Method and device for detecting traffic traveling in the opposite direction

Abstract

The invention relates to a method and device for detecting oncoming traffic of an autonomous vehicle (220) traveling on a lane of a two-way roadway (200), said method being implemented by a processor and comprising the steps of: Determining a country code in which said vehicle is traveling; Determining a regulatory driving side, right or left, from said determined country code and a predetermined table; Determining the actual driving side, right or left, of said vehicle; and Determining said oncoming traffic detection when said determined regulatory driving side is different from said determined actual driving side. Figure to be published for the abstract: Figure 2

Description

Title of the invention: Method and device for detecting oncoming traffic Technical field of the invention

[0001] The invention is in the field of autonomous vehicle driver assistance systems. In particular, the invention relates to a method and a device for detecting oncoming traffic of an autonomous vehicle traveling on a lane of a two-way roadway. State of the art

[0002] The term "vehicle" means any type of vehicle such as a motor vehicle, moped, motorcycle, warehouse robot, etc. "Autonomous driving" of an "autonomous vehicle" means any process capable of assisting the driving of the vehicle. This process may consist of partially or fully controlling the vehicle or providing any type of assistance to a person driving the vehicle. The process thus covers all autonomous driving, from level 0 to level 5 in the OICA (International Organization of Motor Vehicle Manufacturers) scale.

[0003] The term "road" means a means of communication that allows the movement of vehicles between two given geographical points, generally two urban areas. The term "carriageway" means one or more parts of the road normally used for the movement of vehicles. The term "traffic lane," or "lane," means a subdivision of the carriageway having sufficient width to allow the movement of a single line of vehicles.

[0004] For example, a motorway classically comprises two carriageways separated by a central reservation and / or a barrier, each carriageway comprising at least two lanes having the same direction of travel (a single direction of travel).

[0005] As another example, a national highway or a departmental road typically comprises a single carriageway. The carriageway includes at least two lanes: a first lane on which vehicles travel in one direction, and a second lane on which vehicles travel in the opposite direction, the second direction being opposite to the first. In what follows, this type of road is referred to as a "two-way carriageway," a two-way road, or a two-way road. Generally, specific road markings delineate the two lanes. Another road marking delineates the edges, or sides, of the carriageway. This other marking is also called the edge line.

[0006] On a two-way road, the normal driving lane is determined by national legislation. Driving on the right, as in France, refers to situations where, under normal driving conditions, the vehicle must be kept as close as possible to the right edge of the road, depending on its condition or profile. In England, the legislation mandates driving on the left.

[0007] Driving against traffic, also known as "driving the wrong way," on a two-way road, i.e., driving in the wrong lane, is extremely dangerous. This can happen due to fatigue or impaired judgment for various reasons (such as drowsiness). It is even more likely when crossing borders, particularly when traffic laws change and the designated driving side changes.

[0008] A device for determining oncoming traffic based on measurements of a turning radius and the left or right side of a curve is known from document JP2009259147. However, this device is only functional when turning. Summary of the invention

[0009] An object of the present invention is to remedy the aforementioned problem, in particular to determine in a more regular and reliable manner a traffic in the opposite direction.

[0010] To this end, a first aspect of the invention relates to a method for detecting oncoming traffic of an autonomous vehicle traveling on a lane of a two-way roadway, said method being implemented by a processor and comprising the steps of: • Determination of a country code in which the said vehicle is circulating; • Determination of a driving side, right or left, as required by law, based on the aforementioned country code and a predetermined table; • Determination of the current driving side, right or left, of said vehicle; and • Determination of said oncoming traffic detection when said determined regulatory driving side is different from said determined actual driving side.

[0011] Thus, first, the regulatory driving side, left-hand drive or right-hand drive, is determined in the country in which the vehicle is traveling. Next, the current driving side, right-hand or left-hand, is determined at the present moment or over a predetermined time period close to the present moment. Finally, a simple comparison between these two determinations determines whether, at the present moment, the vehicle is traveling in the opposite direction.

