CN114604269A

CN114604269A - Method and apparatus for controlling turning operation of vehicle

Info

Publication number: CN114604269A
Application number: CN202210193523.7A
Authority: CN
Inventors: 李和安
Original assignee: Mercedes Benz Group AG
Current assignee: Mercedes Benz Group AG
Priority date: 2022-03-01
Filing date: 2022-03-01
Publication date: 2022-06-10
Also published as: DE102023000561A1

Abstract

The present invention relates to the field of autonomous driving. The present invention proposes a method for controlling a turning operation of a vehicle, the method comprising the steps of: s1: acquiring the state of a traffic signal lamp at an intersection when a vehicle is about to perform a turning operation at the intersection; s2: checking the existence of a turn waiting area under the condition that the state of the traffic signal lamp accords with a first predefined condition; s3: selecting a position for the vehicle to perform the waiting operation and controlling the vehicle to perform the waiting operation at the position according to the result of the check on the presence of the turning waiting area. The present invention also provides an apparatus for controlling a turning operation of a vehicle and a computer program product. The invention aims to enable the automatic driving vehicle to make a correct parking decision in a manner of adapting to the ground mark at the intersection, thereby improving the acceptance of the automatic driving vehicle.

Description

Method and apparatus for controlling turning operation of vehicle

Technical Field

The present invention relates to a method for controlling a turning operation of a vehicle, and also relates to an apparatus for controlling a turning operation of a vehicle and a computer program product.

Background

At present, more and more vehicles are equipped with an automatic driving/driving assistance function, however, in some traffic scenes with complex road conditions or diversified driving rules, the automatic driving function still faces challenges. For example, at a large intersection in some countries, in order to avoid traffic congestion caused by excessive backlog of left-turning vehicles, a left-turning waiting area is usually set to allow the left-turning vehicles to make preparations for turning in advance. If the autonomous vehicle does not enter such a transition area at the right timing but keeps waiting all the time in front of the intersection, such driving behavior is likely to be unacceptable to the user and also causes prompt complaints from the following vehicles.

For this reason, a method of determining a parking position of an autonomous vehicle is proposed in the related art, in which if one of a turn signal lamp and a straight signal lamp indicates that the vehicle can pass, a position of a first stop line of a turn waiting area is set as a position to be parked, and it is determined whether the vehicle is parked or continuously driven at the parking position based on a subsequent state of the turn signal lamp.

A method for parking an autonomous vehicle at an intersection with precision is also known, in which zebra crossing, obstacles, lane markings and traffic light information at the intersection are acquired by means of image acquisition technology and the parking operation of the autonomous vehicle at the intersection is controlled thereby.

However, the above-mentioned solutions known at present still have a number of disadvantages, in particular, it has only been proposed in the prior art to control the parking behavior of the vehicle on the premise that the presence of a turning waiting area has been determined, but no prior determination is made as to the presence of a turning waiting area. Therefore, the application scenarios still have many limitations.

In this context, it is desirable to provide an improved vehicle turning behavior control scheme aimed at adapting autonomous vehicles to the road markings at the crossing to make the correct parking decisions, thereby increasing the acceptance of autonomous vehicles.

Disclosure of Invention

It is an object of the present invention to provide a method for controlling a turning operation of a vehicle, an apparatus for controlling a turning operation of a vehicle and a computer program product to solve at least some of the problems in the prior art.

According to a first aspect of the present invention, there is provided a method for controlling a turning operation of a vehicle, the method comprising the steps of:

s1: acquiring the state of a traffic signal lamp at an intersection when a vehicle is about to perform a turning operation at the intersection;

s2: checking the existence of a turn waiting area under the condition that the state of the traffic signal lamp accords with a first predefined condition;

s3: selecting a position for the vehicle to perform the waiting operation and controlling the vehicle to perform the waiting operation at the position according to the result of the check on the presence of the turning waiting area.

The invention comprises in particular the following technical concepts: the method can be widely applied to different intersection scenes, and passengers experience driving behaviors which are highly intelligent and meet the regional characteristics because the vehicles can make parking strategies in a mode of adapting to specific ground marking types, so that the acceptance of automatically driving the vehicles is improved. Furthermore, the opportunity to check the presence of the turn waiting area is advantageously limited by the traffic light status, so that such checking operations are only introduced in the context of a scene in which parking may be required, reducing the sensing and calculation overhead on the vehicle side.

