Method, device and equipment for vehicle control and storage medium

Abstract

The embodiment of the invention provides a vehicle control method and device, electronic equipment and a storage medium. The method includes determining whether a minimum width of a drivable area associated with an autonomous vehicle satisfies a parallel passing condition in response to detecting a target vehicle running opposite to the autonomous vehicle, the parallel passing condition relating to a width of the autonomous vehicle and a width of the target vehicle; in response to determining that the minimum width does not meet the parallel passing condition, determining a meeting area meeting the parallel passing condition from the drivable areas; and controlling the autonomous vehicle based on the meeting area, so that the autonomous vehicle and the target vehicle oppositely pass through the meeting area. In this way, according to the embodiment of the invention, the problem of traffic jam or safety risk can be avoided, and the travel efficiency and travel reliability of the vehicle are improved.

Description

TECHNICAL FIELD

[0001] Example embodiments of the present disclosure generally relate to the field of computers, and in particular, to a method, an apparatus, a device and a computer readable storage medium for vehicle control. BACKGROUND

[0002] With the rapid development of transportation tools and the improvement of people's living standards, more and more people choose to travel by vehicle. How to select a suitable meeting area to control the autonomous vehicle and other vehicles to complete the meeting in a narrow road driving scene is a focus problem. SUMMARY

[0003] In a first aspect of the present disclosure, a method for vehicle control is provided. The method comprises: in response to detecting a target vehicle driving in the opposite direction of an autonomous vehicle, determining whether a minimum width of a drivable area associated with the autonomous vehicle satisfies a parallel passing condition, the parallel passing condition being related to a width of the autonomous vehicle and a width of the target vehicle; in response to determining that the minimum width does not satisfy the parallel passing condition, determining a meeting area from the drivable area that satisfies the parallel passing condition; and controlling the autonomous vehicle based on the meeting area, so that the autonomous vehicle and the target vehicle pass in the opposite direction within the meeting area.

[0004] In a second aspect of the present disclosure, an apparatus for vehicle control is provided. The apparatus comprises: a first determining module configured to, in response to detecting a target vehicle driving in the opposite direction of an autonomous vehicle, determine whether a minimum width of a drivable area associated with the autonomous vehicle satisfies a parallel passing condition, the parallel passing condition being related to a width of the autonomous vehicle and a width of the target vehicle; a second determining module configured to, in response to determining that the minimum width does not satisfy the parallel passing condition, determine a meeting area from the drivable area that satisfies the parallel passing condition; and a control module configured to control the autonomous vehicle based on the meeting area, so that the autonomous vehicle and the target vehicle pass in the opposite direction within the meeting area.

[0005] In a third aspect of the present disclosure, an electronic device is provided. The device comprises at least one processing unit; and at least one memory coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit. The instructions, when executed by the at least one processing unit, cause the device to perform the method of the first aspect.

[0006] In a fourth aspect of the present disclosure, a computer readable storage medium is provided. The computer readable storage medium has stored thereon a computer program, the computer program being executable by a processor to implement the method of the first aspect.

[0007] It is to be understood that the content described in this Background section is not to be taken as an acknowledgement that this content is prior art to the present disclosure relative to any present or future application. The content described in this Background section is to be taken as an enabling disclosure to one of ordinary skill in the art. BRIEF DESCRIPTION OF DRAWINGS

[0008] The above and other features, aspects, and advantages of various embodiments of the present disclosure will become more apparent from the following detailed description when taken in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements, wherein: FIG. 1 A schematic diagram showing an example environment in which embodiments of the present disclosure can be implemented is shown; FIG. 2 A flow diagram showing a process for vehicle control according to some embodiments of the present disclosure is shown; FIGS. 3A-3E A driving scenario diagram is shown for the present disclosure according to some embodiments of the present disclosure; FIG. 4 A flow diagram showing generation of a driving trajectory according to certain embodiments of the present disclosure is shown; FIG. 5 A schematic block diagram showing an apparatus for vehicle control according to certain embodiments of the present disclosure is shown; FIG. 6 A block diagram of an electronic device capable of implementing various embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0009] Embodiments of the present disclosure will be described more fully hereinafter with reference to the accompanying drawings. While several embodiments of the present disclosure are described, it should be understood that the present disclosure can be embodied in many other forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and fully convey the scope of the present disclosure to those skilled in the art.

[0010] It should be noted that the headings provided herein are for the convenience of the reader and are not to be construed as limiting the present disclosure. Various embodiments are described throughout this document, and any type of embodiment can be included under any heading. Further, embodiments described in any heading can be combined with any other embodiment described in the same heading and / or in a different heading.

[0011] In the description of embodiments of the disclosure, the term "includes" and its conjugates are to be construed as open-ended, i.e., "includes but is not limited to". The term "based on" is to be construed as "based at least in part on". The term "one embodiment" or "an embodiment" is to be construed as "at least one embodiment". The term "some embodiments" is to be construed as "at least some embodiments". The terms "a" or "an", as used herein, are defined as "one or more" or "at least one" and can be used interchangeably with "one or more" or "at least one". The term "another" as used herein, is defined as "one or more, i.e., at least one, in addition to the one or more already mentioned". The terms "comprises", "comprising", "comprised of", "comprising of", "containing", "containing" and "having" are to be construed as "including". The term "automatically" is to be construed as "at least partially automatically". The term "another" is to be construed as "one or more, i.e., at least one, in addition to the one or more already mentioned". The terms "comprises", "comprising", "comprised of", "comprising of", "containing", "containing" and "having" are to be construed as "including". The term "automatically" is to be construed as "at least partially automatically". The following description can include examples, aspects, and / or implementations that contain various features, which can be applied in various combinations and / or permutations. It is intended that each potential feature, aspect, and / or implementation can be combined with any other potential feature, aspect, and / or implementation. The following description is not meant to be limiting.

[0012] Embodiments of the present disclosure can involve data of users, acquisition and / or use of data, etc. These aspects are subject to the corresponding laws and regulations and relevant provisions. In embodiments of the present disclosure, all data collection, acquisition, processing, processing, forwarding, use, etc. are carried out on the premise that the user is aware of and confirms. Accordingly, in the implementation of various embodiments of the present disclosure, the type of data or information that can be involved, the scope of use, the use scenario, etc. should be informed to the user and authorized by the user in a proper manner according to the relevant laws and regulations. The specific notification and / or authorization method can vary according to the actual situation and application scenario, and the scope of the present disclosure is not limited in this regard.

[0013] In the schemes in the specification and embodiments, if personal information processing is involved, it will be processed on the premise of legality (for example, with the consent of the subject of personal information, or as necessary for the performance of a contract, etc.), and only within the scope prescribed or agreed. Users refuse to process personal information other than the necessary information required for basic functions, which will not affect the user's use of basic functions.

[0014] Example Environment FIG. 1 A schematic diagram of an example environment 100 in which various embodiments of the present disclosure can be implemented is shown. In this example environment 100, some typical objects are schematically shown, including an autonomous vehicle 110 and a target vehicle 130 traveling on a road, where the target vehicle 130 can be a vehicle traveling in the opposite direction of the autonomous vehicle 110.