[0012] Advantageously, said method further comprises a step of creating a signal representative of a wrong-way driving alert, and emitting said signal to a human-machine interface, said human-machine interface being configured to alert an occupant of said vehicle of the current wrong-way driving.

[0013] Thus, an occupant of the vehicle, a driver or passenger, can be alerted to regain or have regained control of the vehicle.

[0014] Advantageously, said determination of said country code in which said vehicle is circulating is obtained from information processing, said information being transmitted by radio frequency, and / or said determination of said country code is obtained by geolocation associated with mapping.

[0015] Several methods can be used to determine the country code, the country in which the vehicle is traveling. A combination of these methods makes this determination more reliable.

[0016] Advantageously, the determination of said current driving side is carried out from data from image processing captured from at least one camera capable of perceiving an environment in front of said vehicle, and / or is carried out from geolocation data associated with a map.

[0017] Several methods can be used to determine the driving side. A combination of these methods makes this determination more reliable.

[0018] Advantageously, said data from said image processing includes a first distance, called left lateral distance, between said vehicle and a left edge of said roadway, a second lateral distance, called right lateral distance, between said vehicle and a right side of said roadway, and when said left lateral distance is greater than said right lateral distance said current driving side determined is a right side, otherwise said current driving side determined is a left side.

[0019] Thus, in a simple and efficient way, the current driving side is determined.

[0020] Advantageously, said data from said image processing includes an identification of a rear face of a road sign and a third lateral distance between said sign and said vehicle, said determination of the current driving side is based on said third lateral distance.

[0021] Thus, the current driving side is determined simply and efficiently. Combined with other determination methods, the determination of the driving side is made more reliable.

[0022] Advantageously, the method further comprises a step of determining traffic on a one-way roadway, and when traffic on a one-way roadway is determined said step of creation of said sign representing a warning of driving in the wrong direction is inhibited.

[0023] Thus, unnecessarily alerting an occupant of the vehicle is avoided.

[0024] A second aspect of the invention relates to a device comprising a memory associated with at least one processor configured to implement the method according to the first aspect of the invention.

[0025] The invention also relates to a vehicle comprising the device.

[0026] The invention also relates to a computer program comprising instructions which, when the program is executed by the device according to the second aspect of the invention, lead the latter to implement the process according to the first aspect of the invention. Brief description of the figures

[0027] Other features and advantages of the invention will become apparent from the description of the following non-limiting embodiments of the invention, with reference to the accompanying figures, in which:

[0028] [Fig-1] schematically illustrates a device, according to a particular example of realization of the present invention.

[0029] [Fig.2] schematically illustrates a use case of vehicle traffic on a roadway, according to a particular embodiment of the present invention.

[0030] [Fig. 3] schematically illustrates a method for detecting oncoming traffic of an autonomous vehicle, according to a particular embodiment of the present invention. Detailed description of the invention

[0031] The invention is described below in its non-limiting application to the case of an autonomous motor vehicle on a lane of a two-way roadway. Other applications such as a robot in a warehouse or a motorcycle on a country road are also conceivable.

[0032] Figure 1 shows an example of a device 101 included in the vehicle, in a network (“cloud”), or in a server. This device 101 can be used as a centralized device responsible for at least some steps of the process described below with reference to Figure 3. In one embodiment, it corresponds to an autonomous driving computer.

[0033] In the present invention, the device 101 is included in the vehicle. This device 101 can take the form of a housing comprising printed circuits, any type of computer or even a mobile phone (“smartphone”).

[0034] The device 101 includes a random access memory 102 for storing instructions for the implementation by a processor 103 of at least one step of the process as described above. The device also includes a mass memory 104 for storing data intended to be retained after the implementation of the process.

[0035] The device 101 may further include a digital signal processor (DSP) 105. This DSP 105 receives data to shape, demodulate and amplify, in a manner known per se, this data.

[0036] The device 101 also includes an input interface 106 for receiving the data implemented by the method according to the invention and an output interface 107 for transmitting the data implemented by the method according to the invention.