Optionally, in step S2, the "the state of the traffic light meets the first predefined condition" includes:

under the condition that the traffic signal lamps comprise a turn signal lamp and a straight-going signal lamp, the turn signal lamp indicates that turning is impossible to pass through; or

The traffic signal lights include only straight-ahead signal lights.

The following technical advantages are achieved in particular here: it has been recognized that there is a lack of uniform decision logic in determining the necessity of parking at an intersection due to imperfections in transportation facilities. By performing the filtering in terms of the type of traffic light, the decision mechanism for the necessity of parking is simplified.

Optionally, the step S3 includes:

in the event that it is determined that there is a turn waiting area, checking whether the state of the traffic light meets a second predefined condition, wherein the meeting of the state of the traffic light meets the second predefined condition comprises in particular: the state of the traffic signal lamp indicates that the traffic signal lamp can go straight;

and when the state of the traffic light meets the first predefined condition and does not meet the second predefined condition, controlling the vehicle to enter a turning waiting area to execute waiting operation, and when the state of the traffic light meets the first predefined condition and does not meet the second predefined condition, controlling the vehicle to execute waiting operation at a stop line of a turning special lane.

The following technical advantages are achieved in particular here: by performing the check in terms of the second predefined condition, the timing of entering the turn waiting area is determined for the autonomous vehicle, thereby enabling the parking position to be varied in accordance with the recognized traffic light status. For the passengers, a smooth driving feeling in accordance with local traffic habits can be experienced.

Optionally, the method further comprises the steps of:

and planning the driving track of the vehicle after entering the turning waiting area according to the detected shape of the turning waiting area, wherein the vehicle is guided and controlled to stop at a stop line at the end of the turning waiting area especially along the extension direction of the dotted line of the turning waiting area.

The following technical advantages are achieved in particular here: since the course of the turn waiting area is usually offset from the direction of extension of the normal traffic lane, it is difficult to guide the vehicle, and safe driving of the vehicle can be advantageously supported by recognizing and taking into account the shape of the turn waiting area.

Optionally, the method further comprises the steps of:

in a case where the vehicle enters the turn waiting section to perform a waiting operation, it is checked whether there is another vehicle in the turn waiting section, wherein the vehicle is controlled to perform the waiting operation behind the other vehicle in a case where there is the other vehicle, and the vehicle is controlled to perform the waiting operation at a stop line at an end of the turn waiting section in a case where there is no other vehicle.

The following technical advantages are achieved in particular here: this is understood to mean that the position and behavior of the other road users are taken into account when controlling the vehicle guidance, as a result of which the detection range can be expanded and a more accurate prediction of the course of the road in the turn waiting area can be made. Furthermore, the possibility of collision of the autonomous vehicle can be reduced by following the vehicle ahead while complying with the applicable traffic regulations.

Optionally, before controlling the vehicle to enter the turn waiting area, checking an idle degree of the turn waiting area, wherein controlling the vehicle to enter the turn waiting area to perform the waiting operation only when the idle degree satisfies a preset condition, wherein the idle degree satisfies the preset condition particularly includes: the remaining space in the turn waiting area allows the vehicle to stop in the turn waiting area without occupying the crosswalk line.

The following technical advantages are achieved in particular here: according to current traffic regulations, vehicles must avoid pedestrian crossing lines when queuing into a left turn waiting area. By taking this into account advantageously when planning the parking position, the automatic driving behavior can be adapted to the traffic situation that changes in real time, offering the possibility of coping with different situations.

Optionally, the step S1 includes: shooting an image of the traffic signal lamp by means of a vehicle-mounted camera and determining the state of the traffic signal lamp based on an image recognition technology; and/or

Information regarding the status of the traffic light is received from the traffic light, other vehicles, and/or roadside units.

The following technical advantages are achieved in particular here: with the development of V2X technology, it is possible not only to rely on the vehicle's own sensing capabilities to identify traffic signal conditions, but also to receive such information based on communication technology. Thereby, effective support is provided when visibility is poor or vehicle perception capability is insufficient.

