Method for maneuvering at least partially autonomous driving vehicle at intersection

Abstract

The present disclosure relates to a method (100) for maneuvering an at least partially autonomous driving vehicle (10) from a first road (31) located at an intersection (30) into a second road (32) intersecting the first road (31) at the intersection (30), the method (100) comprising:-observing a first area (1) of the second road (32) so that a detection system (13) of the vehicle (10) detects a road user (20), -changing the detection area of the detection system (13) to include a second area (2) of the second road (32), the second area (2) including another area (3) of the second road (32) not included in the first area (31),-observing the second area (2) of the second road (32) to detect a road user (20) by the detection system (13), and-detecting the road user (20) based on the observation of the second area (2) of the second road (32). The vehicle (10) is manipulated into the second roadway (32).

Description

Technical Field

[0001] The present disclosure relates to a method, a vehicle, and a computer program product for maneuvering an at least partially autonomously driven vehicle from a first road located at an intersection to a second road that intersects the first road at the intersection. Background Art

[0002] Merging at intersections, especially at unsignalized intersections with obstructed vision, is challenging for both drivers and autonomous vehicles. It is difficult for vehicles on the main road of the intersection to detect vehicles merging into the main road in time, and it is difficult for vehicles trying to merge into the main road to assess the traffic conditions on the main road. Summary of the invention

[0003] The above-mentioned problems are at least partly solved or alleviated by the subject matter of the independent claims of the present disclosure, wherein further embodiments are incorporated in the dependent claims.

[0004] According to a first aspect, there is provided a method for maneuvering an at least partially autonomously driven vehicle from a first road located at an intersection to a second road intersecting the first road at the intersection, the method comprising:

[0005] observing a first area of ​​a second road so that a detection system of the vehicle detects a road user,

[0006] changing the detection area of ​​the detection system to include a second area of ​​the second road, the second area including another area of ​​the second road not included in the first area,

[0007] observing a second area of ​​a second road so that the detection system detects a road user, and

[0008] Based on the observation of the second area of ​​the second road, the vehicle is maneuvered onto the second road.

[0009] The method of the first aspect is based on the following discovery: One of the main reasons for the above-mentioned problems is the limited field of view of the on-board sensors (such as but not limited to cameras, radars and / or lidars), coupled with the trajectory planned and followed by the merging vehicle when merging into the second road (which may be a main road). In order to increase the critical field of view, the method of the first aspect provides for changing the detection area of ​​the second road or the main road so that a second area is observed on the second road to detect road users in the area, which area includes other areas that are not visible when observing the first area of ​​the second road. Therefore, when observing the first area and the second area at the same time, the overall field of view can be increased, thereby enabling at least a partially autonomous vehicle to perform vehicle maneuvers in a safer manner based on more traffic information on the main road.

[0010] The intersection may be an unsignalized intersection. This means that an unsignalized intersection does not have a traffic light to direct traffic. The intersection may be a T-junction. This means that a first road ends at a second road. When the vehicle is at the intersection and is about to maneuver into the second road, the intersection may only provide an obstructed view. For example, in this case, walls, trees, houses, and the like may obstruct the view. Any of the above intersection types or any combination may exist. The vehicle may be configured to detect the intersection type specifically through its detection system and change the detection area based on the detected intersection type.

[0011] Examples of changing the detection area by rotating the vehicle, for example, are described in more detail below. In general, the detection area of ​​the detection system may be limited and not include the entire second road, for example, due to difficult conditions such as night time, obstructed vision at an intersection, or the vehicle's detection system may not be able to overlook the entire second road at the same time. The second area may completely include the first area. Therefore, the second area may be a larger detection area compared to the first area. However, this may not be the case. Instead, the second area may be an offset detection area that may not include or only partially include the first area. In this case, a portion of the first area may still be observed, but the detection area has shifted to a more distant area.

[0012] Any observation step may be performed at an instant or over a period of time, such as a few seconds. Thus, the detection system may observe the first area and / or the second area at an instant or over a period of time in order to detect road users on the second road at that instant or during that period of time. Detecting road users based on observation of the second area may include determining their position (absolute position or relative to the vehicle), direction of travel, speed and / or acceleration on the second road, etc.