[0037] For example, the input interface 106 can receive the following data: vehicle position or geographical location, vehicle speed and / or acceleration, setpoint or predetermined positions / speeds / accelerations, engine speed, position and / or stroke of the clutch, brake and / or accelerator pedal, detection of other vehicles or objects, position or geographical location of other vehicles or objects detected, speed and / or acceleration of other vehicles or objects detected, operating states of sensors, confidence index of data from or processed by sensors and / or devices similar to device 101.For example, sensors capable of providing data include: GPS-type geolocation devices, from the English "Global Positioning System" associated or not with mapping, tachometers, accelerometers, RADAR, LIDAR, lasers, ultrasound, cameras, radio telecommunication devices allowing the vehicle to receive and / or exchange information with its environment (analog or digital radio, V2X communications...).In particular, the input interface can receive information relating to a country code, geolocation data, lateral distances between the vehicle and the edges of a roadway on which the vehicle is traveling, geolocation of a traffic sign, lateral distance between a traffic sign and an edge of the roadway, lateral distance between the traffic sign and the vehicle, information on the detection of the back face of a traffic sign, traffic information on a two-way or one-way roadway.

[0038] For example, the output interface 107 can transmit data similar to the data received by the input interface 106. In particular, the output interface 107 can transmit a country code indicating the vehicle's current location, a standard driving side, a table linking a country code to a driving side, the current driving side, oncoming traffic detection, a signal indicating an oncoming traffic alert, data from image processing captured from at least one camera capable of perceiving an environment in front of the vehicle, a lateral distance between the vehicle and a road edge, a specific driving side, and identification of a face rear of a road sign, lateral distance between a sign and the vehicle, traffic direction on a one-way road, a one-way road, a warning sign, ...

[0039] [Fig.2] schematically illustrates a use case of a vehicle circulating on a roadway, according to a particular embodiment of the present invention.

[0040] In this [Fig. 2], a vehicle 220 is traveling in a lane 211 of a carriageway 200 of a road. The road comprises a single carriageway 200. The terms "left" and "right" are defined with respect to the normal direction of travel of the vehicle 220. The carriageway 200 comprises two lanes, a first lane called the left lane 210 and a second lane called the right lane 211. The vehicle is traveling in the right lane 211. The direction of travel of the left lane 210 is indicated by an arrow 214. The direction of travel of the right lane 211 is given by an arrow 215. The direction of travel 214 of the left lane 210 is reversed, therefore in the opposite direction, with respect to the direction of travel 215 of the right lane 211. The carriageway 200 is a two-way carriageway.

[0041] The road, and therefore here the carriageway 200, comprises two edges, represented by a first edge line called the left edge line 212 and a second edge line called the right edge line 213. In [Fig.2], the left edge line 212 coincides with the left edge of the carriageway 200, and the right edge line 213 coincides with the right edge of the carriageway 200. The two lanes 210 and 211 are separated by a marking on the ground, called the separation line 201.

[0042] Next to the right edge of the carriageway 200, therefore of the right bank line 213, a signpost 240 is installed.

[0043] Line 221 represents a future trajectory from an origin of a frame of reference associated with vehicle 220. The future trajectory 221 of vehicle 220 is determined, for example, over a period of 10 seconds, over a period of 30 seconds, or over any other duration. In [Fig. 2], the future trajectory 221 is rectilinear. The future trajectory may be non-rectilinear and follow the curvature of a road, for example. It is known how to predict the future trajectory of a vehicle.

[0044] The vehicle 220 includes a camera 222 capable of capturing images of the environment in front of the vehicle, the front being defined according to the vehicle's normal operating direction. The camera 220 is generally mounted in the center and at the top of the vehicle's windshield. The triangle 223 schematically represents an environment perceived by the camera. The camera 220 perceives, for example, the roadway 200, lanes 210 and 211, the dividing line 201, the edges 212 and 213 of the roadway, a front face or a rear face of the traffic sign 240. In [Fig. 2], the camera perceives a rear face of the traffic sign 240.

