target lane, and a second predicted travel trajectory may be determined based on the constraint point and the target trajectory point by a spline (spline) algorithm.

In the embodiment of the disclosure, the second predicted running track is determined through the constraint point at the first moment and the target track point at the second moment, so that the technical problem that in the prior art, the predicted running track is directly predicted based on the road information, and the accuracy of track prediction is low is solved, the technical effect of improving the accuracy of track prediction is further realized, and the technical problem that the accuracy of track prediction is low is solved.

As an alternative embodiment, determining the target track point at the second time on the target lane based on the track point at the first time includes: and determining the target track point based on the track point at the first moment and the direction of the target lane.

In this embodiment, the speed of the autonomous vehicle reaching the target point may be determined based on the speed of the track point at the first time and the direction of the target lane, and if the speed reaching the target point exceeds the maximum speed preset in advance, the target track point may be determined by pushing backward along the target lane, so as to achieve the purpose of determining the target track point based on the track point at the first time and the direction of the target lane.

As an alternative embodiment, generating the second predicted travel track based on at least the track point at the first time and the target track point comprises: and generating a second predicted running track based on the track point at the third moment, the track point at the first moment and the target track point, wherein the third moment is before the first moment.

In this embodiment, the second predicted travel locus may be determined based on the locus point at the third time, the locus point at the first time, and the target locus point. The third time may be a time before the first time, may be a time preset according to experience, for example, may be 1 second, 3 seconds, etc., and is only used as an example herein, and the size and the determination manner of the third time are not specifically limited. The trajectory point at the third time may also be referred to as a constraint point, and may be used to determine the second predicted travel trajectory.

Alternatively, a third time, the first time, and the second time may be preset, where the third time is before the first time, and the first time is before the second time. The track point at the third time, the track point at the first time, and the target track point at the second time are determined, and a second predicted travel track may be generated based on the track point at the third time, the track point at the first time, and the target track point at the second time.

For example, the first time, the second time, and the third time may be determined based on empirical values, such as trajectory points of 1 second, 3 seconds, and 5 seconds may be determined as constraint points. A target trajectory point at a second time is determined on the target lane, and a trajectory line may be determined based on the constraint point and the target trajectory point.

As an alternative embodiment, in response to the second predicted travel track not conforming to the target travel rule, determining a track point at a fourth time on the second predicted travel track, wherein the fourth time is before the second time; and adjusting the second predicted running track at least based on the track point at the fourth moment and the target track point, wherein the adjusted second predicted running track accords with the target running rule.

In this embodiment, it may be determined whether the second predicted travel track meets the target travel rule, and in response to the second predicted travel track not meeting the target travel rule, a track point at a fourth time may be determined on the second predicted travel track. The second predicted travel track may be adjusted based on at least the track point at the fourth time and the target track point to obtain a second predicted travel track that meets the target travel rule. The fourth time may be a time preceding the second time, for example, when the second time is 8 seconds, the fourth time may be 4 seconds.

Optionally, the second predicted running track may be determined, whether the second predicted running track meets the target running rule may be determined, and in response to the second predicted running track not meeting the target running rule, the track point not meeting the target running rule may be deleted, and the track point at the fourth time before the second time may be determined, so as to complete the trace back. The second predicted running track can be adjusted based on the track point at the fourth time and the target track point, so that the second predicted running track conforming to the target running rule is obtained.

For example, when it is determined that the constraint point of the 5 second position exceeds the road center line, but the prohibited track point in the target driving rule exceeds the road center line, it may be determined that the second predicted driving track at this time does not conform to the target driving rule. Whether the 4-second track point exceeds the road center line or not can be further determined until the track point which does not exceed the road center line and faces the track point meeting the condition is found, so that the track point at the fourth moment is determined, and the second predicted running track can be adjusted based on the track point at the fourth moment, so that the second predicted running track meeting the target running rule is obtained.

In the related art, only track points are determined so as to determine a predicted running track, but the method cannot process the predicted running track based on priori knowledge and map information, and the predicted running track may not be driven normally or may have illegal risks in the driving process, so that the problem of low accuracy of the predicted running track exists. In order to avoid the above-mentioned problems, according to the embodiment of the present disclosure, the track points in the second predicted travel track are adjusted based on the target travel rule, so that the accuracy of the predicted travel track is improved, and the risk that the predicted travel track does not conform to the travel track or the traffic rule and similar problems are avoided.

As an optional embodiment, in response to the second predicted travel track being a retrograde track, determining that the second predicted travel track does not conform to the target travel rule, deleting the second predicted travel track; and in response to the autonomous vehicle being in an acceleration state and the longitudinal distance of the second predicted travel path meeting a first longitudinal distance threshold, or in response to the autonomous vehicle being in a deceleration state and the longitudinal distance of the second predicted travel path meeting a second longitudinal distance threshold, determining that the second predicted travel path does not meet the target travel rule, adjusting the longitudinal distance of the second predicted travel path based on the acceleration of the autonomous vehicle, wherein the first longitudinal distance threshold is determined based on the current speed and the acceleration of the autonomous vehicle, and the second longitudinal distance threshold is determined based on the acceleration.

In this embodiment, it is determined whether the second predicted travel locus is a reverse travel locus, if the second predicted travel locus is a reverse travel locus, it may be determined that it is impossible to travel in the second predicted travel locus, in response to the second predicted travel locus being a reverse travel locus, it may be determined that the second predicted travel locus does not conform to the target travel rule, and the second predicted travel locus may be deleted.