[0013] The vehicle is at least partially autonomous. This means that the vehicle can achieve partially or fully autonomous driving. Partially autonomous driving involves one or more driver assistance functions, such as but not limited to cruise control, lane keeping assistance and distance control assistance. The maneuvering of the vehicle can be at least partially or fully autonomous. In other words, maneuvering the vehicle into the second road based on the observation of the second area of ​​the second road can be performed at least autonomously by the vehicle. The maneuvering of the vehicle is not necessarily based only on the observation of the second area of ​​the second road, but can also be further based on the observation of the first area, the third area described below and / or further information, which can come from V2X communications with one or more entities (for example, road users on the second road).

[0014] In an embodiment, the observation of the second area of ​​the second road may include detecting, by the detection system, at least one road user in another area of ​​the second road. Thus, the detection area may be increased or moved by including another area so that at least one road user is detected therein. If the detection area is not increased or moved, such at least one road user may not be detected, which may result in dangerously maneuvering the vehicle into the second road when the driving trajectory of the vehicle being maneuvered intersects the driving trajectory of the at least one road user in the another area.

[0015] In one embodiment, the method may include, before changing the detection area, detecting at least one road user in another area of ​​the second road, the detection of the at least one road user being based on an audio recording of the sound of the at least one road user in the another area of ​​the second road by an audio recording system of the vehicle. Thus, the at least one road user in the another area may first be roughly located based on its sound (e.g., road sound or engine sound). In order to detect the position or location of the road user, the recorded audio may be processed to determine the rough location from which the sound is emitted. Furthermore, if the audio recording contains different sounds and / or sounds from different locations, the different sounds may be distinguished from each other by such audio processing. Then, in order for the detection system to detect the at least one road user located based on its sound, the detection area may be changed to include more areas located based on its sound. Thus, based on the sound detection, the vehicle may know which area of ​​the second road it needs to observe within the possibly limited detection area.

[0016] In one embodiment, the method may include:

[0017] changing the detection area of ​​the detection system to include a third area of ​​the second road, the third area including a further area of ​​the second road not included in the first area and the second area, and

[0018] observing a third area of ​​the second road in order to detect a road user by the detection system,

[0019] Maneuvering the vehicle into the second road is also based on observing a third area of ​​the second road. Thus, there may be more than one step of changing the detection area. For example, due to the limited field of view of the eye, changing the detection area may mimic the behavior of a human looking around at an intersection. Thus, different areas of the second road may be observed, and road users among any of these users may be detected, and their positions, directions of travel, and / or speeds determined thereby may be taken into account when maneuvering the vehicle.

[0020] In one embodiment, the method may include rotating the vehicle at the intersection to change the detection area. The rotation of the vehicle may be provided by yaw wheels and / or driving forward or backward. Rotating the entire vehicle to change the detection area is just one embodiment. In addition or alternative to rotating the entire vehicle, other examples described herein may also be provided.

[0021] In one embodiment, the method may include rotating at least one detection unit of the detection system to change the detection area. Thus, the detection system itself and one or more detection units thereof may be rotated to increase or move the detection area. For the rotation of the at least one detection unit, the detection system may include one or more actuators for rotating the one or more detection units individually or together.

[0022] In one embodiment, the at least one rotating detection unit is at least one of a camera detection unit, a laser radar detection unit, and a radar detection unit. This includes that the detection unit is any one of the above or any combination of two or more of the above detection units.

[0023] In one embodiment, changing the detection area may include increasing at least one of the lighting intensity, lighting direction and lighting area of ​​the vehicle lighting system. The vehicle lighting of the vehicle lighting system may in particular be vehicle exterior lighting, for example including but not limited to the headlights and / or high beams of the vehicle. By increasing the lighting intensity at the intersection, the detection area may be increased to include further areas. In addition or alternatively, the lighting direction may also be changed, for example by rotating the entire vehicle or one or more lighting units of the vehicle (such as headlights) to change the detection area. Additionally or alternatively, the lighting area of ​​the detection area may also be increased or decreased by, for example, switching the vehicle lighting mode. For example, it is possible to switch between a mode in which the headlights are activated and a mode in which the high beams are additionally or alternatively activated.

[0024] In one embodiment, at least one of the illumination intensity and the illumination area of ​​the vehicle illumination system can be increased by operating the high-beam illumination system of the vehicle illumination system. Since the high-beam illumination system may distract other road users, it may not be feasible to use the high-beam illumination system all the time at night in general, but the high-beam illumination system can be used for a short period of time to change the detection area, thereby detecting road users in a farther area, and ultimately improving traffic safety by preventing collisions at intersections.