[0045] It is known that image processing from the camera 222 is capable of determining a first distance 224, referred to as the left lateral distance, between said vehicle 220 and the left edge 212 of said roadway 200, and is capable of determining a second lateral distance 225, referred to as the right lateral distance, between said vehicle 220 and the right side 213 of said roadway 200. Advantageously, said left lateral distance 224 and right lateral distance 225 are determined from an orthogonal projection of an edge onto the future trajectory 221 of the vehicle at a predetermined distance 226. Other reference points relative to the vehicle or other distances 226 may be used to determine said left lateral distance 224 and said right lateral distance 225.

[0046] The image processing is also capable of determining a third lateral distance 227 between the sign 240 and the car 220, and is capable of determining a longitudinal distance 228 between the sign 240 and the car 220. The image processing is also capable of identifying the presence of a rear face of the road sign 240. Advantageously, image processing from the camera 222 is capable of determining whether a road sign, of which a rear face is identified, is present on the left side 212 or on the right side 213 of the roadway 200.

[0047] [Fig.3] schematically illustrates a method for detecting traffic in the direction unlike an autonomous vehicle, according to a particular embodiment of the present invention, the vehicle 220 traveling on a lane of a two-way road 200, said process being implemented by the processor 103 of the device 101, said process comprising several steps.

[0048] Step 301, CountryCode, is a step for determining the country code in which the vehicle is traveling. The country code is determined by information typically received by the input interface 106 of device 101. This information is generally transmitted by other devices 101. This information may originate from an input interface in which a user specifies a country, or a language that allows for narrowing down a list of possible countries.

[0049] Advantageously, the determination of the country code in which the vehicle is traveling is obtained from information processing, the information being transmitted by radio frequency, and / or the determination of the country code is obtained by geolocation associated with mapping. The information received by the input interface 106 may originate from the determination of geolocation based on the reception of GPS signals associated with mapping. This information may also originate from the processing of a signal received from a signal emitted by a radio telecommunication or radioelectric antenna (by example 2G, 3G, 4G, 5G telecommunications antenna...FM, AM, digital radio antenna, ..., television or satellite antennas, ...).

[0050] Advantageously, the country code is represented according to ISO 3166-1 alpha-2 (country codes represented by 2 letters), ISO 3166-1 alpha-3 (country codes represented by 3 letters), or ISO 3166-1 numeric (country codes represented by numbers). Other coding or representation systems are possible. It is also possible that determining the country code may yield an "undetermined country" value if, for various reasons such as loss of GPS signal or driving very close to the border, the country code cannot be reliably determined.

[0051] Step 302, CountrySide, is a step for determining the regulatory driving side, right or left, based on the country code and a predetermined table. Tables are known to determine the driving side, right or left, depending on the country. For example, for France with a country code of "FR", the table may give the value "right", "right-hand drive", "DR", "R", or any other code that represents right-hand drive. For example, for the United Kingdom with a country code of "GB", the table may give the value "left", "left-hand drive", "GA", "L", or any other code that represents left-hand drive.

[0052] In what follows, the determination of the regulatory driving side provides the information "regulatory driving on the right", "regulatory driving on the left" or "regulatory side undetermined". A value "regulatory side undetermined" is possible, for example, if the country code could not be determined in the previous step, if the predetermined table is incomplete, ...

[0053] Step 303, SideCalc, is a step for determining the current driving side, right or left, of the vehicle. There are several ways to determine the current driving side of vehicle 220. "Current" refers to the present moment when vehicle 220 is in operation, but also to a time window during which the determination is performed. For example, a time window could be 10 seconds, one minute, or several minutes before the present moment. Determining the vehicle's current driving side within a time window helps to smooth and improve the reliability of the determination by, for example, excluding aberrant or inconsistent data received, such as "country undetermined," "regulatory side undetermined," or, as another example, during the determinations described below.