Alternatively, in step S1, the checking the presence of the turn waiting area includes:

checking the number of stop lines associated with the turn-only lane by means of an image recognition technique, wherein the presence of a turn waiting zone is determined in the event that the presence of at least two stop lines is detected; and/or

The presence of a broken line extending along the lane line of the turn-only lane to the intersection is checked by means of image recognition technology, wherein the presence of a turn waiting area is determined in the event of detection of said broken line.

The following technical advantages are achieved in particular here: by focusing on the typical characteristics of the turning waiting area in the identification process, the search window can be effectively limited, and the identification efficiency is further improved.

According to a second aspect of the present invention, there is provided an apparatus for controlling a turning operation of a vehicle, the apparatus being for performing the method according to the first aspect of the present invention, the apparatus comprising:

an acquisition module configured to acquire a state of a traffic signal light at an intersection during a turning operation that a vehicle is about to perform at the intersection;

a checking module configured to check the presence of a turn waiting area in case the state of the traffic light complies with a first predefined condition; and

a control module configured to select a position at which to perform a waiting operation for the vehicle and control the vehicle to perform the waiting operation at the position, according to a result of the check on the presence of the turn waiting area.

According to a third aspect of the present invention, there is provided a computer program product, wherein the computer program product comprises a computer program for implementing the method according to the first aspect of the present invention when executed by a computer.

Drawings

The principles, features and advantages of the present invention may be better understood by describing the invention in more detail below with reference to the accompanying drawings. The drawings comprise:

fig. 1 shows a block diagram of an apparatus for controlling a turning operation of a vehicle according to an exemplary embodiment of the present invention;

FIG. 2 shows a flowchart of a method for controlling a turning operation of a vehicle according to an example embodiment of the invention;

FIG. 3 shows a flow chart of one method step of the method in FIG. 2;

FIG. 4 shows a flow chart of two method steps of the method in FIG. 2;

5 a-5 c show schematic diagrams of the use of the method according to the invention in an exemplary application scenario; and

fig. 6 shows a schematic representation of the use of the method according to the invention in a further exemplary application scenario.

Detailed Description

In order to make the technical problems, technical solutions and advantageous effects of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings and exemplary embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and do not limit the scope of the invention.

Fig. 1 shows a block diagram of an apparatus for controlling a turning operation of a vehicle according to an exemplary embodiment of the present invention.

As shown in fig. 1, a vehicle 100 comprises a device 1 according to the invention. Here, the vehicle 100 further includes a panoramic vision sensing system including a front view camera 11, a left view camera 12, a rear view camera 13, and a right view camera 14, a radar sensor 15, and a laser radar sensor 16, for example. With these in-vehicle environment sensors, the vehicle 100 can perform various functions such as back-up assistance, obstacle detection, road structure recognition, and the like to support partially autonomous travel or fully autonomous travel, for example. Furthermore, the vehicle 100 for example also comprises a communication interface 17 based on car networking technology for receiving traffic information from other traffic participants, infrastructure and/or road supervision platforms and is also able to share the traffic information collected by the vehicle 100 to other traffic participants. It should be noted herein that the vehicle 100 may include other types and numbers of sensors besides the sensors shown in fig. 1, and the present invention is not particularly limited thereto.

In order to control the turning operation of the vehicle 100, the device 1 comprises an acquisition module 10, a checking module 20 and a control module 30, which are communicatively connected to each other.

The acquisition module 10 is used, for example, to acquire the state of a traffic light at an intersection during a turning operation that the vehicle 100 is about to perform at the intersection. In order to understand the scene in which the vehicle 100 is located and grasp the turning intention of the vehicle 100, the acquisition module 10 is connected to or includes, for example, a navigation unit that receives information from various on-vehicle sensors, a GPS unit, a map database, and the like to estimate the position of the vehicle 100 on a map. Then, based on the estimated own position and the pre-planned driving route, the obtaining module 10 can determine: whether the vehicle 100 is in an intersection scene and whether the vehicle 100 should perform a turning operation at the intersection. The acquisition module 10 also receives images of the road environment in front of the vehicle 100, for example from a front-view camera 11, and identifies traffic lights from these images by means of a trained image classifier or an artificial neural network. By means of a suitable image recognition algorithm, the acquisition module 10 is able to recognize the contour of the traffic light from the captured image. The current signal state of the traffic signal lamp can be identified by combining the corresponding color and brightness information. Furthermore, the acquisition module 10 can also access, for example, a traffic regulation database in which various types of traffic light parameters are stored. Thus, for example, by means of shape and contour comparison, further category information of the traffic light can be derived.