[0015] In FIG. 1 In the example, the autonomous vehicle 120 or the target vehicle 130 can be any type of vehicle that can carry people and / or objects and move by a power system such as an engine. Examples of the vehicle 120 include, but are not limited to, a car, a truck, a bus, an electric vehicle, a motorcycle, a house car, a train, etc.

[0016] In some embodiments, the autonomous vehicle 110 or the target vehicle 130 in environment 100 is a vehicle with certain assisted driving capabilities or autonomous driving capabilities; such vehicles are also referred to as intelligent driving vehicles. Of course, the target vehicle 130 can also be a non-intelligent driving vehicle, that is, an ordinary vehicle without assisted driving capabilities.

[0017] In some embodiments, the electronic device 120 may be communicatively coupled to the autonomous vehicle 110. Although shown as a separate entity, the electronic device 120 may also be embedded within the autonomous vehicle 110. Alternatively, the electronic device 120 may also be an entity external to the autonomous vehicle 110 and may communicate with the autonomous vehicle 110 via a wireless network.

[0018] like FIG. 1 As shown, in response to detecting a target vehicle 130 traveling in the opposite direction to the autonomous vehicle 110, the electronic device 120 determines whether the minimum width of the drivable area associated with the autonomous vehicle 110 satisfies the parallel passage condition, which is related to the width of the autonomous vehicle 110 and the width of the target vehicle 130. Further, in response to determining that the minimum width does not satisfy the parallel passage condition, the electronic device 120 can determine a meeting area from the drivable area that satisfies the parallel passage condition. Further, the electronic device 120 can control the autonomous vehicle 110 based on the meeting area, so that the autonomous vehicle 110 and the target vehicle 130 pass in the opposite direction within the meeting area.

[0019] It should be understood that the structure and function of the various elements in environment 100 are described for illustrative purposes only and do not imply any limitation on the scope of this disclosure.

[0020] Traditionally, when an autonomous vehicle gets stuck in a narrow road encounter, it can send a distress signal to a remote device, allowing a user associated with that device to manually drive through. However, this method is inefficient. Alternatively, a user associated with the remote device can generate a distress trajectory by drawing points (also known as key points). This method often relies on the user's knowledge and experience, resulting in low accuracy. In other words, current traditional methods are insufficient for efficiently and accurately handling oncoming traffic in narrow road situations, potentially leading to vehicle entrapment, traffic congestion, and even safety risks.

[0021] Embodiments of the present disclosure propose a scheme for vehicle control, which can determine whether a minimum width of a drivable region associated with an autonomous vehicle satisfies a side-by-side passing condition in response to detecting a target vehicle traveling in an opposite direction of the autonomous vehicle, the side-by-side passing condition being related to a width of the autonomous vehicle and a width of the target vehicle. Further, a meeting region that satisfies the side-by-side passing condition can be determined from the drivable region in response to determining that the minimum width does not satisfy the side-by-side passing condition. Further, the autonomous vehicle can be controlled based on the meeting region to cause the autonomous vehicle and the target vehicle to pass in the meeting region in opposite directions.

[0022] According to embodiments of the present disclosure, the problem of traffic congestion or safety risk can be avoided, and the travel efficiency and reliability of the vehicle can be improved.

[0023] Example Process FIG. 2 A flowchart illustrating a process 200 for vehicle control according to some embodiments of the present disclosure is shown. The process 200 can be implemented at the electronic device 120. The process 200 is described below with reference to FIG. 1 The process 200 is described.

[0024] At block 210, the electronic device 120 determines whether a minimum width of a drivable region associated with the autonomous vehicle 110 satisfies a side-by-side passing condition in response to detecting a target vehicle 130 traveling in an opposite direction of the autonomous vehicle 110, the side-by-side passing condition being related to a width of the autonomous vehicle 110 and a width of the target vehicle 130.

[0025] In some embodiments, the autonomous vehicle 110 can be a vehicle that navigates and travels independently of human operation, which has certain assisted driving capability or automatic driving capability, such a vehicle is also referred to as an intelligent driving vehicle.

[0026] In some embodiments, the target vehicle 130 can also be another autonomous vehicle 110 that has certain assisted driving capability or automatic driving capability, of course, it can also be a common vehicle that does not have assisted driving capability or automatic driving capability, which is not described here.

[0027] In some embodiments, the autonomous vehicle 110 or the target vehicle 130 can be any type of vehicle that can carry people and / or objects and move through a power system such as an engine. Examples of the autonomous vehicle 110 or the target vehicle 130 include, but are not limited to, a car, a truck, a bus, an electric vehicle, a motorcycle, a motor home, a train, and the like.

[0028] In some embodiments, the autonomous vehicle 110 can travel on any suitable road, and there is a drivable area associated with the autonomous vehicle 110 on this road, which can support the autonomous vehicle 110 to travel or park. In some embodiments, the drivable area can correspond to any suitable shape, such as a rectangle, a square, an irregular shape, etc.

[0029] In some embodiments, the target vehicle 130 can be a vehicle traveling in the opposite direction of the autonomous vehicle 110. As an example, the drivable area can include a first lane and a second lane, and the autonomous vehicle 110 corresponds to the first lane and the target vehicle 130 corresponds to the second lane, the first lane and the second lane correspond to different travel directions. The first lane and the second lane can also be referred to as opposite double lanes. FIG. 3A As an example, the autonomous vehicle 110 can travel northward on the lane 140-1, and the target vehicle 130 travels southward on the lane 140-2, where the lane 140-1 and the lane 140-2 are opposite double lanes.

[0030] Since there is a risk of being unable to pass in parallel in a narrow lane scenario within a certain period of time when the distance between the target vehicle and the autonomous vehicle is less than a threshold value, the detected distance between the target vehicle 130 and the autonomous vehicle 110 can be less than the threshold value. The threshold value can be, for example, 200m, 300m, etc.

[0031] The following describes the detection process corresponding to the target vehicle 130.

[0032] In some embodiments, the electronic device 120 can obtain the predicted trajectory information of the target vehicle 130. This predicted trajectory information can be determined and sent by any suitable vehicle management device, which is not described here. The predicted trajectory information can be travel data corresponding to the target vehicle 130 within a period of time after the current time. The travel data can include, but is not limited to, the position traveled to by the target vehicle 130 at each time in the future, the speed traveled, the direction traveled, etc.

[0033] In some embodiments, this predicted trajectory information can be determined based on the historical trajectory information of the target vehicle 130. The historical trajectory information can indicate the travel data of the target vehicle 130 within a period of time before the current time. The travel data can include, but is not limited to, the position traveled to by the target vehicle 130 at each time in the historical process, the speed traveled, the direction traveled, etc.