[0054] In what follows, the determination of the current driving side, right or left, provides information such as "current driving side on the right", "current driving side on the left", or "current driving side undetermined". In certain situations, the driving side is undetermined, for example, if the country code is undetermined, if the regulatory driving side is undetermined, or if the vehicle is temporarily traveling on the left. in the middle of the roadway, if the information received by the input interface is not invalid, inconsistent, unreliable, ...

[0055] Advantageously, the determination of said current driving side is carried out from data from image processing captured from at least one camera 222 capable of perceiving an environment in front of 223 said vehicle 220, and / or is carried out from geolocation data associated with a map.

[0056] Advantageously, the determination made from geolocation data associated with a map is obtained if the geolocation is sufficiently precise and the map is sufficiently precise. A sufficiently precise map is understood to be one that represents, for example, roadway 200 with its lanes 210 and 211. A sufficiently precise geolocation is understood to be one that is capable of determining the geolocation of vehicle 220 on lane 210 or 211. Thus, knowing the lane on which the vehicle is traveling, the current driving side of vehicle 220 has been determined.

[0057] Advantageously, said data from said image processing includes a first distance, called left lateral distance 224, between said vehicle 200 and a left edge 212 of said roadway, a second lateral distance, called right lateral distance 225, between said vehicle 220 and a right side 213 of said roadway, and when said left lateral distance 224 is greater than said right lateral distance 225 said determined current driving side is a right side, i.e. a "right-hand current driving side", otherwise said determined current driving side is a left side, i.e. a "left-hand current driving side".Advantageously, if the difference, in absolute value, between the left lateral distance 224 and the right lateral distance 225 is less than a first predetermined value, for example 10 centimeters, 50 centimeters, or any other positive value, the determination is indeterminate and can provide information on "current driving side indeterminate". For example, this latter situation can occur when the vehicle 220 overtakes a cyclist, or moves slightly away from the curb.

[0058] Advantageously, said data from said image processing includes an identification of the rear face of a road sign and a third lateral distance 227 between said sign 240 and said vehicle 220, said determination of the current driving side is based on said third lateral distance 227. For example, the image processing can determine the edge, left 212 or right 213, where the road sign 240 is located. And if the third lateral distance 227 is less than a second predetermined value, for example a theoretical lane width, the vehicle 220 travels in the lane, left 210 or right 211, closest to the edge, left 212 or right 213, where the sign 240 is located. In a Another example, it is also possible to use in addition the distances, left lateral 224 and right lateral 225, in order to determine the lane in which the vehicle is traveling.

[0059] Advantageously, a combination of different means of determining the current driving side, some of which are described above, makes it possible to determine the current driving side more reliably and safely.

[0060] Advantageously, the method further comprises a step of determining traffic flow on a one-way roadway. This determination can be carried out by various means, such as by combining a geolocation method with a map, the map including roadway type information (e.g., one-way roadway, two-way roadway). In another example, this determination is obtained from processing images perceived by the camera 222, such as by identifying road signs (one-way road sign, sign indicating a motorway or expressway, etc.).

[0061] For example, when traffic on a one-way roadway is determined, the said step of creating said sign representing a warning of driving in the wrong direction is inhibited.

[0062] Step 304, Comp, is a comparison step between the regulatory driving side determined in step 302 and the actual driving side determined in step 303. If either step 302 or 303 provides information on an undetermined side, the process proceeds to step 301, for example. Advantageously, it also proceeds to step 301 when one-way traffic is determined.

[0063] When said determined regulatory driving side is different from said determined current driving side, contrary traffic of the autonomous vehicle 220 has been detected and we proceed to step 305.

[0064] Step 305, Alarm, is a step for creating a signal representing a wrong-way driving alert and transmitting said signal to a human-machine interface, said human-machine interface being configured to alert an occupant of said vehicle of the current wrong-way driving. This step is initiated when wrong-way driving of vehicle 220 has been detected. This event allows the creation of a signal to alert a vehicle occupant of a dangerous driving situation with an increased risk of an accident.

[0065] Advantageously, step 305 is inhibited when one-way traffic is determined. There is no creation of said signal representing a warning of driving in the wrong direction.