[0025] In one embodiment, the illumination intensity of the vehicle's lighting system may be increased based on ambient light measurements from the vehicle's ambient light sensor system. Thus, the illumination intensity, such as the illumination intensity of the high beam lighting system, may be selected to increase only to the extent necessary to detect the second area and not to significantly distract road users in the second area.

[0026] In one embodiment, the method may include starting to signal road users on the second road or increasing the amount of signaling relative to a nominal signaling value before and / or when the vehicle is maneuvered into the second road. The nominal signaling value may be a normal value representing the amount of signaling of the vehicle during normal operation at the intersection (i.e., without increasing the amount of signaling). For example, signaling may involve sounds, lights, and / or any other signal emitted from the vehicle.

[0027] For example, the amount of signaling may be the volume of a sound, which is emitted by the vehicle. This provides a simple and effective way of making road users on the second road aware of a vehicle that is located at the intersection and is about to maneuver into the second road, thereby improving traffic safety.

[0028] In one embodiment, the sound emitted may be an engine sound emitted by an engine sound simulation device to simulate the engine sound of a vehicle. For example, the vehicle may be an electric vehicle. Therefore, although the road sound emitted by a vehicle (especially an electric vehicle) is smaller than that emitted by an internal combustion engine vehicle, the engine sound simulation device may still be activated to start sending a signal or increase the amount of the signal sent so that road users on the second road may still notice the vehicle located at the intersection and preparing to maneuver into the second road.

[0029] According to a second aspect, a vehicle is provided, comprising a component configured to perform the method of the first aspect of the present disclosure. Such a component may include a detection system and a computer component, such as a microprocessor or a computer, for observing a first area and a second area. Such a computer component or other computer components may also be configured to at least partially autonomously manipulate the vehicle to enter a second road. In addition, the vehicle may include a component for changing the detection area, which may be the above-mentioned computer component, and which may be configured to rotate the vehicle as a whole, or, alternatively or additionally, it may be a component such as an actuator, such as at least one detection unit for a rotation detection system, a high beam lighting system and / or an engine sound simulation unit.

[0030] According to a third aspect, a computer program product is provided, which includes instructions for causing a vehicle to execute the method of the first aspect of the present disclosure. The computer program product may be a computer program itself, or a product having instructions stored thereon, such as a computer-readable storage medium.

[0031] It should be noted that the above embodiments can be combined with each other, regardless of the aspects involved. Thus, the method can be combined with structural features, and similarly, the device and system can also be combined with the features described above with respect to the method.

[0032] These and other aspects of the disclosure will become apparent from and be elucidated with reference to the embodiments described hereinafter. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Embodiments of the present disclosure will be described below with reference to the following drawings.

[0034] Figure 1 The steps of the method according to the embodiment of the present disclosure are shown;

[0035] Figure 2 A vehicle according to an embodiment of the present disclosure is shown; and

[0036] Figure 3-5 Shown with Figure 2 of vehicles at the intersection where the vehicle performs Figure 1 different steps of the method. DETAILED DESCRIPTION

[0037] The accompanying drawings are only schematic diagrams and are only used to illustrate the embodiments of the present disclosure. The same or equivalent elements are generally provided with the same reference numerals.

[0038] Figure 1 A method 100 is shown for operating an at least partially autonomous vehicle 10 (see Figures 2 to 5 ) from the first road 31 at the intersection 30 to the second road 32 intersecting with the first road 31 at the intersection 30 (see Figures 3 to 5 ). Figures 3 to 5 The intersection 30 in FIG. 1 is exemplarily shown as a T-junction without signalization.

[0039] Figure 2 The vehicle 10 and its components are shown in a schematic manner. The vehicle 10 may be at least partially autonomous and / or an electric vehicle. The vehicle 10 comprises a computer 11 and a computer program product 12. The computer program product 12 comprises instructions executable by the computer 11 in order to perform the method 100.

[0040] The vehicle 10 also includes a detection system 13, which includes one or more detection units 14, such as a camera detection unit, a lidar detection unit, and a radar detection unit. In addition, the vehicle 10 may also include a vehicle lighting system 15, which may include a headlight lighting system 16, a high beam lighting system 17, and an ambient light sensor system 18. In addition, the vehicle 10 may also include an engine sound simulation unit 19a and / or an audio recording system 19b.