In the embodiment shown in fig. 1, the acquisition module 10 is also connected to a communication interface 17, for example, in order to be able to receive information about the state of a traffic light, for example, from other traffic participants, traffic lights or roadside units in the surroundings. Additionally, the acquisition module 10 is also connected, for example, to a radar sensor 15 and a lidar sensor 16 of the vehicle 100, so that, for example, the image recognition result can be verified or supplemented by means of additional detection data.

The checking module 20 receives information about the traffic signal status (e.g. the analysis result in terms of the first predefined condition) from the acquisition module 10. In the checking module 20, in response to receiving information that the status of the traffic light meets a first predefined condition, the checking module 20 checks for the presence of a turn waiting area. For this purpose, the inspection module 20 is likewise connected, for example, to the forward-looking camera 11 and the communication interface 17 of the vehicle 100, so that on the one hand a turn waiting area can be detected on the basis of the image recognition result of the road surface ahead and on the other hand the presence of the turn waiting area can be determined by means of the received traffic information. Whether a turn waiting area exists at the intersection ahead can also be judged according to the position of the vehicle and map (such as a high-precision map) information.

The acquisition module 10 and the check module 20 are each connected to the control module 30 and provide status information on traffic lights and presence information of a turn waiting area to the control module 30, respectively. The control module 30 is used to select a parking position for the vehicle 100 according to the real-time state of the traffic signal and the presence of a turn waiting area, and control the vehicle to perform a waiting operation at the selected position at an appropriate timing. To this end, the control module 30 is connected, for example, to the lateral and longitudinal guiding mechanisms of the vehicle 100 in order to cause the vehicle 100 to interrupt a turning operation or to continue to complete a turning operation at a certain position, for example, by driving an actuating mechanism of a throttle, a brake, a steering unit, or the like.

Fig. 2 shows a flowchart of a method for controlling a turning operation of a vehicle according to an exemplary embodiment of the present invention. The method exemplarily comprises the steps S1-S3 and may be implemented, for example, using the device 1 shown in fig. 1.

In step S1, during a turning operation that the vehicle is about to perform at an intersection, the state of the traffic light at the intersection is acquired.

In the sense of the present invention, "turning operation" may mean, for example, a left-turn operation, a right-turn operation, or a turn-around operation, but depending on the traffic driving regulations enforced by a specific country or region, particularly refers to turning behavior in which a driving track needs to pass through an intersection to reach a target lane during execution of a turn.

In the sense of the present invention, "the vehicle is about to perform a turning operation at the intersection" means in particular: the vehicle has arrived at the intersection and will cross the stop line and enter the intersection area if continued to travel forward.

In order to recognize the operating state of the vehicle itself, it can be determined whether the vehicle is in an intersection scene, for example, based on GPS position data of the vehicle and map information. Furthermore, if the navigation route of the vehicle can be accessed, it may also be determined whether the vehicle should perform a turning operation based on the planned route.

In order to obtain the state of the traffic light, it is possible here, for example, to receive images of the road environment ahead of the vehicle from the respective vehicle-mounted camera in real time and to recognize the traffic light and its respective light/dark color state therefrom by means of image recognition technology and thus to draw conclusions about the phase in which the traffic light is present. It is also conceivable to receive the real-time signal status of the traffic light from other vehicles, traffic lights, road side units in conjunction with a high-precision map of the vehicle's locality or by means of the V2X technology.

In the sense of the present invention, "state of a traffic light" means in particular the luminous state of a traffic light, which in the simplest case includes, for example: the traffic light current color indicates whether traffic is passing (e.g., green) or forbidden (e.g., red). It is furthermore conceivable that the "state of the traffic light" also comprises category/contour/volume/quantity information of the traffic light, which for example comprises: the traffic signal lamp relates to a single lane signal lamp or a multi-lane signal lamp.

In step S2, in the case where the state of the traffic signal lamp meets the first predefined condition, the presence of the turn waiting area is checked.