In this embodiment, the running state of the autonomous vehicle may be determined. In response to the autonomous vehicle being in an accelerating state and the longitudinal distance of the second predicted travel track meeting the first longitudinal distance threshold, or in response to the autonomous vehicle being in a decelerating state and the longitudinal distance of the second predicted travel track meeting the second longitudinal distance threshold, it may be determined that the second predicted travel track does not meet the target travel rule. When the second predicted travel locus does not meet the target travel rule, the longitudinal distance of the second predicted travel locus may be adjusted based on the acceleration of the autonomous vehicle. The first longitudinal threshold may be a preset value, and may be a maximum longitudinal distance. The second longitudinal threshold may be a longitudinal distance threshold calculated based on acceleration.

In this embodiment, the determined second predicted travel track is preprocessed, the retrograde second predicted travel track is deleted, and the longitudinal distance of the second predicted travel track which does not conform to the target travel rule is adjusted, so that the second predicted travel track which conforms to the target travel rule is obtained, and the effects of improving the accuracy and the traveling performance of track prediction are further achieved.

For example, the retrograde second predicted travel trajectory may be deleted; or the second predicted travel locus may be adjusted according to the target travel rule. Wherein adjusting the second predicted travel track according to the target travel rule may include: the maximum longitudinal distance may be calculated based on the current speed and the maximum acceleration of the autonomous vehicle, and when the determined longitudinal distance of the trajectory line (second predicted travel locus) is greater than the longitudinal distance, it may be determined that the second predicted travel locus does not conform to the target travel rule, the shape of the second predicted travel locus may be unchanged, and the longitudinal distance of the second predicted travel locus may be adjusted based on the acceleration of the current autonomous vehicle, to obtain the adjusted second predicted travel locus. Or when the automatic driving vehicle is in a decelerating state and the longitudinal distance of the second predicted running track is smaller than the longitudinal distance threshold calculated based on the acceleration when the automatic driving vehicle is continuously decelerating for 5 frames, responding to the automatic driving vehicle in the decelerating state and the longitudinal distance of the second predicted running track meets the second longitudinal distance threshold, determining that the second predicted running track does not accord with the target running rule, keeping the shape of the second predicted running track unchanged, and adjusting the longitudinal distance of the track line based on the current acceleration to obtain the adjusted second predicted running track.

As an alternative embodiment, determining at least one first predicted travel track that meets the target travel rule in the at least one predicted travel track includes: selecting the predicted running tracks of the target number, the probability value of which meets the probability threshold value, from at least one predicted running track; and respectively removing abnormal track points from the predicted running tracks of the target number, or removing the abnormal predicted running tracks from the predicted running tracks of the target number to obtain at least one first predicted running track.

In this embodiment, among at least one predicted travel track, a target number of predicted travel tracks whose probability value satisfies the probability threshold may be selected, and the abnormal track points in the target number of predicted travel tracks may be removed respectively, or the abnormal predicted travel track may be removed from the target number of predicted travel tracks, thereby obtaining at least one first predicted travel track. The probability threshold may be a value set empirically in advance.

For example, a predicted travel locus of the number of targets (for example, three predicted travel loci may be selected), a predicted travel locus probability, and as close to 1 as possible may be selected. The plurality of predicted travel tracks (anchor tracks) are ordered based on the probability values of the predicted travel track predictions, and the first predicted travel track (TOP 1) can be output when the probability value of the first predicted travel track is greater than 0.5 and the probability value of the second predicted travel track (Top 2) is less than 0.3 (Top 1>0.5& Top2< 0.3), so as to obtain at least one first predicted travel track. When the probability value of the first predicted travel track is greater than 0.5 and the probability value of the second predicted travel track is greater than 0.3 or the probability value of the first predicted travel track is between 0.3 and 0.5 (Top 1>0.5& Top2> 0.3|0.3 < Top1< 0.5), the first predicted travel track and the second predicted travel track may be output to obtain two first predicted travel tracks. When the probability value of the first predicted running track is smaller than 0.3, outputting the first three predicted running tracks to obtain three first predicted running tracks. It should be noted that the number of the first predicted running tracks is merely illustrative, and the number of the first predicted running tracks is not specifically limited herein. Unreasonable trajectory points may be determined based on prior knowledge and map information, and unreasonable trajectory points and/or trajectory lines may be deleted.

In the embodiment of the disclosure, a reasonable first predicted running track conforming to the target running rule is determined from at least one predicted running track of the automatic driving vehicle, and a corresponding target lane (exit lane) is determined based on a reasonable track point on the first predicted running track, so that a second predicted running track conforming to the target running rule is generated based on the reasonable track point and the target lane, thereby achieving the technical effect of effectively generating the running track of the automatic driving vehicle and solving the technical problem that the running track of the automatic driving vehicle cannot be effectively generated.

The embodiment of the present disclosure further provides another method for generating a predicted driving track of an automatic driving vehicle from a man-machine interaction side, fig. 2a is a flowchart of another method for generating a predicted driving track of an automatic driving vehicle according to an embodiment of the present disclosure, and as shown in fig. 2a, an implementation of the method for generating a predicted driving track of an automatic driving vehicle may at least include the following implementation steps:

step S202, at least one predicted running track output by a track prediction model is displayed on an operation interface, wherein the track prediction model is used for predicting the running track of the automatic driving vehicle.