[0034] As an example, the autonomous vehicle 110 can travel northward on the lane 140-1, and the target vehicle 130 travels southward on the lane 140-2, where the lane 140-1 and the lane 140-2 are opposite double lanes. FIG. 3BAs an example, the current position of the target vehicle 130 is 150-1, the prediction trajectory information can indicate that the target vehicle 130 will travel to position 150-2 in the next 1st second, to position 150-3 in the 2nd second, to position 150-4 in the 3rd second, and so on.

[0035] Further, the electronic device 120 can determine that the target vehicle 130 travels towards the autonomous vehicle 110 in response to the prediction trajectory information indicating that the target vehicle 130 travels towards the direction of the autonomous vehicle 110 at a time period after the current time, and the autonomous vehicle 110 also travels towards the direction of the target vehicle 130.

[0036] Since there can be obstacles on the road, some areas on the road do not support the travel of the autonomous vehicle 110, and therefore, in order to accurately determine the drivable area associated with the autonomous vehicle 110, the electronic device 120 can determine the drivable area associated with the autonomous vehicle 110 based on the boundary information corresponding to the road associated with the autonomous vehicle 110 and the obstacle information associated with the road.

[0037] The boundary information can be a pre-labeled boundary of the boundary of the road. Specifically, the labeled boundary can be a boundary labeled in advance for any appropriate curb on the road (such as the boundary of the curb of the first lane and the boundary of the curb of the second lane, etc.), a boundary labeled for a building, etc. The obstacle information can be an object that hinders the travel of the autonomous vehicle 110 parked or moving on the road, such as a car parked on the road, a maintenance barrier set on the road, etc.

[0038] As an example, the electronic device 120 can determine a candidate travel area based on the boundary information corresponding to the road, the first position information of the autonomous vehicle 110, and the second position information of the target vehicle 130. The candidate travel area can be an area that can support the travel of the autonomous vehicle 110 in an ideal state without considering the obstacles on the road. The first position information can be the position information corresponding to the tail of the autonomous vehicle 110, and can also be position information determined based on the position information corresponding to the tail of the autonomous vehicle 110 and the preset buffer information, such as position information determined by moving a preset distance backward from the position information of the tail, where backward is the direction away from the head of the autonomous vehicle 110. The second position information can be the position information corresponding to the tail of the target vehicle 130, and can also be position information determined based on the position information corresponding to the tail of the target vehicle 130 and the preset buffer information, such as position information determined by moving a preset distance backward from the position information of the tail, where backward is the direction away from the head of the target vehicle 130.

[0039] For example, the electronic device 120 can determine a first lateral boundary of the candidate travel region based on the first location information of the autonomous vehicle 110. The electronic device 120 can also determine a second lateral boundary of the candidate travel region based on the second location information of the target vehicle 130. The electronic device 120 can further determine two longitudinal boundaries based on the hard boundaries corresponding to the two sides of the road. Further, the electronic device 120 can determine the candidate travel region based on the first lateral boundary, the second lateral boundary, and the two longitudinal boundaries.

[0040] For example, the electronic device 120 can determine a first lateral boundary of the candidate travel region based on the first location information of the autonomous vehicle 110. The electronic device 120 can also determine a second lateral boundary of the candidate travel region based on the second location information of the target vehicle 130. The electronic device 120 can further determine two longitudinal boundaries based on the hard boundaries corresponding to the two sides of the road. Further, the electronic device 120 can determine the candidate travel region based on the first lateral boundary, the second lateral boundary, and the two longitudinal boundaries. FIG. 3C As an example, the electronic device 120 can determine the candidate travel region 160-1 based on the boundary information corresponding to the road 140, the first location information of the autonomous vehicle 110, and the second location information of the target vehicle 130, where the first lateral boundary of the candidate travel region 160-1 is the lower boundary of the candidate travel region 160-1, the second lateral boundary of the candidate travel region 160-1 is the upper boundary of the candidate travel region 160-1, and the two longitudinal boundaries of the candidate travel region 160-1 are the left boundary and the right boundary of the candidate travel region 160-1, respectively.

[0041] Further, the electronic device 120 can determine, based on the obstacle information, at least one non-travelable region corresponding to at least one obstacle located in the candidate travel region. In some embodiments, the at least one obstacle can be any suitable type of object, such as a vehicle parked in a parking spot on the road 140, a flower bed, a maintenance barrier, and the like.

[0042] For example, the electronic device 120 can determine a first lateral boundary of the candidate travel region based on the first location information of the autonomous vehicle 110. The electronic device 120 can also determine a second lateral boundary of the candidate travel region based on the second location information of the target vehicle 130. The electronic device 120 can further determine two longitudinal boundaries based on the hard boundaries corresponding to the two sides of the road. Further, the electronic device 120 can determine the candidate travel region based on the first lateral boundary, the second lateral boundary, and the two longitudinal boundaries. FIG. 3C As an example, the at least one obstacle located in the candidate travel region 160-1 can include the obstacle 161-1, the obstacle 161-2, the obstacle 161-3, and the obstacle 161-4. The non-travelable region can include the region corresponding to the object boxes of the four obstacles in the candidate travel region 160-1.

[0043] Further, the electronic device 120 can determine, based on the candidate travel region and the non-travelable region, a travelable region. As an example, the electronic device 120 can remove the non-travelable region from the candidate travel region to obtain the travelable region. For example, FIG. 3D As an example, the electronic device 120 can remove the non-travelable region corresponding to the obstacle 161-1, the obstacle 161-2, the obstacle 161-3, and the obstacle 161-4 from the candidate travel region 160-1 to determine the travelable region 160-2.

[0044] Further, the electronic device 120 can determine whether a minimum width of the travelable region associated with the autonomous vehicle 110 satisfies the side-by-side passing condition.

[0045] The boundaries of the drivable region can be composed of points at a predetermined resolution, and thus the width of the drivable region can be the distance between a point of one longitudinal boundary and a corresponding point of another longitudinal boundary, where the two points are at a horizontal location. The minimum width can also be referred to as a minimum lateral distance of the drivable region.

[0046] Since the drivable region can be an irregularly shaped region, the drivable region can correspond to multiple widths. For example, the width of the drivable region can be the distance between a point of one longitudinal boundary and a corresponding point of another longitudinal boundary, where the two points are at a horizontal location. FIG. 3D As an example, the minimum width of the drivable region 160-2 can be the width corresponding to the line segment 199, which is a schematic line segment and does not represent an actual line segment in a driving scenario.

[0047] In some embodiments, the side-by-side passing condition can indicate that the passable width reaches a width threshold. The passable width can indicate a width that both the autonomous vehicle 110 and the target vehicle 130 can pass through, including a width that the autonomous vehicle 110 and the target vehicle 130 can pass side-by-side.

[0048] To accurately determine whether the width of the drivable region can accommodate the autonomous vehicle 110 and the target vehicle 130 passing side-by-side, the width threshold can be determined based on a sum of a width of the autonomous vehicle 110 and a width of the target vehicle 130.