[0066] To illustrate an example, in the case of [Fig. 2], if vehicle 220 is traveling in Great Britain (United Kingdom), step 301 can provide country code information equal to "GB". Step 302 can provide information "left-hand driving". In step 303, geolocation associated with a map can To determine a "current right-hand drive side." Also in step 303, since the left lateral distance 224 is greater than the right lateral distance 225, the determined current driving side is a "current right-hand drive side." Also, the traffic sign 240, the rear of which the camera perceives, is on the right side, near the right edge 213. The difference, in absolute value, between the third lateral distance 227 and the right lateral distance 225 is less than one lane width. Thus, it is determined that the determined current driving side is a "current right-hand drive side." Since a "regulatory left-hand drive" has been determined, and vehicle 220 is travelling in the right lane, by determining a "current right-hand drive side," it is then determined that vehicle 220 is travelling in the opposite direction.A signal can be created and emitted by the output interface 107 so that a human-machine interface can communicate with and alert the driver and / or an occupant of the vehicle 220 of the dangerous situation.

[0067] The present invention is not limited to the embodiments described above by way of example: it extends to other variants.

[0068] Thus, an embodiment has been described above in which the process has been described according to a sequence of steps. Some steps can be carried out in parallel or according to another sequence.

[0069] Advantageously, the method can be activated or deactivated via the interface with a Human-Machine Interface. Activation can be automatically offered in the event of a change of country, the change of country being detected, for example, by geolocation associated with a map, by interpretation of the meaning of a road sign, by recognition of road markings or road signs, etc.

[0070] Advantageously, the choice of activation and deactivation of the process, therefore the user parameters, are saved in a non-volatile memory 104 when the motor contact ("key off" in English) is cut off and / or stopped.

Claims

Demands

1. A method for detecting oncoming traffic of an autonomous vehicle (220) traveling on a lane of a two-way roadway (200), said method being implemented by a processor (103) and comprising the steps of:

2. • Determination (301) of a country code in which said vehicle is being circulated; • Determination (302) of a driving side, right or left, prescribed from said determined country code and a predetermined table; • Determination (303) of the current right or left-hand drive side of said vehicle; and • Determination (304) of said oncoming traffic detection when said determined regulatory driving side is different from said determined actual driving side • wherein the determination (303) of said current driving side is carried out from data obtained from image processing captured from at least one camera (222) capable of perceiving an environment (223) in front of said vehicle, • wherein said data from said image processing include a first distance, called left lateral distance (224), between said vehicle (220) and a left edge (212) of said roadway, a second lateral distance, called right lateral distance (225), between said vehicle (220) and a right side (2113) of said roadway, and where said left lateral distance (224) is greater than said right lateral distance (225) said current driving side determined is a right side, otherwise said current driving side determined is a left side, • wherein said data from said image processing include an identification of a rear face of a road sign (240) and a third lateral distance (227) between said sign and said vehicle, said determination of the current driving side is based on said third lateral distance (227). A method according to claim 1, wherein said method further comprises a step of creating (305) a signal representing a warning of driving in the wrong direction, and emitting said signal to destination of a human-machine interface, said human-machine interface being configured to alert an occupant of said vehicle of the current driving in the opposite direction.

3. A method according to any one of the preceding claims, wherein said determination (301) of said country code in which said vehicle is circulating is obtained from information processing, said information being transmitted by radio frequency, and / or said determination of said country code is obtained by geolocation associated with mapping.

4. A method according to any one of the preceding claims, wherein said method further comprises a step of determining traffic on a one-way carriageway, and when one-way traffic is determined, said step of creating said signal representing a warning of driving in the wrong direction is inhibited.

5. Device (101) comprising a memory (102) associated with at least one processor (103) configured to implement the method according to one of the preceding claims.

6.

7. Vehicle comprising the device according to the preceding claim. Computer program comprising instructions which, when the program is executed by the device (101), cause the device to implement the method according to any one of claims 1 to 4.

Images