Here, "the state of the traffic light meets the first predefined condition" is understood to be: by interpreting the state of the traffic light, it can be determined that the vehicle should not directly perform a turning operation at the present time and thus there is a temporary parking demand, or it cannot be directly determined whether the vehicle can immediately perform a turning operation and thus there is a temporary parking demand.

In order to check the presence of the turn waiting area, the shape and type of the markings printed on the road surface ahead can be detected on the one hand on the basis of image recognition technology and compared with a reference shape of the turn waiting area, which can be done in particular by means of a trained machine learning model. On the other hand, it is also possible to receive information of the intersection where the vehicle is currently located by means of the V2X technology, and thereby determine the type of the road sign corresponding to the intersection. Whether a turn waiting area exists at the front intersection can be judged according to the position of the vehicle and map (such as a high-precision map) information, and specific information of the turn waiting area can be acquired from the map.

In step S3, a position at which the waiting operation is to be performed is selected for the vehicle and the vehicle is controlled to perform the waiting operation at the position, according to the result of the check regarding the presence of the turn waiting area.

Here, "waiting operation" is understood as: the vehicle may need to be temporarily stopped before performing a turning operation at an intersection due to restrictions imposed by the traffic policy reflected by the traffic light.

Here, the "position where the waiting operation is performed" may have various possibilities depending on the road surface marking form. In the simplest case, a solid white/yellow line transverse to the direction of travel of the lane at the intersection of the lane with the intersection region can be understood as a possibility for such a position. In the case where there is a turn waiting area, the position where the waiting operation is performed may also involve the end solid line of the turn waiting area. Therefore, it is necessary to select an appropriate parking position in conjunction with the state of the traffic signal and the presence of the turn waiting area.

Fig. 3 shows a flow chart of a method step of the method in fig. 2. In the exemplary embodiment, method step S1 in FIG. 2 includes, for example, steps S11-S16.

In step S11, the intention to turn the vehicle is recognized, for example, by an onboard GPS unit or a navigation unit.

In step S12, the state of the traffic signal in front of the vehicle is acquired based on the image recognition technology and/or based on the V2X technology.

In step S13, it is determined based on the state information of the traffic signal: whether the traffic signal includes not only a turn signal but also a straight traveling signal, or whether the traffic signal includes only a straight traveling signal.

If it is determined that the traffic signal includes only the straight traveling signal, it may be directly determined that the state of the traffic signal satisfies the first predefined condition in step S15. This means that although the vehicle intends to perform a left turn operation at the intersection, there is no traffic indication signal uniquely corresponding to such a left turn operation. Due to the lack of clear traffic instructions, left-turning vehicles need not only to stop following the relevant signals at the red light, but also to take into account the intersection and interference of the trajectories of the oncoming straight vehicles even at the green light, and to control the vehicles to select the appropriate position to wait for an opportunity to complete the left turn. In this case, therefore, it is meant that at least a temporary parking position selection of the left-turning vehicle is involved anyway.

In another case, if it is determined in step S13 that the traffic signal includes not only the turn signal but also the straight traveling signal, it may be further checked whether the turn signal indicates impassability, for example, in step S14.

If the turn signal light indicates that the vehicle is not passable, the traffic light indicates that a traffic indication signal corresponding to the turning operation to be performed by the vehicle exists in the current traffic scene, and the traffic indication signal reflects that the vehicle has the parking necessity at the current moment. In this case, it may also be determined in step S15 that the state of the traffic signal lamp meets the first predefined condition.

If the turn signal indicates passable, this indicates that it can be unambiguously determined that: the vehicle is allowed to continue to complete the turning operation in the current scene, and therefore the selection of the parking position is not involved. In this case, it may be determined in step S16, for example, that the state of the traffic signal lamp does not meet the first predefined condition.

Fig. 4 shows a flow chart of two method steps of the method in fig. 2. In the exemplary embodiment, method steps S2 in FIG. 2 include, for example, S21-S24, and method steps S3 include, for example, S31-S35. This embodiment is based on the following assumptions: it has been determined by means of the methods shown in fig. 2-3 that the state of the traffic signal lamp meets the first predefined condition.

In step S21, an image of the road surface ahead of the vehicle is captured by a front-view camera of the vehicle.