In the technical solution provided in the above step S202, the track prediction model predicts the running track of the automatic driving vehicle to obtain at least one predicted running track, and the at least one predicted running track output by the track prediction model may be displayed on the operation interface. The trajectory prediction model may be used to predict a driving trajectory of an autonomous vehicle, and it should be noted that, as long as the model can predict the driving trajectory of the autonomous vehicle, the type of the trajectory prediction model should not be specifically limited. The operation interface may be a display interface of the planning module, an interface of the mobile terminal, or the like, and is not particularly limited herein.

In step S204, at least one first predicted travel track conforming to a target travel rule is displayed on the operation interface, wherein the target travel rule is used for guiding the autonomous vehicle to travel on the road section in a normal travel state.

In the technical solution provided in step S204 of the present disclosure, at least one first predicted travel track that meets the target travel rule in the at least one predicted travel track may be displayed on the operation interface. The target driving rule may be a priori knowledge and/or map information, may be used to screen at least one predicted driving track, and may be used to guide the automatic driving vehicle to drive on the road section in a normal driving state. The normal running state may refer to a running state in which traffic regulations are not violated such as driving violations, reverse running, etc., and is merely an example, and the normal running state is not particularly limited. The first predicted travel path may be a reasonable path line of the at least one predicted travel path.

Alternatively, the target driving rule may be predetermined, at least one first predicted driving track conforming to the target driving rule among the at least one predicted driving track may be determined, and the at least one first predicted driving track may be displayed on the operation interface.

In step S206, in response to the track generation instruction acting on the operation interface, a second predicted running track of the at least one first predicted running track is displayed on the operation interface, where the second predicted running track is used to control the autonomous vehicle to run to the target lane, and is generated based on the track point on the first predicted running track and the target lane, the target lane is a lane to which the autonomous vehicle is to run and conforms to the target running rule, and the target lane is determined on the road section based on the track point on the first predicted running track.

In the technical solution provided in step S206, a track generation instruction on the operation interface may be obtained, and in response to the obtained track generation instruction, a second predicted running track of the at least one first predicted running track may be displayed on the operation interface. The second predicted driving track may be a driving track conforming to a target driving rule, and may be used to control the autonomous vehicle to drive into the target lane. The trajectory generation command may be a command input through a space in the operation interface and may be used to instruct a second predicted travel trajectory determined from the at least one first predicted travel trajectory.

For example, in response to a trajectory generation instruction acting on the operation interface, an orientation of a last trajectory point may be determined based on the trajectory point on the first predicted travel trajectory, a target lane corresponding to the first predicted travel trajectory and conforming to the target travel rule may be determined on the road section based on the orientation of the last trajectory point, and a second predicted travel trajectory of the autonomous vehicle may be generated based on the trajectory point and the target lane. A second predicted travel path of the at least one first predicted travel path may be displayed on the operator interface.

FIG. 2b is a schematic diagram of an operator interface on which at least one predicted travel path output by a path prediction model may be displayed, as shown in FIG. 2b, in accordance with an embodiment of the present disclosure; displaying at least one first predicted running track conforming to the target running rule in the at least one predicted running track on the operation interface; and a track generation instruction can be sent out by clicking a track generation control in the operation interface. And responding to a track generation instruction acted on the operation interface, and displaying a second predicted running track in the at least one first predicted running track on the operation interface.

Through the steps S202 to S206, displaying at least one predicted travel track outputted by a track prediction model on an operation interface, wherein the track prediction model is used for predicting the travel track of the automatic driving vehicle; displaying at least one first predicted running track conforming to a target running rule in at least one predicted running track on an operation interface, wherein the target running rule is used for guiding an automatic driving vehicle to run on a road section in a normal running state; and responding to a track generation instruction acted on the operation interface, displaying a second predicted running track in at least one first predicted running track on the operation interface, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to a target lane, the track point on the first predicted running track and the target lane are generated, the target lane is a lane to which the automatic driving vehicle is to run and accords with a target running rule, and the target lane is determined on a road section based on the track point on the first predicted running track. That is, in the embodiment of the present disclosure, a reasonable first predicted travel track that meets a target travel rule is determined from at least one predicted travel track of an autonomous vehicle, and a corresponding target lane (exit lane) is determined based on a reasonable track point on the first predicted travel track, so that a second predicted travel track that meets the target travel rule is generated based on the reasonable track point and the target lane, thereby achieving a technical effect of effectively generating a travel track of the autonomous vehicle, and solving a technical problem that the travel track of the autonomous vehicle cannot be effectively generated.

The foregoing technical solutions of the embodiments of the present disclosure are further described by way of example with reference to the preferred embodiments.

The predicted running track has a larger influence on the downstream planning module, and the reasonable and accurate predicted running track can better improve the intelligence and the running rationality of the automatic driving vehicle.

At present, a predicted running track is usually generated by outputting continuous points through a model, but the model is more in input and mostly in original perception information, and implicit knowledge which cannot be learned by the model exists, so that the output track points cannot guarantee to consider all expert priori information and cannot perfectly match current map information, obvious error tracks often occur, and meanwhile, the output discrete tracks cannot meet downstream requirements, for example, when the downstream needs 8 seconds of smooth continuous predicted running track, a plurality of discrete track points with larger intervals are intelligently output in the related technology.

In order to solve the problems, in the embodiment of the disclosure, discrete prediction model points, prior running information and map information are combined, a series of operations such as deleting and adjusting are performed on track points, finally, a spline algorithm is performed, a smooth curve is generated by constraint points, the requirement of an unmanned vehicle on a predicted running track is met, the predicted track is processed based on the prior running information and the map information, and the technical problem that in the prior art, the accuracy of the generated predicted running track is low due to the fact that the predicted running track is generated only through a track prediction model is solved.