[0049] As an example, the electronic device 120 can determine whether the minimum width of the drivable region satisfies the side-by-side passing condition based on whether the minimum width of the drivable region is greater than a sum of a width of the autonomous vehicle 110 and a width of the target vehicle 130 (which can also be referred to as a width sum value). In particular, the electronic device 120 can determine that the minimum width of the drivable region associated with the autonomous vehicle 110 satisfies the side-by-side passing condition in response to determining that the minimum width is greater than the width sum value. The electronic device 120 can also determine that the minimum width of the drivable region associated with the autonomous vehicle 110 does not satisfy the side-by-side passing condition in response to determining that the minimum width is less than or equal to the width sum value.

[0050] At block 220, the electronic device 120 determines a passing region from the drivable region that satisfies the side-by-side passing condition in response to determining that the minimum width does not satisfy the side-by-side passing condition.

[0051] In some embodiments, the passing region can be a region that allows the autonomous vehicle 110 and the target vehicle 130 to pass side-by-side.

[0052] Since the regions in the drivable area that can support the autonomous vehicle 110 and the target vehicle 130 to pass each other can include multiple regions, in order to guarantee the quality of the trip, the electronic device 120 can select the optimal passing region from the at least one candidate region to pass each other after determining the at least one candidate region. Specifically, the electronic device 120 can determine at least one candidate region that satisfies the side-by-side passing condition from the drivable area.

[0053] As an example, the electronic device 120 can determine a set of candidate regions that satisfy the side-by-side passing condition from the drivable area, that is, a plurality of candidate regions that can support the autonomous vehicle 110 and the target vehicle 130 to pass each other are determined from the drivable area.

[0054] Since the width of some candidate regions can accommodate the autonomous vehicle 110 and the target vehicle 130 to pass each other, but these candidate regions can have unreasonable places, such as the autonomous vehicle 110 can not successfully enter a certain candidate region, or there is a risk of collision between the autonomous vehicle 110 and the target vehicle 130 based on a certain candidate region to pass each other, in order to guarantee the rationality of the candidate region and reduce the workload of subsequently determining the passing region used for passing each other, the electronic device 120 can determine at least one candidate region that satisfies the motion constraint from the set of candidate regions, and the motion constraint can be associated with the autonomous vehicle 110 and / or the target vehicle 130. In some embodiments, the motion constraint can indicate a physical limit of the autonomous vehicle 110 and / or the target vehicle 130, which is associated with the motion of the autonomous vehicle 110 and / or the target vehicle.

[0055] In some embodiments, the motion constraint can include but is not limited to at least one of the following: a first constraint related to the dynamics information of the autonomous vehicle 110; a second constraint related to the motion prediction of the target vehicle 130.

[0056] In some embodiments, the dynamics constraint can include but is not limited to constraints such as maximum acceleration, maximum deceleration, maximum steering angular velocity, curvature, minimum turning radius, etc. As an example, the first constraint can indicate that the candidate region can support the minimum turning radius of the autonomous vehicle 110 to be 5 meters, etc. As another example, the first constraint can indicate that the candidate region can support the maximum front wheel steering angle of the autonomous vehicle 110 to be 60 degrees.

[0057] In some embodiments, the second constraint related to the motion prediction of the target vehicle 130 can indicate that the candidate region is located between the predicted stop position corresponding to the target vehicle 130 and the position of the autonomous vehicle 110. The predicted stop position corresponding to the target vehicle 130 can be that the target vehicle 130 travels at a predetermined deceleration until the corresponding position when it stops.

[0058] In some embodiments, the autonomous vehicle 110 may be subject to certain constraints regarding its direction of travel during operation. These constraints may indicate aspects that are more conducive to safer travel and more in line with traffic requirements.

[0059] Specifically, the electronic device 120 can determine the detour direction of the autonomous vehicle 110 based on the driving direction constraints associated with the drivable area.

[0060] For example, since autonomous vehicle 110 should travel in lane 140-1 and target vehicle 130 should travel in lane 140-2, if there is a situation where target vehicle 130 and autonomous vehicle 110 cannot travel side by side, it is more in line with traffic and safety requirements for autonomous vehicle 110 to travel to the right. Therefore, when determining the meeting area, electronic device 120 can give priority to the area to the right of autonomous vehicle 110, that is, the detour direction is to the right.

[0061] Furthermore, the electronic device 120 can identify at least one obstacle in the drivable area associated with the detour direction, wherein the distance from the at least one obstacle to the opposite boundary of the drivable area does not satisfy the parallel passage condition. In some embodiments, the obstacle associated with the detour direction can be an obstacle on the road located in the detour direction; for example, if the detour direction is to the right, the obstacle associated with the detour direction can be an obstacle on the right side of the road. This at least one obstacle can be any suitable type of obstacle, such as a parked vehicle, a flower bed, etc.

[0062] by FIG. 3E As an example, the autonomous vehicle 110 is traveling in the right direction, so the obstacles associated with the travel direction can be obstacles 161-1, 161-2, 161-3 and 161-4 on the right lane (i.e. lane 140-1).

[0063] The opposite boundary of the drivable area can be the boundary of another direction opposite to the detour direction. For example, if the detour direction is to the right, then the opposite boundary is the left boundary 188.

[0064] Furthermore, the electronic device 120 can determine at least one candidate region from the drivable area based on at least one obstacle. As an example, the electronic device 120 can determine at least one sub-region corresponding to at least one obstacle from a longitudinal section of the drivable area, where the longitudinal section corresponds to a driving direction constraint. For example, if the driving direction is north-south, then this longitudinal section corresponds to a north-south oriented section. FIG. 3E As an example, the longitudinal section of the drivable area is the section indicated by line segment 189.

[0065] In some embodiments, the sub-interval corresponding to the obstacle can be a longitudinal interval corresponding to the obstacle, and the at least one candidate region can be determined from the longitudinal interval. FIG. 3E As an example, the sub-interval corresponding to the obstacle 161-3 is the interval indicated by the line segment 189-1. The sub-interval corresponding to the obstacle 161-2 is the interval indicated by the line segment 189-2.

[0066] Further, the electronic device 120 can remove at least one sub-interval from the longitudinal interval to determine at least one candidate region.

[0067] For ease of description, the sub-interval remaining after the removal of the at least one sub-interval from the longitudinal interval can be referred to as a target sub-interval. The target sub-interval can be one or more, such as, for example, FIG. 3E As an example, the target sub-interval can include three. If the target sub-interval includes multiple, the electronic device 120 can determine one candidate region from the target sub-interval for each target sub-interval. For example, a region corresponding to a predetermined size in the target sub-interval can be determined as a candidate region. For another example, the candidate region can also be determined based on the opposite boundary of the drivable region and the width of the target vehicle 130.

[0068] For example, the electronic device 120 can determine a region corresponding to the target sub-interval in the opposite boundary of the drivable region as a candidate region. FIG. 3E As an example, the electronic device 120 can move the sub-boundary corresponding to the target sub-interval in the opposite boundary of the drivable region to the width of the target vehicle 130 in the detour direction of the autonomous vehicle 110, and determine the moved sub-boundary as one longitudinal boundary of the candidate region. Further, the electronic device 120 can determine the sub-boundary corresponding to the target sub-interval in the detour direction boundary of the drivable region as another longitudinal boundary. Further, the electronic device 120 can connect the two end points of one longitudinal boundary to the two end points of another longitudinal boundary to determine the region formed as a candidate region.