In step S22, the image of the road surface ahead is analyzed based on the image recognition technique, and it is checked that: whether multiple stop lines associated with the turn-only lane are identified, and/or whether a dashed line extending from the turn-only lane to the intersection area is identified.

If the above-defined elemental feature is not recognized in the image in step S22, it may be determined that no turn waiting area exists at the intersection. Then, for example, the vehicle may be controlled to perform a waiting operation at a stop line at the end of the turn-dedicated lane in step S24, and to complete the turning operation according to the subsequent state of the traffic signal or the oncoming traffic flow.

If these elemental features are recognized in step S22, it is determined that there is a turn waiting area at the intersection, for example. Then, for example, it may be further checked in step S31: whether the state of the traffic signal light meets a second predefined condition.

In the sense of the present invention, "the state of the traffic light meets the second predefined condition" means: there is a possibility that the vehicle is switched from the first parking position to the second parking position. Here, for example, it is possible to check: whether the state of the traffic light indicates straight-through passable.

If it is found that the traffic light does not comply with the second predefined condition, that is, the state of the traffic light indicates, for example, straight-ahead non-passing, the vehicle may be controlled to perform a waiting operation at the stop line at the end of the turn-only lane in step S32.

If the traffic light is found to meet the second predefined condition, for example, if the state of the traffic light indicates straight-through passable, the vehicle may be controlled to enter the turn waiting area to perform a waiting operation in step S33. Before or during this, the driving behavior of the vehicle can be appropriately influenced in combination with the degree of idleness of the turn waiting area and the shape of the turn waiting area, among others.

It should be noted here that controlling the vehicle to enter the turn waiting area does not mean that the end stop line of the turn waiting area is determined as the final stop position of the vehicle, but the stop position should also be selected accordingly in connection with the vehicle situation already existing within the turn waiting area. As an example, if there is already at least one traffic object in line in the turn waiting area, it is for example necessary to take into account a certain safety distance from the preceding vehicle when determining the final parking position, and if there are no other traffic objects in the turn waiting area, the stop line of the turn waiting area may be selected as the parking position.

It is then also possible, for example, to continuously monitor the state of the traffic light and check whether a third predefined condition is fulfilled, on the premise that the vehicle has performed a waiting operation at the selected position. Here, the compliance with the third predefined condition includes, for example: the state of the traffic light indicates that the turn is passable.

If the traffic light has not indicated that the turn is passable, the vehicle is caused to continue to remain waiting at the current location. If the traffic light is switched to indicate that the turn is passable after a period of time, the vehicle may be controlled to end the parking wait and complete the turning operation in step S35.

Fig. 5 a-5 c show schematic diagrams of the use of the method according to the invention in an exemplary application scenario.

In the scenario shown in fig. 5a, the vehicle 100 is driving in a first direction on a first road 501 having three lanes L1, L2, L3 and is about to arrive at an intersection 500. Here, the vehicle 100 intends to shift to the second road 502 on the left side of the intersection 500 by a left-turn operation and travel in a third direction perpendicular to the first direction, for example.

Since the vehicle 100 is about to perform a left turn operation, the vehicle 100 selects, for example, to travel on the left-turn exclusive lane L3 of the first road 501 and has approached the end of the exclusive lane L3.

In order to safely and reliably control the vehicle 100 to complete the turning operation, the vehicle 100 detects the front road environment by means of the in-vehicle sensors and detects the traffic signal lamp 300 at the intersection 500. Upon detection of the traffic signal 300, the vehicle 100 further recognizes based on the image recognition algorithm that the traffic signal 300 includes a turn signal 302 in addition to the straight signal 301. Furthermore, it is also identified: in the present case, both the turn signal light 302 and the straight traveling signal light 302 indicate red lights.

Therefore, by appropriate analysis, the vehicle 100 determines that a waiting operation should be temporarily performed at the intersection 500. In order to accurately determine the parking position, the vehicle 100 further incorporates an in-vehicle sensor to detect the road surface in front and detect the presence of a stripe-shaped region surrounded by a dotted line 530 and a terminal solid line 520 on the road surface in front. In addition, the vehicle 100 recognizes the stop line 510 at the end of the turn-only lane L3. In this way, it can be determined that the turn waiting area 540 exists at the intersection 500, for example.