Fig. 3 is a flowchart of a driving trajectory generation method according to an embodiment of the present disclosure, and as shown in fig. 3, the driving trajectory generation method combining trajectory prediction model output and map information and expert a priori information may include the following steps.

Step S302, selecting reasonable track points.

In this embodiment, the trajectory prediction model may predict a plurality of predicted travel trajectories, and may determine a trajectory in which the autonomous vehicle may travel according to a probability value of the predicted travel trajectories. The probability value may be determined according to actual experience, or may be calculated according to multiple experiments, and the method for determining the probability value is not particularly limited.

For example, a predicted travel locus of the number of targets (for example, three predicted travel loci may be selected), a predicted travel locus probability, and as close to 1 as possible may be selected. The plurality of predicted travel tracks may be ordered based on the predicted probability values, and the first predicted travel track may be output when the probability value of the first predicted travel track is greater than 0.5 and the probability value of the second predicted travel track is less than 0.3. The first predicted travel track and the second predicted travel track may be output when a probability value of the first predicted travel track is greater than 0.5 and a probability value of the second predicted travel track is greater than 0.3 or the probability value of the first predicted travel track is between 0.3 and 0.5 (Top 1>0.5& & Top2>0.3||0.3< Top1< 0.5). When the probability value of the first predicted travel track is smaller than 0.3, the first predicted travel track, the second predicted travel track and the third predicted travel track which are ranked three above can be output.

And step S304, deleting the unreasonable track points and/or track lines.

In this embodiment, an unreasonable trajectory point may be determined based on a priori knowledge and map information, and the unreasonable trajectory point and/or trajectory line may be deleted.

For example, fig. 4 is a schematic diagram of a track point outside an intersection according to an embodiment of the disclosure, as shown in fig. 4, when the track point is outside the intersection (Junction), it may be determined that an autonomous vehicle cannot walk out of such a track according to a priori knowledge and/or map information, and thus, deletion processing may be performed on the track point. Fig. 5 is a schematic diagram of a track point crossing boundary according to an embodiment of the present disclosure, as shown in fig. 5, when a predicted travel track crosses a non-traversable boundary or a yellow line, it may be determined that an autonomous vehicle cannot walk out of such a track according to a priori knowledge and/or map information, and thus deletion processing may be performed on the predicted travel track. Fig. 6 is a schematic diagram of rollback of a track point, as shown in fig. 6, when a predicted track point is rolled back, it may be determined that an autonomous vehicle cannot walk out of such a track according to a priori knowledge and/or map information, and thus the predicted travel track may be deleted.

Step S306, determining an exit lane based on the trajectory point.

In this embodiment, fig. 7 is a schematic diagram of a target lane selection according to an embodiment of the present disclosure, and as shown in fig. 7, it may be determined whether the last track point of the predicted travel track is on the candidate target lane (may be the actual exit lane). If the last track point is on the candidate Target Lane, the candidate Target Lane may be determined as a Target Lane (Target Lane). If the last track point is not on the exit channel, a first orientation may be determined based on the last two track points of the predicted travel track, and a second orientation in which the last track point points to the candidate target lane may be determined based on the first orientation and the second orientation.

Alternatively, the first orientation may be determined by the orientation of the last two track points, and the second orientation may be determined by the orientation of the last track point pointing to the candidate target lane. When the last track point is not located on the exit channel, the angle between the first direction and each second direction can be respectively determined, the second direction with the smallest angle formed by the first direction is determined, and the candidate target lane corresponding to the determined second direction is determined as the target lane. The difference in angle between the first orientation and each second orientation may be determined by the following equation:

fabs(Obs_end_heading-pos_heading)

Wherein obs_end_head may be used to represent the first orientation. pos_header may be used to represent a second orientation. fabs () may be used to represent the absolute value of the difference between the first orientation and the second orientation.

In this embodiment, for a predicted travel track with a small partial curvature, or on a left-turn lane, a better choice in left-turn can be obtained from scene reasoning, but it is difficult to judge only by head_diff.

Fig. 8 is a schematic diagram of an automatic driving vehicle direction according to an embodiment of the present disclosure, and as shown in fig. 8, a difference between a current direction of a vehicle head and an exit direction of a candidate target lane may be determined first, and whether to select left turn is determined through a lateral distance (L) and a head_diff judgment on a second coordinate axis. For example, a transverse distance threshold and a difference threshold may be preset, whether the transverse distance meets the transverse distance threshold and the difference meets the difference threshold may be determined, and in response to the transverse distance meeting the transverse distance threshold and the difference meeting the difference threshold, it may be determined that a left turn is required at the time; if the lateral distance does not meet the lateral distance threshold and/or the difference does not meet the difference threshold, it may be determined that no left turn is needed at this time.

Fig. 9 is a schematic diagram of a target Lane selection according to an embodiment of the present disclosure, and as shown in fig. 9, an arrival time of an autonomous vehicle longitudinal direction to a Reference Lane may be determined from a projection (v_s) of a speed on a road longitudinal coordinate axis and the road longitudinal coordinate (S) with the candidate exit Lane as the Reference Lane. The offset of the autonomous vehicle on the lateral coordinate system can be determined according to the projection (v_l) of the arrival time and the speed on the lateral coordinate axis of the road, and the reference lane with the smallest offset can be determined as the target lane.

Step S308, generating a trajectory line based on the trajectory point and the exit lane.

In this embodiment, the trajectory points and the target points of the exit lane may be processed by a spline algorithm to obtain the trajectory line.