[0069] For example, the electronic device 120 can determine a region corresponding to the target sub-interval in the opposite boundary of the drivable region as a candidate region. FIG. 3E As an example, the candidate region can include the candidate region 170-1, the candidate region 170-2, and the candidate region 170-3.

[0070] Further, the electronic device 120 can determine a passing region from the at least one candidate region.

[0071] As an example, the electronic device 120 can send an assistance request to the remote device, the assistance request indicating the at least one candidate region.

[0072] To reduce the workload of the remote device to confirm the passing area, in some embodiments, the electronic device 120 can determine whether the number of the at least one candidate area is greater than a threshold value before sending the assistance request to the remote device. The threshold value can be any appropriate value, such as 1. Further, the electronic device 120 can send the assistance request to the remote device in response to the number of the at least one candidate area being greater than the threshold value.

[0073] To improve the quality of the passing area selected for the vehicle to pass, in other embodiments, the electronic device 120 can also send the assistance request to the remote device in response to the confidence of the area selected from the at least one candidate area by the screening model being lower than a threshold value.

[0074] In some embodiments, the screening model can be any appropriate machine learning model that can be configured to select the passing area from the at least one candidate area for the vehicle to pass. In some embodiments, the screening model can be a model deployed on the autonomous vehicle 110.

[0075] That is, the electronic device 120 can also determine the passing area from the at least one candidate area for the vehicle to pass based on the screening model. Specifically, the electronic device 120 can provide the image and / or the description information associated with the at least one candidate area to the screening model. Further, the electronic device 120 can obtain the passing area selected by the screening model and the confidence corresponding to the passing area.

[0076] If the confidence is lower than the threshold value, it means that the selection result of the passing area output by the screening model is not accurate enough at this time, and therefore, in order to ensure the quality of the selected passing area, the electronic device 120 can send the assistance request to the remote device, so that the remote device can determine the passing area from the at least one candidate area for the vehicle to pass.

[0077] Since the passing area confirmed by the remote device has high quality, in order to improve the accuracy of the screening model, in some embodiments, the electronic device 120 can construct training data based on the passing area and the scene information. The scene information can be any appropriate information, such as the image and / or the description information associated with the at least one candidate area. The passing area can be used as the annotation information to participate in the training process of the screening model.

[0078] Further, the electronic device 120 can train the screening model deployed on the autonomous vehicle 110 using the training data, and the screening model is configured to screen the passing area from the at least one candidate area.

[0079] As an example, the electronic device 120 can provide the scene information to the screening model to obtain a predicted region output by the screening model. Further, the electronic device 120 can train the screening model based on the predicted region and the contrast of the meeting region until a predetermined training completion condition is reached, which can be that the loss value is less than a threshold, and the like, which will not be repeated here.

[0080] Of course, if the confidence is higher than or equal to the threshold, it means that the selection result of the meeting region output by the screening model is accurate enough at this time, so in order to reduce the interaction cost and improve the travel efficiency, the electronic device 120 can directly determine the meeting region output by the screening model as the final region used for the target vehicle 130 to meet, without performing the process of sending an assistance request to the remote device to enable the remote device to determine the meeting region for the meeting from the at least one candidate region.

[0081] Returning to the process of the remote device receiving the assistance request sent by the electronic device 120, further, the remote device can present an assistance interface, which is configured to provide remote assistance functions to the autonomous vehicle 110. Specifically, the remote device can present the at least one candidate region in the assistance interface in a preset style. The preset style can be any appropriate style, such as presenting the at least one candidate region in the form of a list, a grid, a map, and the like. FIG. 3E As an example, the remote device can present an assistance interface 300E as shown in FIG. 4 The assistance interface can present the candidate region 170-1, the candidate region 170-2, and the candidate region 170-3.

[0082] Further, the remote device can generate an assistance message based on the received confirmation of the meeting region in the group of candidate regions. As an example, the remote device can receive the confirmation of the candidate region (meeting region) 170-3 in response to receiving a click on the candidate region 170-3 in the assistance interface 300E. Further, the remote device can send the assistance message to the electronic device 120.

[0083] Further, the electronic device 120 can receive the assistance message from the remote device, and the assistance message indicates the confirmation of the meeting region in the group of candidate regions.

[0084] In block 230, the electronic device 120 controls the autonomous vehicle 110 based on the meeting region, so that the autonomous vehicle 110 and the target vehicle 130 pass through each other in the meeting region.

[0085] To successfully complete the passing, in some embodiments, the electronic device 120 can control the autonomous vehicle 110 to travel to the passing area. As an example, the electronic device 120 can control the autonomous vehicle 110 to pull over to a target position of the passing area to wait for the target vehicle 130 to travel through the passing area. As another example, the electronic device 120 can also control the autonomous vehicle 110 to travel to the passing area to slow down and pull over, i.e., the autonomous vehicle 110 does not stop during the travel to the passing area, but still travels at a lower speed to wait for the target vehicle 130 to pass through the passing area. Further, the electronic device 120 can control the autonomous vehicle 110 to travel out of the passing area in response to the target vehicle 130 traveling through the passing area.

[0086] In some embodiments, the electronic device 120 can construct geometric constraint information corresponding to the passing area. The geometric constraint information can indicate a position range of a plurality of trajectory points used to generate a travel trajectory. Further, the electronic device 120 can generate the travel trajectory of the autonomous vehicle 110 based on the geometric constraint information. Specifically, the electronic device 120 can generate a plurality of trajectory points that satisfy the geometric constraint information based on the geometric constraint information. Further, the electronic device 120 can generate the travel trajectory of the autonomous vehicle 110 based on the plurality of trajectory points. It is to be noted that the travel trajectory can satisfy a predetermined constraint, which can include, but is not limited to, a safety constraint, a comfort constraint, and the like. The safety constraint can indicate that the autonomous vehicle 110 will not collide with a road edge or the like based on the travel trajectory. The comfort constraint can indicate that the autonomous vehicle 110 will not have an emergency brake or a steering wheel rotation angle exceeding a threshold based on the travel trajectory. Further, the electronic device 120 can control the autonomous vehicle 110 to travel to the passing area based on the travel trajectory.

[0087] FIG. 4 A flowchart of generating a travel trajectory according to certain embodiments of the present disclosure is shown, which will now be described with reference to Example Devices and Equipment FIG. 4.

[0088] At block 401, the electronic device 120 can identify a narrow road passing scenario.

[0089] In some embodiments, the narrow road passing scenario can represent that the target vehicle 130 travels in the opposite direction of the autonomous vehicle 110, and a minimum width of a drivable area of the autonomous vehicle 110 is not sufficient for the autonomous vehicle 110 and the target vehicle 130 to pass side by side.