[0041] In step 102 of method 100, as Figure 3By way of example, the detection system 13 observes a first area 1 of the second road 32 so that it can detect the road user 20 thereon. The size of the first area 1 can be determined by the detection area of ​​the detection system 13 in terms of its capabilities. Figure 3 In the exemplary embodiment of FIG. 1 , the detection system 13 can detect a road user 20 in the form of another vehicle on the right side of the vehicle 10. For example, the detection system 13 can detect the position, speed, driving direction, etc. of the road user 20 by means of its at least one detection unit 14. However, in this exemplary case, the vehicle 10 cannot see the road user 20 in the form of another vehicle on the left side of the vehicle 10 because the left road user 20 is located outside the first area 1. When the at least partially autonomously operated vehicle 10 turns left or right at the intersection 30 based on the observation of the detection system 13, this may lead to a potentially dangerous situation.

[0042] To avoid this potentially dangerous situation, the method 100 includes a step 104 in which the detection area of ​​the detection system 13 is changed to include the second area 2 of the second road 32, such as Figure 4 The second area 2 includes another area 3 of the second road 32 that is not included in the first area 31. Therefore, in step 106 of the method 100, the detection system 13 can observe the second area 2 of the second road 32 to detect the road user 20. Figure 4 As can be seen in the example of FIG. 1 , the vehicle 10 is now able to detect a left-hand road user 20 in another area 3 , so that the at least partially autonomously driven vehicle 10 is able to be aware of the left-hand road user 20 and take it into account when maneuvering the vehicle 10 into the second road 30 , which is similar to FIG. 1 . Figure 5 Corresponding to step 108 of the method 100 exemplarily illustrated in FIG.

[0043] Prior to observing the further area 3 by the detection system 13, the method 100 may further include detecting a left-hand road user 20 in the further area 3 of the second road 32 based on an audio recording made by the audio recording system 19b, the audio recording including sounds from the left-hand road user 20. Figure 3 and Figure 4 In the embodiment of the present invention, the recorded audio may be processed to detect the direction of the recorded sound, so that the source of the sound, i.e., the rough position of the road user 20 emitting the sound on the second road 32, may be estimated. Therefore, the vision-based detection area of ​​the detection system 13 may be changed based on the prior audio-based detection of one or more road users 20, rather than randomly changing the detection area.

[0044] The detection system 13 detects changes in the area Figure 4exemplarily shown in FIG. 1 as a rotation of the entire vehicle 10. However, alternatively or additionally, the detection area can be changed by rotating at least one detection unit 14, increasing at least one of the lighting intensity, lighting direction and lighting area of ​​the vehicle lighting system 15 of the vehicle 10 (e.g., by operating the high beam lighting system 17 as an addition or alternative to the headlight lighting system 16) and / or starting to signal the vehicle 10 to the road users 20 on the second road 32 (e.g., by operating the engine sound simulation unit 19a). Variants of the lighting change can be based on ambient light measurements of the ambient light sensor system 18. The benefit of increasing lighting and / or sound is that the vehicle 10 can be made aware of by the road users 20 on the second road 32, thereby improving safety.

[0045] In addition, steps 104 and 106 may be repeated to include other areas that are not visible in the first area 1 or the second area 2. In addition, other steps of the method 100 related to the positioning of the vehicle 10 at the intersection 30 may also be employed. In particular, the method 100 may include pushing the vehicle 10 into the second road 32 before maneuvering the vehicle 10 into the second road 32. This may further increase the detection area of ​​the detection system 13. If the vehicle 10 is pushed into the second road 32, the vehicle 10 may also back up if necessary (e.g., if a road user 20 is close to the vehicle 10), otherwise there is a risk of an accident. The amount of pushing the vehicle 10 into the second road 32 may be determined by a machine learning model, such as may be utilized by the computer 11. In addition, the method 100 may also include performing a risk assessment on maneuvering the vehicle 10 into the second road 32. The risk assessment may take into account any road users 20 detected during observation of the first area, the second area, and / or any other area of ​​the second road 32. Therefore, based on the risk assessment, the maneuvering of the vehicle 10 into the second road 32 may be timed so that it is performed when the risk is minimal or below a threshold.