For example, fig. 10 is a schematic diagram of a constraint point selection according to an embodiment of the present disclosure, as shown in fig. 10, constraint points may be determined based on empirical values, for example, trajectory points of 1 second (1S), 3 seconds (3S), and 5 seconds (5S) may be determined as constraint points. A target point is determined on the target lane, and a trajectory line is determined based on the constraint point and the target point of the target lane. The Target point of the Target Lane may be a road center point (Lane point) of the Target Lane (Target Lane), the speed of the automatic driving vehicle reaching the Target point may be determined based on the speed of the last track point and the direction of the Target Lane, and if the speed reaching the Target point is too high, the constraint point may be traced back. Fig. 11a is a schematic diagram of a constraint point backtracking, as shown in fig. 11a, where constraint points may be found back, for example, when it is determined that a constraint point at a 5 second position exceeds a road center, it may be further determined whether a 4 second trajectory point exceeds a road center line until the found constraint point does not exceed the road center line and is toward a constraint point meeting a condition.

Alternatively, fig. 11b is a schematic diagram of a generated result of a trajectory line according to an embodiment of the present disclosure, and as shown in fig. 11b, the trajectory line may be determined based on the determined constraint point and the target point, and the autonomous vehicle may be controlled to drive according to the trajectory line.

Step S310, post-processing is performed on the track line.

In this embodiment, fig. 11c is a schematic diagram of a post-processing result of a trace line according to an embodiment of the present disclosure, and as shown in fig. 11c, to further improve accuracy of prediction of the trace line, an abnormal trace may be removed by a method of post-processing the trace line, for example, a retrograde trace may be deleted; or the track line can be adjusted according to the actual road condition to obtain the final predicted running track, such as the position pointed by the arrow in fig. 11 c.

Alternatively, the maximum longitudinal distance is calculated based on the current speed and the maximum acceleration of the autonomous vehicle, and when the determined longitudinal distance of the trajectory is greater than the maximum longitudinal distance, the shape of the trajectory may be unchanged, and the longitudinal distance of the trajectory is adjusted based on the current acceleration, resulting in an adjusted trajectory.

Alternatively, when the autonomous vehicle is decelerating for 5 consecutive frames and the longitudinal distance of the trajectory line is smaller than the longitudinal distance threshold calculated based on the acceleration, the shape of the trajectory line may be unchanged, and the longitudinal distance of the trajectory line may be adjusted based on the current acceleration, resulting in an adjusted trajectory line.

The embodiment of the disclosure also provides a predicted travel track generation device of the autonomous vehicle for executing the predicted travel track generation method of the autonomous vehicle of the embodiment shown in fig. 1.

Fig. 12 is a schematic diagram of a predicted travel track generation device of an autonomous vehicle according to an embodiment of the present disclosure. As shown in fig. 12, the predicted travel track generation device 1200 of the autonomous vehicle may include: an acquisition unit 1202, a first determination unit 1204, a second determination unit 1206, and a generation unit 1208.

An acquisition unit 1202 for acquiring at least one predicted travel track of the autonomous vehicle.

The first determining unit 1204 is configured to determine at least one first predicted travel track that meets a target travel rule, where the target travel rule is used to guide the autonomous vehicle to travel on the road segment in a normal traveling state.

The second determining unit 1206 is configured to determine, on the basis of the track point on the first predicted driving track, a target lane corresponding to the first predicted driving track on the road segment, where the target lane is a lane to which the autonomous vehicle is to travel and meets a target driving rule.

A generating unit 1208 is configured to generate a second predicted travel track of the autonomous vehicle based on the track point and the target lane, where the second predicted travel track is used to control the autonomous vehicle to travel to the target lane.

Optionally, the first determining unit 1204 includes: and the first determining module is used for determining the predicted running track matched with the map information of the road section as a first predicted running track in at least one predicted running track.

Optionally, the first determining unit 1204 includes: and the second determining module is used for determining the predicted running track matched with the prior running information as the first predicted running track in at least one predicted running track.

Optionally, the second determining unit 1206 includes: and the third determining module is used for determining the target lane at least based on the last track point on the first predicted running track, wherein a plurality of track points on the first predicted running track are arranged according to the corresponding track directions.

Optionally, the third determining module includes: a first determining sub-module for determining the candidate target lane as the target lane in response to the last track point being on the candidate target lane; alternatively, the target lane is determined based on a first orientation determined by the last two track points of the first predicted travel track and a second orientation of the last track point pointing to each of the at least one candidate target lane in response to the last track point not being in the candidate target lane.

Optionally, the third determining module further includes: a second determining sub-module for determining a second heading having a smallest angle with the first heading in at least one candidate target lane; and determining the candidate target lane corresponding to the determined second direction as the target lane.

Optionally, the second determining unit 1208 includes: the first processing module is used for determining the time when the track point on the first predicted running track moves to each candidate target lane in the at least one candidate target lane according to the first coordinate axis; determining the offset when the track point on the first predicted running track moves to the candidate target lane according to the second coordinate axis according to time; the target lane is determined based on the offset.

Optionally, the processing module further comprises: and the second determining subunit is used for determining the candidate target lane corresponding to the minimum offset as the target lane in the at least one candidate target lane.

Optionally, the processing module further comprises: a first processing sub-module for acquiring a third orientation of the autonomous vehicle and a fourth orientation of each of the at least one candidate target lane; in response to the angle between the third and fourth directions meeting the angle threshold and the coordinate value of the autonomous vehicle moving on the second coordinate axis meeting the coordinate threshold, determining the candidate target lane as the target lane for target steering of the autonomous vehicle.