In conjunction with the current state of the traffic light 300 (both the straight and turn

lights

301, 302 are red), the stop line 510 at the end of the turn-only lane is selected as the parking waiting position, for example, and the vehicle 100 is thus controlled to perform a waiting operation in front of the stop line 510.

In the scenario shown in fig. 5b, the difference from the scenario shown in fig. 5a is that the state of the traffic signal lamp 300 is changed at this time, wherein the straight-ahead signal lamp 301 changes from red to green, and the turn signal lamp 302 still maintains red.

Based on the corresponding decision logic, the vehicle 100, for example, departs again from the stop line 510 of the left-turn-only lane L3 and drives slowly into the already recognized turn waiting area 540. Here, the trajectory of the vehicle 100 is also adjusted in conjunction with the shape of the turn waiting area 540 so as not to exceed the range defined by the broken line 530 during traveling.

It can be seen in this embodiment that there are no other vehicles in the turn waiting area 540, so the vehicle 100 can travel until it reaches the stop line 520 at the end of the turn waiting area 540.

In the scenario shown in fig. 5c, unlike the scenarios shown in fig. 5 a-5 b, the type of traffic signal light 300 at the intersection 500 has changed. At the intersection 500, the traffic signal light 300 no longer reflects the traffic instructions of the left-turn lane L3 and the straight-going lane L2 at the same time, but indicates only the trafficability of the straight-going lane L2. In this case, the vehicle 100 on the left-turn exclusive lane L3, for example, also needs to follow the state of the blinker 300 to perform the corresponding driving operation. In this example, the traffic light 300 is, for example, a green light, which indicates that a vehicle on the straight lane L2 can pass.

In response to the recognition result in terms of the state of the traffic light 300, the vehicle 100 confirms that the turn waiting area 540 can be entered from the current position, for example. After entering the turn waiting area 540, the vehicle 100 further selects an appropriate timing to complete the turning operation in conjunction with the opposite-to-straight traffic flow situation.

In the scenario shown in fig. 6, the vehicle 100 has learned, based on the environment recognition result or the received traffic information: the traffic light 300 at the intersection 500 includes both the turn signal light 302 and the straight traveling signal light 301, and at this time, the turn signal light 302 is red and the straight traveling signal light 301 is green. Furthermore, the vehicle 100 also concludes by means of an analysis of the road surface image in front: there is a turn waiting area 540 at the intersection 500.

In this case, with the method according to the invention, it can be determined, for example: the vehicle 100 should enter the turning operation region 540 to perform the parking waiting under the present situation. However, at this time, the vehicle 100 further recognizes in conjunction with the environmental awareness result that another vehicle 200 is already present in the turning waiting area 540. Then, the degree of idleness of the turn waiting area 540 is additionally checked before controlling the vehicle 100 to follow the vehicle 200 into the turn waiting area 540. With such a check, for example, it is confirmed that if the vehicle 100 enters the turning waiting area 540, a part of the pedestrian crossing line (as shown by a broken line 100' in fig. 6) is occupied in the parking situation, which is not allowed in the law in some countries or regions. Therefore, in this case, it is judged that: the degree of idleness of the turn waiting area 540 does not satisfy the preset condition, and therefore even if the state of the traffic signal lamp 300 satisfies the condition for the vehicle 100 to enter the turn waiting area 540, the vehicle 100 is not controlled to enter the area, but the waiting is continuously performed at the stop line 510 kept at the end of the left-turn exclusive lane L3 to ensure safe and reliable driving behavior.

Although specific embodiments of the invention have been described herein in detail, they have been presented for purposes of illustration only and are not to be construed as limiting the scope of the invention. Various substitutions, alterations, and modifications may be devised without departing from the spirit and scope of the present invention.

Claims

1. A method for controlling a turning operation of a vehicle (100), the method comprising the steps of:

s1: acquiring a state of a traffic light (300) at an intersection (500) during an upcoming turning operation at the intersection (500) by a vehicle (100);

s2: checking the presence of a turn waiting area (540) in case the status of the traffic light (300) meets a first predefined condition; and

s3: according to the result of the check on the presence of the turn waiting area (540), a position at which the waiting operation is performed is selected for the vehicle (100) and the vehicle (100) is controlled to perform the waiting operation at the position.