[0046] As used herein, the phrase "at least one", when referring to a list of one or more entities, should be understood to mean at least one entity selected from any one or more entities in the list of entities, but does not necessarily include at least one of each entity specifically listed in the list of entities, nor does it exclude any combination of entities in the list of entities. This definition also allows for the optional presence of other entities in addition to the entities specifically specified in the list of entities to which the phrase "at least one" refers, whether or not they are related to the specifically specified entities. Thus, as a non-limiting example, "at least one of A and B" (or equivalently "at least one of A or B", or equivalently "at least one of A and / or B") may refer to at least one, optionally including more than one A, without B present (optionally including entities other than B); in another embodiment, to at least one, optionally including more than one B, without A present (optionally including entities other than A); in yet another embodiment, to at least one, optionally including more than one A, and at least one, optionally including more than one B (optionally including other entities). In other words, the phrases "at least one", "one or more", and "and / or" are open-ended expressions that can be either conjunctive or non-conjunctive in operation. For example, each of the expressions “at least one of A, B, and C,” “at least one of A, B or C,” “one or more of A, B and C,” “one or more of A, B or C,” and “A, B and / or C” may refer to A alone, B alone, C alone, A and B together, A and C together, B and C together, A, B and C together, and any of the above, optionally in combination with at least one other entity.

[0047] By studying the drawings, the disclosure and the appended claims, a person skilled in the art can understand and implement other variations of the disclosed embodiments when implementing the disclosed claims. In the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality. The fact that certain measures are described in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. The computer program product may be stored / published on a suitable medium, such as an optical storage medium or solid-state medium provided with or as part of other hardware, but may also be published in other forms, such as via the Internet or other wired or wireless communication systems. Any reference signs in the claims should not be construed as limiting the scope of the claims.

Claims

1. A method (100) for maneuvering an at least partially autonomous vehicle (10) from a first road (31) located at an intersection (30) to a second road (32) intersecting the first road (31) at the intersection (30), the method (100) comprising: - observing a first area (1) of a second road (32) in order to detect a road user (20) by a detection system (13) of a vehicle (10), - changing the detection area of ​​the detection system (13) to include a second area (2) of the second road (32), the second area (2) including another area (3) of the second road (32) that does not belong to the first area (31), - observing a second area (2) of a second road (32) to detect a road user (20) by means of a detection system (13), and - Based on the observation of the second area (2) of the second road (32), maneuvering the vehicle (10) onto the second road (32).

2. The method (100) of claim 1, wherein the observing of the second area (2) of the second road (32) comprises detecting, by the detection system (13), at least one road user (30) in the further area (3) of the second road (32).

3. The method (100) according to claim 2, comprising detecting the at least one road user (20) in the other area (3) of the second road (32) before changing the detection area, the detection of the at least one road user (20) being based on an audio recording of the sound of the at least one road user (20) from the other area (3) of the second road (32) by an audio recording system (19b) of the vehicle (10).

4. The method (100) according to any one of the preceding claims, comprising: - changing the detection area of ​​the detection system (13) to include a third area of ​​the second road (32), the third area including another area of ​​the second road (32) not included in the first area (1) and the second area (2), and - observing a third area of ​​the second road (32) in order to detect a road user (20) by means of the detection system (13), Maneuvering the vehicle (10) onto the second road (32) is further based on observing a third area of ​​the second road (32).

5. The method (100) according to any one of the preceding claims, comprising rotating the vehicle (10) at the intersection (30) to change the detection area.

6. The method (100) according to any of the preceding claims, comprising rotating at least one detection unit (14) of the detection system (13) to change the detection area.

7. The method (100) according to claim 6, wherein the at least one rotating detection unit (14) is at least one of a camera detection unit, a lidar detection unit and a radar detection unit.

8. The method (100) according to any one of the preceding claims, the changing of the detection area comprising increasing at least one of a lighting intensity, a lighting direction and a lighting area of ​​a vehicle lighting system (15) of the vehicle (10).

9. The method of claim 8, wherein at least one of the illumination intensity and the illumination area of ​​the vehicle illumination system (15) is increased by operating a high beam illumination system (17) of the vehicle illumination system (15) of the vehicle (10).

10. The method (100) of claim 8 or 9, the lighting intensity of the vehicle lighting system (15) being increased based on ambient light measurements of an ambient light sensor system (18) of the vehicle (10).

11. A method (100) according to any of the preceding claims, comprising starting to signal road users (20) on the second road (32) before and / or when the vehicle (10) enters the second road (32), or increasing the amount of signaling sent by the vehicle (10) relative to a nominal signaling value.

12. The method (100) according to claim 11, wherein the signal quantity is a volume of a sound, the sound being emitted by the vehicle (10).

13. The method (100) according to claim 12, wherein the sound emitted is an engine sound, and the sound is emitted by an engine sound simulation device (19a) to simulate the engine sound of the vehicle (10).

14. A vehicle (10) comprising components configured to perform the method (100) of any one of the preceding claims.

15. A computer program product (12) comprising instructions for causing a vehicle (10) to perform a method (100) according to any one of claims 1 to 13.

Images