Optionally, the generating unit 1208 includes: the second processing module is used for determining a target track point at a second moment on the target lane based on the track point at the first moment, wherein the second moment is after the first moment; a second predicted travel path is generated based at least on the path point at the first time and the target path point.

Optionally, the second processing module includes: and the third determination subunit is used for determining the target track point based on the track point at the first moment and the direction of the target lane.

Optionally, the second processing module includes: and the generation subunit is used for generating a second predicted running track based on the track point at the third moment, the track point at the first moment and the target track point, wherein the third moment is before the first moment.

Optionally, the second processing module further comprises: the second processing submodule is used for determining a track point at a fourth moment on the second predicted running track in response to the fact that the second predicted running track does not accord with the target running rule, wherein the fourth moment is before the second moment; and adjusting the second predicted running track at least based on the track point at the fourth moment and the target track point, wherein the adjusted second predicted running track accords with the target running rule.

Optionally, the apparatus further comprises: the processing unit is used for responding to the second predicted running track as a retrograde track, determining that the second predicted running track does not accord with the target running rule and deleting the second predicted running track; and in response to the autonomous vehicle being in an acceleration state and the longitudinal distance of the second predicted travel path meeting a first longitudinal distance threshold, or in response to the autonomous vehicle being in a deceleration state and the longitudinal distance of the second predicted travel path meeting a second longitudinal distance threshold, determining that the second predicted travel path does not meet the target travel rule, adjusting the longitudinal distance of the second predicted travel path based on the acceleration of the autonomous vehicle, wherein the first longitudinal distance threshold is determined based on the current speed and the acceleration of the autonomous vehicle, and the second longitudinal distance threshold is determined based on the acceleration.

The embodiment of the disclosure also provides another predicted travel track generation device of the autonomous vehicle for executing the predicted travel track generation method of the autonomous vehicle of the embodiment shown in fig. 2.

Fig. 13 is a schematic diagram of another predicted travel track generation device of an autonomous vehicle according to an embodiment of the present disclosure. As shown in fig. 13, the predicted travel track generation device 1300 of the autonomous vehicle may include: a first display unit 1302, a second display unit 1304, and a third display unit 1306.

The first display unit 1302 is configured to display at least one predicted driving track output by a track prediction model on the operation interface, where the track prediction model is configured to predict a driving track of the autonomous vehicle.

The second display unit 1304 is configured to display, on the operation interface, at least one first predicted travel track that meets a target travel rule, where the target travel rule is used to guide the autonomous vehicle to travel on the road segment in a normal traveling state.

And a third display unit 1306, configured to display, on the operation interface, a second predicted travel track of the at least one first predicted travel track in response to a track generation instruction acting on the operation interface, where the second predicted travel track is used to control the autonomous vehicle to travel to the target lane, and is generated based on a track point on the first predicted travel track and the target lane, the target lane is a lane to which the autonomous vehicle is to travel and conforms to a target travel rule, and the target lane is determined on the road section based on the track point on the first predicted travel track.

In the predicted travel track generation device of the automatic driving vehicle in the embodiment of the disclosure, a reasonable first predicted travel track conforming to the target travel rule is determined from at least one predicted travel track of the automatic driving vehicle, a corresponding target lane (exit lane) is determined based on a reasonable track point on the first predicted travel track, so that a second predicted travel track conforming to the target travel rule is generated based on the reasonable track point and the target lane, thereby achieving the technical effect of effectively generating the travel track of the automatic driving vehicle and solving the technical problem that the travel track of the automatic driving vehicle cannot be effectively generated.

In the technical scheme of the disclosure, the acquisition, storage, application and the like of the related user personal information all conform to the regulations of related laws and regulations, and the public sequence is not violated.

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

Embodiments of the present disclosure provide an electronic device that may include: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method for generating a predicted travel track for an autonomous vehicle according to an embodiment of the present disclosure.

Optionally, the electronic device may further include a transmission device and an input/output device, where the transmission device is connected to the processor, and the input/output device is connected to the processor.

According to an embodiment of the present disclosure, an automatic driving vehicle is further provided, wherein the automatic driving vehicle may include the above-described electronic device.

According to an embodiment of the present disclosure, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing a computer to execute the predicted travel track generation method of the autonomous vehicle of the embodiment of the present disclosure.

Alternatively, in the present embodiment, the above-described nonvolatile storage medium may be configured to store a computer program for performing the steps of:

s1, acquiring at least one predicted running track of an automatic driving vehicle;

s2, determining at least one first predicted running track which accords with a target running rule in at least one predicted running track, wherein the target running rule is used for guiding an automatic driving vehicle to run on a road section in a normal running state;

s3, determining a target lane corresponding to the first predicted running track on the road section based on the track point on the first predicted running track, wherein the target lane is a lane which is to be driven by the automatic driving vehicle and accords with the target running rule;

And S4, generating a second predicted running track of the automatic driving vehicle based on the track points and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane.

Alternatively, in the present embodiment, the above-described nonvolatile storage medium may be further configured to store a computer program for performing the steps of:

s1, displaying at least one predicted running track output by a track prediction model on an operation interface, wherein the track prediction model is used for predicting the running track of an automatic driving vehicle;

s2, displaying at least one first predicted running track which accords with a target running rule in at least one predicted running track on an operation interface, wherein the target running rule is used for guiding an automatic driving vehicle to run on a road section in a normal running state;

and S3, responding to a track generation instruction acted on the operation interface, and displaying a second predicted running track in at least one first predicted running track on the operation interface, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to a target lane, and is generated based on a track point on the first predicted running track and the target lane, the target lane is a lane to which the automatic driving vehicle is to run and accords with a target running rule, and the target lane is determined on a road section based on the track point on the first predicted running track.