[0090] As an example, the electronic device 120 can determine whether it is a narrow road passing scenario based on whether the minimum width of the drivable area of the autonomous vehicle 110 satisfies a side-by-side passing condition.

[0091] For example, if the minimum width of the drivable region of the autonomous vehicle 110 satisfies the parallel passing condition, it is determined that it is not a narrow road passing scenario, and the autonomous vehicle 110 and the target vehicle 130 can pass in parallel without passing. For another example, if the minimum width of the drivable region of the autonomous vehicle 110 does not satisfy the parallel passing condition, it is determined that it is a narrow road passing scenario, and there is a risk of collision between the autonomous vehicle 110 and the target vehicle 130.

[0092] At block 402, the electronic device 120 can determine a detour direction and find a longitudinal interval sufficient for two vehicles to pass on the corresponding side.

[0093] In some embodiments, the electronic device 120 can determine the detour direction of the autonomous vehicle 110 based on the driving direction constraint associated with the drivable region. The detour direction can indicate which direction the autonomous vehicle 110 should travel to complete the passing with the target vehicle 130.

[0094] If the detour direction is the right side of the autonomous vehicle 110, then a longitudinal interval sufficient for two vehicles to pass can be determined on the right side of the road on which the autonomous vehicle 110 travels. This longitudinal interval corresponds to the driving direction constraint, such as the driving direction constraint indicating that the autonomous vehicle 110 travels from south to north, and this longitudinal interval is the interval indicated by the south-north direction, i.e., the south-north direction is the longitudinal direction, and the east-west direction is the transverse direction.

[0095] In some embodiments, this longitudinal interval sufficient for two vehicles to pass can be a remaining longitudinal interval after removing the sub-interval corresponding to the obstacle from the longitudinal interval of the drivable region. The obstacle is also associated with the detour direction and is located on the road on which the autonomous vehicle 110 travels.

[0096] In some embodiments, there can be one or more longitudinal intervals sufficient for two vehicles to pass.

[0097] At block 403, the electronic device 120 can generate a candidate region for each longitudinal interval.

[0098] As an example, if there are multiple longitudinal intervals sufficient for two vehicles to pass, a candidate region can be generated for each longitudinal interval. This candidate region can be a region of a predetermined size determined from the sub-drivable region corresponding to the longitudinal interval, and can also be a region determined based on the width of the target vehicle 130 and the opposite boundary of the drivable region. The opposite boundary of the drivable region can be the opposite boundary of the boundary corresponding to the detour direction, such as the opposite boundary being the left boundary of the drivable region if the detour direction is to the right.

[0099] At block 404, the electronic device 120 can determine whether the screening model accuracy is greater than a threshold value.

[0100] Further, the electronic device 120 can determine, from the plurality of candidate regions, a passing region and a confidence level corresponding to the passing region, using the screening model. Further, the electronic device 120 can determine whether the confidence level (accuracy) of the passing region is greater than a threshold value.

[0101] As an example, the electronic device 120 can perform the operation of block 405 in response to determining that the accuracy of the screening model is less than or equal to the threshold value. As another example, the electronic device 120 can perform the operation of block 410 in response to determining that the accuracy of the screening model is greater than the threshold value.

[0102] In block 405, the electronic device 120 can filter out some unreasonable candidate regions according to some rules.

[0103] As an example, the electronic device 120 can filter out a candidate region that cannot support a maximum front wheel steering angle of 60 degrees of the autonomous vehicle 110.

[0104] As another example, the electronic device 120 can also filter out a candidate region that cannot support a minimum turning radius of 5 meters of the autonomous vehicle 110.

[0105] As another example, the electronic device 120 can also filter out a candidate region that is located outside a predicted stop position of the target vehicle 130 and a position of the autonomous vehicle 110. The predicted stop position of the target vehicle 130 can be a position corresponding to a situation in which the target vehicle 130 travels at a predetermined deceleration until stopping.

[0106] In block 406, the electronic device 120 can determine whether only one candidate region is left.

[0107] As an example, the electronic device 120 can perform the process of block 407 in response to determining that only one candidate region is left.

[0108] As another example, the electronic device 120 can perform the process of block 408 in response to determining that more than one candidate region is left, i.e., there are multiple candidate regions, so that the remote device can further determine a passing region for the passing from the multiple candidate regions.

[0109] In block 407, the electronic device 120 can convert the passing region into a geometric constraint and generate a driving trajectory using a predetermined algorithm.

[0110] The geometric constraint information can indicate a position range of a plurality of trajectory points used to generate the driving trajectory.

[0111] Specifically, the electronic device 120 can generate a plurality of trajectory points that conform to the geometric constraint information based on the geometric constraint information. Further, the electronic device 120 can generate a driving trajectory of the autonomous vehicle 110 based on the plurality of trajectory points. It should be noted that the driving trajectory can satisfy a predetermined constraint, which can include but is not limited to a safety constraint, a comfort constraint, and the like. The safety constraint can indicate that the autonomous vehicle 110 will not collide with a road edge or the like when driving based on the driving trajectory. The comfort constraint can indicate that the autonomous vehicle 110 will not perform an emergency brake or the steering wheel will not rotate by more than a threshold when driving based on the driving trajectory, and the like.

[0112] At block 408, the electronic device 120 can receive a selection of the meeting area sent by the remote device.

[0113] In some embodiments, the electronic device 120 can send a request for assistance to the remote device, the request for assistance indicating the plurality of candidate areas. Further, the remote device can receive a selection of the meeting area in the candidate area.

[0114] Further, the electronic device 120 can perform the processes of block 407 and block 409.

[0115] At block 409, the electronic device 120 can store the selected meeting area as a real label to train the screening model.

[0116] In some embodiments, the electronic device 120 can construct training data based on the selected meeting area and the scene information. The scene information can be any appropriate information, such as images and / or description information associated with the plurality of candidate areas. The meeting area can be used as a label to participate in the training process of the screening model.

[0117] Further, the electronic device 120 can train the screening model deployed on the autonomous vehicle 110 using the training data. As an example, the electronic device 120 can provide the scene information to the screening model to obtain a predicted area output by the screening model. Further, the electronic device 120 can train the screening model based on a comparison between the predicted area and the meeting area until a predetermined training completion condition is reached, which can be that the loss value is less than a threshold, and the like, which will not be described herein.

[0118] At block 410, the electronic device 120 can select an optimal meeting area using the screening model.

[0119] In some embodiments, the electronic device 120 can use the meeting area determined by the screening model as the final meeting area for the autonomous vehicle 110 to complete the meeting with the target vehicle 130.

[0120] According to the embodiments of this disclosure, traffic congestion or safety risks can be avoided, and the efficiency and reliability of vehicle travel can be improved.

[0121] FIG. 5 Embodiments of this disclosure also provide corresponding apparatus for implementing the above methods or processes. FIG. 5 A schematic structural block diagram of a vehicle control device 500 according to certain embodiments of the present disclosure is shown. The device 500 may be implemented as or included in the electronic device 120 discussed above. The various modules / components in the device 500 may be implemented by hardware, software, firmware, or any combination thereof.