2. The method according to claim 1 or 2, wherein in step S2, the "state of the traffic signal lamp (300) meeting a first predefined condition" comprises:

in the case where the traffic signal (300) includes a turn signal and a straight traveling signal, the turn signal indicates that the turn is impassable; or

The traffic signal (300) includes only straight-ahead signal lights.

3. The method according to claim 1 or 2, wherein the step S3 comprises:

in case it is determined that there is a turn waiting area (540), checking whether the state of the traffic signal lamp (300) complies with a second predefined condition, wherein the state of the traffic signal lamp (300) complies with the second predefined condition comprises in particular: the status of the traffic light (300) indicates straight-through passable;

controlling the vehicle (100) to enter a turn waiting area (540) to perform a waiting operation when the state of the traffic light (300) meets a first predefined condition and meets a second predefined condition, and controlling the vehicle (100) to perform the waiting operation at a stop line (510) of a turn-only lane when the state of the traffic light (300) meets the first predefined condition and does not meet the second predefined condition.

4. The method according to any one of claims 1 to 3, wherein the method further comprises the steps of:

the trajectory of the vehicle (100) after entering the turn waiting area (540) is planned according to the detected shape of the turn waiting area (540), wherein the vehicle (100) is guided and the vehicle (100) is controlled to stop at a stop line (520) at the end of the turn waiting area (540), in particular, following the direction in which the dashed line (530) of the turn waiting area (540) extends.

5. The method according to any one of claims 1 to 4, wherein the method further comprises the steps of:

in a case where the vehicle (100) enters the turn waiting section (540) to perform a waiting operation, it is checked whether or not there is another vehicle (200) in the turn waiting section (540), wherein the vehicle (100) is controlled to perform the waiting operation behind the other vehicle (200) in a case where there is the other vehicle (200), and the vehicle (100) is controlled to perform the waiting operation at a stop line (520) at an end of the turn waiting section (540) in a case where there is no other vehicle (200).

6. The method according to any one of claims 1 to 5, wherein, before controlling the vehicle (100) to enter the turn waiting area (540), a degree of idleness of the turn waiting area (540) is checked, wherein the vehicle (100) is controlled to enter the turn waiting area (540) to perform a waiting operation only when the degree of idleness satisfies a preset condition, wherein the degree of idleness satisfies the preset condition particularly comprises: the remaining space in the turn waiting area (540) allows the vehicle (100) to not occupy the pedestrian crossing line in the case of parking in the turn waiting area (540).

7. The method according to any one of claims 1 to 6, wherein the step S1 includes: capturing an image of the traffic light (300) by means of the vehicle-mounted camera and determining the state of the traffic light (300) on the basis of an image recognition technique; and/or

Information regarding the status of the traffic signal light (300) is received from the traffic signal light (300), other vehicles (200), and/or roadside units.

8. The method according to any one of claims 1 to 7, wherein, in step S1, checking for the presence of a turn waiting area (540) comprises:

checking the number of stop lines (510, 520) associated with the turn-only lane by means of an image recognition technique, wherein the presence of a turn waiting zone (540) is determined in the event that the presence of at least two stop lines (510, 520) is detected; and/or

The presence of a broken line (530) extending along the lane line of the turn-only lane to the intersection (500) is checked by means of image recognition technology, wherein the presence of a turn waiting area (540) is determined in the event of detection of the broken line (530).

9. An apparatus (1) for controlling a turning operation of a vehicle (100), the apparatus (1) being adapted to perform the method according to any one of claims 1 to 8, the apparatus (1) comprising:

an acquisition module (10) configured to acquire a state of a traffic light (300) at an intersection (500) during an upcoming turning operation of a vehicle (100) at the intersection (500);

a checking module (20) configured to check the presence of a turn waiting area (540) in case the status of the traffic signal light (300) complies with a first predefined condition; and

a control module (30) configured to select a position for the vehicle (100) to perform a waiting operation and to control the vehicle (100) to perform the waiting operation at the position, according to a result of the check on the presence of the turn waiting area (540).

10. A computer program product, wherein the computer program product comprises a computer program for implementing the method according to any one of claims 1 to 8 when executed by a computer.