Alternatively, in the present embodiment, the non-transitory computer readable storage medium described above 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 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.

According to an embodiment of the present disclosure, the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of:

Optionally, in this embodiment, the above computer program may further implement the following steps when executed by a processor:

Fig. 14 is a block diagram of an electronic device of a predicted travel track generation method of an autonomous vehicle according to an embodiment 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 telephones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the disclosure described and/or claimed herein.

As shown in fig. 14, the apparatus 1400 includes a computing unit 1401 that can perform various appropriate actions and processes according to a computer program stored in a Read Only Memory (ROM) 1402 or a computer program loaded from a storage unit 1408 into a Random Access Memory (RAM) 1403. In the RAM1403, various programs and data required for the operation of the device 1400 can also be stored. The computing unit 1401, the ROM1402, and the RAM1403 are connected to each other through a bus 1404. An input/output (I/O) interface 1405 is also connected to the bus 1404.

Various components in device 1400 are connected to I/O interface 1405, including: an input unit 1406 such as a keyboard, a mouse, or the like; an output unit 1404 such as various types of displays, speakers, and the like; a storage unit 1408 such as a magnetic disk, an optical disk, or the like; and a communication unit 1409 such as a network card, a modem, a wireless communication transceiver, and the like. The communication unit 1409 allows the device 1400 to exchange information/data with other devices through a computer network such as the internet and/or various telecommunications networks.

The computing unit 1401 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of computing unit 1401 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various computing units running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 1401 performs the respective methods and processes described above, for example, a travel locus method of an autonomous vehicle. For example, in some embodiments, the method of generating a predicted travel track of an autonomous vehicle may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 1408. In some embodiments, part or all of the computer program may be loaded and/or installed onto the device 1400 via the ROM 1402 and/or the communication unit 1409. When a computer program is loaded into RAM1403 and executed by computing unit 1401, one or more steps of the data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 1401 may be configured to perform the predicted travel track generation 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 circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), complex Programmable Logic Devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.

Program code for carrying out methods of the present disclosure may be written in any combination of one or more programming languages. These program code 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 code, when executed by the processor or controller, causes the functions/operations specified in the flowchart and/or block diagram to be implemented. 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. The 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: other types of devices may also be used to provide interaction with a user, for example, feedback provided to the user may 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 input, speech input, or tactile input).

The systems and techniques described here can be implemented in a computing system that includes a background 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 background, 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 a client and a server. The client and server are typically 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 incorporating a blockchain.

It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps recited in the present disclosure may be performed in parallel or sequentially or in a different order, provided that the desired results of the technical solutions of the present disclosure are achieved, and are not limited herein.

The above detailed description should not be taken as limiting the scope of the present disclosure. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present disclosure are intended to be included within the scope of the present disclosure.

Claims

1. A predicted travel track generation method of an automatically driven vehicle, comprising:

acquiring at least one predicted running track of the automatic driving vehicle;

determining at least one first predicted running track conforming to a target running rule in the at least one predicted running track, wherein the target running rule is used for guiding the automatic driving vehicle to run on a road section in a normal running state;

Determining a target lane corresponding to the first predicted running track on the road section based on the track point on the first predicted running track, wherein the target lane is a lane which the automatic driving vehicle is to run to and accords with the target running rule;

and generating a second predicted running track of the automatic driving vehicle based on the track point and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane.

2. The method of claim 1, wherein the target travel rule is determined from map information of the road segment, and determining at least one first predicted travel track that meets the target travel rule among the at least one predicted travel track comprises:

and determining a predicted running track matched with the map information of the road section as the first predicted running track in the at least one predicted running track.

3. The method of claim 1, wherein the target travel rule is determined from a priori travel information of the autonomous vehicle, and wherein determining at least one first predicted travel track that meets the target travel rule among the at least one predicted travel track comprises:

And determining the predicted running track matched with the prior running information as the first predicted running track in the at least one predicted running track.

4. The method of claim 1, wherein determining a target lane corresponding to the first predicted travel track based on track points on the first predicted travel track comprises:

and determining the target lane at least based on the last track point on the first predicted running track, wherein a plurality of track points on the first predicted running track are arranged according to the corresponding track direction.

5. The method of claim 4, wherein determining the target lane based at least on the terminal track point on the first predicted travel track comprises:

determining the candidate target lane as the target lane in response to the last track point being on the candidate target lane; or alternatively, the process may be performed,

and determining the target lane based on a first orientation determined by the last two track points of the first predicted travel track and a second orientation of the last track point to each of at least one candidate target lane in response to the last track point not being in the candidate target lane.

6. The method of claim 5, wherein determining the target lane based on a first orientation determined by a last two trajectory points of the first predicted travel trajectory and a second orientation of the last trajectory point to each of at least one candidate target lane comprises:

determining, in the at least one candidate target lane, the second heading having the smallest angle with the first heading;

and determining the candidate target lane corresponding to the determined second direction as the target lane.

7. The method of claim 1, wherein the road coordinate system on the road segment includes a first coordinate axis and a second coordinate axis, and determining, based on the track point on the first predicted travel track, a target lane corresponding to the first predicted travel track includes:

determining the time when the track point on the first predicted running track moves to each candidate target lane in at least one candidate target lane according to the first coordinate axis;

determining the offset when the track point on the first predicted running track moves to the candidate target lane according to the second coordinate axis according to the time;

The target lane is determined based on the offset.