[0122] like FIG. 6 As shown, the device 500 includes a first determining module 510 configured to determine, in response to detecting a target vehicle traveling in the opposite direction to the autonomous vehicle, whether the minimum width of the drivable area associated with the autonomous vehicle satisfies the parallel passage condition, the parallel passage condition being related to the width of the autonomous vehicle and the width of the target vehicle; a second determining module 520 configured to determine, in response to determining that the minimum width does not satisfy the parallel passage condition, a meeting area from the drivable area that satisfies the parallel passage condition; and a control module 530 configured to control the autonomous vehicle based on the meeting area, so that the autonomous vehicle and the target vehicle pass in the opposite direction within the meeting area.

[0123] In some embodiments, the first determining module 510 is further configured to: determine at least one candidate region from the drivable region that satisfies the parallel passage condition; and determine a meeting region from the at least one candidate region.

[0124] In some embodiments, the first determining module 510 is further configured to: send an assistance request to a remote device, the assistance request indicating at least one candidate area; and determine a meeting area based on the assistance message received from the remote device.

[0125] In some embodiments, the remote device is configured to: present at least one candidate area in a preset style in the assistance interface; and generate an assistance message based on the selection of a meeting area among the at least one candidate area.

[0126] In some embodiments, the device 500 further includes a construction module configured to: construct training data based on meeting area and scene information; and a training module configured to: use the training data to train a screening model deployed on an autonomous vehicle, the screening model being configured to screen meeting areas from at least one candidate area.

[0127] In some embodiments, the first determining module 510 is further configured to: in response to the number of the at least one candidate region being greater than a threshold, send a request for assistance to a remote device; or in response to a confidence of the region filtered from the at least one candidate region by the screening model being lower than a threshold, send the request for assistance to the remote device.

[0128] In some embodiments, the first determining module 510 is further configured to: determine a set of candidate regions from the drivable region that satisfy the parallel passing condition; and determine the at least one candidate region from the set of candidate regions that satisfy the motion constraint, the motion constraint being associated with the autonomous vehicle and / or the target vehicle.

[0129] In some embodiments, the motion constraint comprises at least one of: a first constraint related to dynamics information of the autonomous vehicle; a second constraint related to a motion prediction of the target vehicle.

[0130] In some embodiments, the first determining module 510 is further configured to: determine a bypass direction of the autonomous vehicle based on a driving direction constraint associated with the drivable region; determine at least one obstacle in the drivable region associated with the bypass direction, a distance of the at least one obstacle to an opposite boundary of the drivable region not satisfying the parallel passing condition; and determine the at least one candidate region from the drivable region based on the at least one obstacle.

[0131] In some embodiments, the first determining module 510 is further configured to: determine at least one sub-interval corresponding to the at least one obstacle from longitudinal intervals of the drivable region, the longitudinal intervals corresponding to the driving direction constraint; and remove the at least one sub-interval from the longitudinal intervals to determine the at least one candidate region.

[0132] In some embodiments, the parallel passing condition indicates that the passable width reaches a width threshold, the width threshold being determined based on a sum of a width of the autonomous vehicle and a width of the target vehicle.

[0133] In some embodiments, the control module 530 is further configured to: control the autonomous vehicle to drive to the passing region; and in response to the target vehicle driving through the passing region, control the autonomous vehicle to drive out of the passing region.

[0134] In some embodiments, the control module 530 is further configured to: construct geometric constraint information corresponding to the passing region; generate a driving trajectory of the autonomous vehicle based on the geometric constraint information; and control the autonomous vehicle to drive to the passing region based on the driving trajectory.

[0135] In some embodiments, the control module 530 is further configured to: control the autonomous vehicle to park to a target position of the passing region to wait for the target vehicle to drive through the passing region.

[0136] In some embodiments, the drivable area includes a first lane and a second lane, the autonomous vehicle corresponds to the first lane, the target vehicle corresponds to the second lane, and the first lane and the second lane correspond to different driving directions.

[0137] The units included in the apparatus 500 can be implemented utilizing various means including software, hardware, and / or firmware. In some embodiments, one or more units can be implemented using software and / or firmware, e.g., machine executable instructions stored on a storage medium. In addition to or as an alternative to machine executable instructions, part or all of the units in the apparatus 500 can be implemented by one or more hardware logic components. Examples of hardware logic components that can be used include field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0138] FIG. 6 A block diagram of an electronic device 600 in which one or more embodiments of the disclosure can be implemented is shown. It should be understood that FIG. 6 The electronic device 600 shown is merely exemplary and should not be construed as limiting the scope of the embodiments described herein. FIG. 1 The electronic device 600 shown can be used to implement FIG. 6 The electronic device 120 shown.

[0139] As FIG. 6 The electronic device 600 is in the form of a general-purpose electronic device, as shown. Components of the electronic device 600 can include, but are not limited to, one or more processors or processing units 610, a memory 620, a storage device 630, one or more communication units 640, one or more input devices 650, and one or more output devices 660. The processing unit 610 can be a real or virtual processor and is capable of executing various processing in accordance with programs stored in the memory 620. In a multi-processor system, multiple processing units execute computer-executable instructions in parallel to improve the parallel processing capability of the electronic device 600.

[0140] The electronic device 600 typically includes a plurality of computer storage media. Such media can be any available media that is accessible by the electronic device 600 and includes both volatile and nonvolatile media, removable and non-removable media. The memory 620 can be volatile (such as register, cache, RAM), non-volatile (such as ROM, EEPROM, flash memory), or some combination of the two. The storage device 630 can be a removable or non-removable media, and can include machine-readable media, such as flash drives, magnetic disks, or any other media that can be used to store information and / or data (e.g., training data for training) and that can be accessed by the electronic device 600.

[0141] The electronic device 600 can further include additional removable / non-removable, volatile / nonvolatile storage media. Although not shown in ​ FIG. 6, a disk drive for reading from or writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM) can be provided. In such instances, each drive can be connected to the bus (not shown) by one or more data media interfaces. The memory 620 can include a computer program product 625 having one or more program modules configured to carry out the various methods or actions of the various embodiments of the present disclosure.

[0142] The communication unit 640 enables communications with other electronic devices over a communication medium. Additionally, the functionality of the components of the electronic device 600 can be implemented in a single computing cluster or a plurality of computer machines that are capable of communicating over a communication connection. As such, the electronic device 600 can operate in a networked environment using logical connections to one or more other servers, network personal computers (PCs), or another network nodes in the networking environment.

[0143] The input device 650 can be one or more input devices, such as a mouse, a keyboard, a trackball, etc. The output device 660 can be one or more output devices, such as a display, a speaker, a printer, etc. The electronic device 600 can also communicate with one or more external devices (not shown) such as a storage device, a display device, etc. through the communication unit 640, as needed, a device that enables a user to interact with the electronic device 600, or any device (e.g., a network card, a modem, etc.) that enables the electronic device 600 to communicate with one or more other electronic devices. Such communication can be carried out via an input / output (I / O) interface (not shown).

[0144] According to an example implementation of the present disclosure, a computer readable storage medium is provided having computer executable instructions stored thereon, where the computer executable instructions are executed by a processor to implement the method described above. According to an example implementation of the present disclosure, a computer program product is also provided that is tangibly stored on a non-transitory computer readable medium and includes computer executable instructions, where the computer executable instructions are executed by a processor to implement the method described above.

[0145] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0146] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0147] The computer readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0148] The computer program product of the present disclosure can have a signal including said computer program. This signal can be electronic, electromagnetic, optical, or any other suitable type of signal. Such a signal can be provided through a communication connection, such as electrical wiring, optical fiber, wireless interface, etc. Examples of computer program products include computer program implemented on a personal computer, server, or other networked device. A non-transitory computer readable medium, such as a floppy disk, CD-ROM, DVD-ROM, Blu-ray Disc, hard disk drive, or any other suitable non-transitory computer readable medium can store the computer program product.

[0149] Various implementations of the disclosure have been described in detail above. The foregoing description is exemplary and explanatory only, and is not intended to be exhaustive or to limit various implementations of the disclosure to the precise forms disclosed. Many modifications and variations are possible in light of the above teachings without departing from the scope and spirit of the disclosure. It is intended that the scope of the disclosure be limited only by the claims and the equivalents thereof. The use of the terms "including," "containing," "comprising," "having," "in involving," "portions," "elements," "components," "steps," "phases," "processes," "operations," "steps," "stages," "procedures," "methods," "mechanisms," "devices," "systems," "apparatuses," "units," "means," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "apparatuses," "units," "devices," "systems," "

Claims

1. A vehicle control method, comprising: In response to detecting a target vehicle traveling in the opposite direction to the autonomous vehicle, it is determined whether the minimum width of the drivable area associated with the autonomous vehicle satisfies a parallel passage condition, which is related to the width of the autonomous vehicle and the width of the target vehicle. In response to determining that the minimum width does not meet the parallel passage condition, a meeting area that meets the parallel passage condition is determined from the drivable area; as well as The autonomous vehicle is controlled based on the meeting area so that the autonomous vehicle and the target vehicle pass each other in the meeting area.

2. The method of claim 1, wherein determining the meeting area satisfying the parallel passage conditions from the drivable area comprises: Determine at least one candidate region from the drivable region that satisfies the parallel passage condition; The meeting area is determined from the at least one candidate area.

3. The method of claim 2, wherein determining the meeting area from the at least one candidate area comprises: Send an assistance request to a remote device, the assistance request indicating the at least one candidate area; as well as The meeting area is determined based on the assistance message received from the remote device.

4. The method of claim 3, wherein the remote device is configured to: In the assistance interface, the at least one candidate region is presented in a preset style; and The assistance message is generated based on the selection of the meeting area among the at least one candidate area.

5. The method according to claim 3, further comprising: Based on the meeting area and scene information, training data is constructed; as well as Using the training data, a screening model deployed on the autonomous vehicle is trained, the screening model being configured to screen passing areas from the at least one candidate area.

6. The method of claim 3, wherein a assistance request is sent to a remote device, the assistance request indicating that the at least one candidate region includes: In response to the number of at least one candidate region being greater than a threshold, the assistance request is sent to the remote device; or In response to the fact that the confidence level of a region selected by the screening model from the at least one candidate region is lower than a threshold, the assistance request is sent to the remote device.

7. The method of claim 2, wherein determining at least one candidate region satisfying the parallel passage condition from the drivable region comprises: From the drivable area, determine a set of candidate areas that satisfy the parallel passage conditions; as well as From the set of candidate regions, at least one candidate region is determined that satisfies a motion constraint associated with the autonomous vehicle and / or the target vehicle.

8. The method of claim 7, wherein the motion constraint comprises at least one of the following: A first constraint related to the dynamics information of the autonomous vehicle; A second constraint related to the motion prediction of the target vehicle.

9. The method of claim 2, wherein determining at least one candidate region satisfying the parallel passage condition from the drivable region comprises: The detour direction of the autonomous vehicle is determined based on the driving direction constraints associated with the drivable area. Identify at least one obstacle in the drivable area that is associated with the detour direction, wherein the distance from the at least one obstacle to the opposite boundary of the drivable area does not satisfy the parallel passage condition; as well as Based on the at least one obstacle, the at least one candidate region is determined from the drivable area.

10. The method of claim 9, wherein determining the at least one candidate region from the drivable area based on the at least one obstacle comprises: From the longitudinal section of the drivable area, at least one sub-section corresponding to the at least one obstacle is determined, the longitudinal section corresponding to the driving direction constraint; as well as Remove at least one sub-interval from the longitudinal interval to determine at least one candidate region.

11. The method of claim 1, wherein the parallel passage condition indicates that the passable width reaches a width threshold, the width threshold being determined based on the sum of the width of the autonomous vehicle and the width of the target vehicle.

12. The method of claim 1, wherein controlling the autonomous vehicle based on the meeting area comprises: Control the autonomous vehicle to drive to the meeting area; as well as In response to the target vehicle passing through the meeting area, the autonomous vehicle is controlled to drive out of the meeting area.

13. The method of claim 12, wherein controlling the autonomous vehicle to travel to the meeting area comprises: Construct geometric constraint information corresponding to the meeting area; Based on the geometric constraint information, the driving trajectory of the autonomous vehicle is generated; as well as Based on the driving trajectory, the autonomous vehicle is controlled to drive to the meeting area.

14. The method of claim 12, wherein controlling the autonomous vehicle to travel to the meeting area comprises: The autonomous vehicle is controlled to stop at the target location in the meeting area, so as to wait for the target vehicle to pass through the meeting area.

15. The method of claim 1, wherein the drivable area includes a first lane and a second lane, the autonomous vehicle corresponds to the first lane, the target vehicle corresponds to the second lane, and the first lane and the second lane correspond to different driving directions.

16. A device for vehicle control, comprising: A first determining module is configured to, in response to detecting a target vehicle traveling in the opposite direction to the autonomous vehicle, determine whether the minimum width of the drivable area associated with the autonomous vehicle satisfies a parallel passage condition, the parallel passage condition being related to the width of the autonomous vehicle and the width of the target vehicle. The second determining module is configured to determine, in response to determining that the minimum width does not meet the parallel passage condition, a meeting area from the drivable area that meets the parallel passage condition; as well as The control module is configured to control the autonomous vehicle based on the meeting area, so that the autonomous vehicle and the target vehicle pass each other in the meeting area.

17. An electronic device comprising: At least one processing unit; as well as At least one memory, coupled to the at least one processing unit and storing instructions for execution by the at least one processing unit, which, when executed by the at least one processing unit, cause the electronic device to perform the method according to any one of claims 1 to 15.

18. A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method according to any one of claims 1 to 15.

Images