8. The method of claim 7, wherein determining the target lane based on the offset comprises:

and determining the candidate target lane corresponding to the minimum offset as the target lane in the at least one candidate target lane.

9. The method of claim 7, further comprising:

acquiring a third direction of the automatic driving vehicle and a fourth direction of each candidate target lane in at least one candidate target lane;

in response to the angle between the third and fourth orientations meeting an angle threshold and the coordinate value of the autonomous vehicle moving on the second coordinate axis meeting a coordinate threshold, the candidate target lane is determined to be the target lane for target steering of the autonomous vehicle.

10. The method of claim 1, wherein generating a second predicted travel track of the autonomous vehicle based on the track point and the target lane comprises:

determining a target track point at a second moment on the target lane based on the track point at a first moment, wherein the second moment is after the first moment;

And generating the second predicted running track at least based on the track point at the first moment and the target track point.

11. The method of claim 10, wherein determining a target track point at a second time on the target lane based on the track point at a first time comprises:

and determining the target track point based on the track point at the first moment and the direction of the target lane.

12. The method of claim 10, wherein generating the second predicted travel track based at least on the track point at the first time and the target track point comprises:

and generating the second predicted running track based on the track point at a third moment, the track point at the first moment and the target track point, wherein the third moment is before the first moment.

13. The method of claim 12, further comprising:

determining the track point at a fourth time on the second predicted travel track in response to the second predicted travel track not conforming to the target travel rule, wherein the fourth time is before the second time;

and adjusting the second predicted running track at least based on the track point at the fourth moment and the target track point, wherein the adjusted second predicted running track accords with the target running rule.

14. The method of claim 1, further comprising:

responding to the second predicted running track as a retrograde track, determining that the second predicted running track does not accord with the target running rule, and deleting the second predicted running track;

and in response to the autonomous vehicle being in an acceleration state and the longitudinal distance of the second predicted travel track meeting a first longitudinal distance threshold, or in response to the autonomous vehicle being in a deceleration state and the longitudinal distance of the second predicted travel track meeting a second longitudinal distance threshold, determining that the second predicted travel track does not meet the target travel rule, adjusting the longitudinal distance of the second predicted travel track based on an acceleration of the autonomous vehicle, wherein the first longitudinal distance threshold is determined based on a current speed of the autonomous vehicle and the acceleration, and the second longitudinal distance threshold is determined based on the acceleration.

15. The method according to any one of claims 1 to 14, wherein determining at least one first predicted travel path that meets the target travel rule among the at least one predicted travel path comprises:

Selecting the predicted running tracks of the target number, the probability value of which meets the probability threshold value, from the at least one predicted running track;

and respectively removing abnormal track points from the predicted track of the target number, or removing abnormal predicted track from the predicted track of the target number to obtain the at least one first predicted track.

16. A predicted travel track generation method of an automatically driven vehicle, comprising:

displaying at least one predicted running track output by a track prediction model on an operation interface, wherein the track prediction model is used for predicting the running track of the automatic driving vehicle;

displaying at least one first predicted running track conforming to a target running rule in the at least one predicted running track on an operation interface, wherein the target running rule is used for guiding the automatic driving vehicle to run on a road section in a normal running state;

and responding to a track generation instruction acted on the operation interface, displaying a second predicted running track in the at least one first predicted running track on the operation interface, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to a target lane, the second predicted running track is generated based on a track point on the first predicted running track and the target lane, the target lane is a lane to which the automatic driving vehicle is to run and accords with the target running rule, and the target lane is determined on the road section based on the track point on the first predicted running track.

17. A predicted travel locus generation device of an autonomous vehicle, comprising:

an acquisition unit for acquiring at least one predicted travel track of the autonomous vehicle;

the first determining unit is used for determining at least one first predicted running track which accords with a target running rule in the at least one predicted running track, wherein the target running rule is used for guiding the automatic driving vehicle to run on a road section in a normal running state;

a second determining unit, configured to determine, on the basis of a track point on the first predicted driving track, a target lane corresponding to the first predicted driving track on the road section, where the target lane is a lane to which the autonomous vehicle is to travel and meets the target driving rule;

and the generation unit is used for generating a second predicted running track of the automatic driving vehicle based on the track point and the target lane, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to the target lane.

18. A predicted travel locus generation device of an autonomous vehicle, comprising:

the first display unit is used for displaying at least one predicted running track output by a track prediction model on an operation interface, wherein the track prediction model is used for predicting the running track of the automatic driving vehicle;

The second display unit is used for displaying at least one first predicted running track which accords with a target running rule in the at least one predicted running track on the operation interface, wherein the target running rule is used for guiding the automatic driving vehicle to run on a road section in a normal running state;

and the third display unit is used for responding to a track generation instruction acted on the operation interface, displaying a second predicted running track in the at least one first predicted running track on the operation interface, wherein the second predicted running track is used for controlling the automatic driving vehicle to run to a target lane, and is generated based on a track point on the first predicted running track and the target lane, the target lane is a lane to which the automatic driving vehicle is to run and accords with the target running rule, and the target lane is determined on the road section based on the track point on the first predicted running track.

19. An electronic device, comprising:

at least one processor; and

a memory communicatively coupled to the at least one processor; wherein, the liquid crystal display device comprises a liquid crystal display device,

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 1-17.

20. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-17.

21. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any of claims 1-17.

22. An autonomous vehicle comprising the electronic device of claim 19.