METHOD AND DEVICE FOR CONTROLLING A SPEED CONTROL SYSTEM OF AN AUTONOMOUS VEHICLE

Description

Technical field of the invention

[0001] The invention relates to autonomous vehicle driver assistance systems. In particular, the invention concerns a speed control system for an autonomous vehicle to manage acceleration of said vehicle approaching a roundabout. State of the art

[0002] The term "vehicle" refers to any type of vehicle, such as a car, moped, motorcycle, warehouse robot, etc. "Autonomous driving" of a "vehicle" refers to any process capable of assisting the driving of the vehicle; the "vehicle" is then also called an "autonomous 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] DE 10 2018 210648 A1 discloses a method for controlling the speed regulation of an autonomous vehicle to manage the acceleration of said vehicle approaching a roundabout, said method being implemented by a processor and comprising a step of determining, from data from a simple definition map and a geolocation system, a first distance, relative to said vehicle, from the beginning of said roundabout, and a first type of first road sign.

[0004] Among the driver assistance systems, examples include lane keeping assist, lane change assist, adaptive cruise control, etc.

[0005] A vehicle equipped with one of these systems includes numerous sensors such as a camera, radar, lidar, ultrasonic sensors, accelerometers, an inertial measurement unit (IMU), position or location sensors, speed sensors, acceleration sensors, and so on. It is known that information is processed by at least one onboard computer, enabling it to perceive its environment. The environment encompasses both the exterior and interior of the vehicle.

[0006] This perception of the environment enables the identification, location, and recognition of road signs, such as signs or traffic lights. Specifically, with the use of an onboard camera and appropriate image processing, it is possible to identify road signs, such as signs or traffic lights, determine the type of sign (for example, a sign type like a STOP sign, or a traffic light type like a three-color traffic light), and determine the distance between the vehicle and the identified road sign.

[0007] Furthermore, this vehicle also includes a navigation system that provides location services and mapping. There are different types of mapping. High-definition mapping, also known as HD mapping, details roads and road-related attributes such as the number of lanes, road curves, gradients, road signs, and so on. With HD mapping, the navigation system, which connects to servers outside the vehicle via telecommunications links, regularly updates the map data. This ensures that road-related attributes are kept current. Additionally, in HD mapping, the attributes are accurately positioned (1-meter resolution).

[0008] Another type of mapping is SD mapping, or simple definition mapping. Lane characterization is significantly less precise, and attributes are not always accurately digitized (missing or less precise positioning on the order of several meters). In SD mapping, all the lanes of a single road, roundabout, etc., are represented by a single line. There is no information or positioning based on lateral distance relative to the road edge or the vehicle's position. Thus, the location of a roundabout entrance is very inaccurate compared to reality. A positioning error at the start of a roundabout is on the order of half the width of a lane multiplied by the number of lanes in the roundabout, plus the positioning error at the start of the roundabout due to the mapping resolution.For example, if we take the roundabout at Place Charles de Gaulle in Paris (Arc de Triomphe roundabout), the error is more than ten meters.

[0009] Adaptive cruise control systems have been developed that manage vehicle acceleration based on a probable trajectory using information from an SD map. Because the starting point of a roundabout on an SD map is generally further away than the actual start of the roundabout, and because this distance difference is not constant and is not determined by the map, cruise control can be uncomfortable and anxiety-inducing. Drivers approach roundabouts faster than a normal driver, requiring harder braking within the roundabout to avoid excessive lateral acceleration, which is also uncomfortable. Summary of the invention

[0010] One object of the present invention is to remedy the aforementioned problem, in particular to improve the accuracy of locating the beginning of a roundabout and to regulate the speed of the vehicle, for example applying a deceleration, as a driver would do.

[0011] To this end, a first aspect of the invention relates to a method for controlling the speed regulation of an autonomous vehicle to manage the acceleration of said vehicle approaching a roundabout, said method being implemented by a processor and comprising the steps of: Determination, from data from a simple definition map and a geolocation system, of: ∘ a first distance, relative to said vehicle, from the start of said roundabout; ∘ a first type of first road sign; and ∘ a second distance, relative to said vehicle, from said first road sign when said first type relates to an intersection or a priority road; Determination of a new starting distance of said roundabout based on said first distance, on said first type and on said second distance; Regulation of the vehicle's speed from said new starting distance of roundabout.

[0012] Therefore, the distance between the vehicle and the start of the roundabout is calculated differently. Taking into account the position of road signs indicating an intersection or priority road, as well as the type of road signage, makes the actual distance from the start of the roundabout to the vehicle more predictable. The variation due to the size or number of lanes of the roundabout is no longer a factor.

[0013] Advantageously, the process also includes the following steps: Determination, from data from a camera mounted on said vehicle, ∘ of a second type of second road sign; and ∘ of a third distance, in relation to said vehicle, of said second road sign when said second type relates to an intersection or a priority road; and in which the determination of said new starting distance of said roundabout is, moreover, based on said second type and on said third distance.

[0014] First, by comparing the first type of road sign to the second type, and then comparing the second distance to the third distance, we can identify that the second road sign is the same as the first. This improves the reliability of determining the distance between the vehicle and the road sign by reducing positioning uncertainties, relative to reality, of objects (road type, road signs, etc.) derived from simple mapping. By combining this information, the environment is better represented. Determining the start of the roundabout (the new distance) is then more repeatable, more precise, and closer to reality. In this way, we reduce the positioning uncertainties associated with simple mapping. This allows for better speed control and acceleration management of the vehicle before entering a roundabout.The vehicle's speed profile before entering a roundabout is closer to what a driver does.

[0015] Advantageously, a road sign whose type relates to an intersection or priority road is a stop sign, a yield sign, or another intersection or priority sign, or in which a road sign whose type relates to an intersection or priority road is a traffic light or other intersection light.

[0016] Advantageously, an intersection or priority sign is also a position sign.

[0017] Therefore, advance warning signs, which indicate the entrance to a roundabout more than 50 meters in advance, are not taken into account. A position sign is placed approximately ten centimeters before the actual start of the signaled area. It indicates the position. An advance warning sign is often accompanied by a supplementary panel indicating a distance before the start, for example, "150 m". However, the actual location of the advance warning sign relative to the indicated distance is approximately 50 m. The indicated distance should not be used to determine the new distance, otherwise the new distance will be less precise.

[0018] A second aspect of the invention relates to a device comprising a simple definition map, a geolocation system, an on-board camera, a memory associated with at least one processor configured to implement the method according to the first aspect of the invention.

[0019] The invention also relates to a vehicle incorporating the device.

[0020] 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

[0021] Other features and advantages of the invention will become apparent from the description of the non-limiting embodiments of the invention below, with reference to the accompanying figures, in which: [ Fig. 1[ ] schematically illustrates a device, according to a particular embodiment of the present invention. ] Fig. 2 [ ] schematically illustrates a vehicle arriving at a roundabout according to a real-life view. ] Fig. 3 [ ] schematically illustrates a vehicle arriving at a roundabout based on data from a simple definition map and a geolocation system. Fig. 4 ] schematically illustrates a method for controlling the speed regulation of an autonomous vehicle, according to a particular embodiment of the present invention. Detailed description of the invention

[0022] The invention is described below in its non-limiting application to the case of an autonomous motor vehicle traveling on a road or traffic lane. Other applications, such as a robot in a warehouse or a motorcycle on a country road, are also conceivable.

[0023] The term "horizontal plane" refers to a plane substantially parallel to the horizontal plane of a road at the point where the vehicle is traveling. The term "longitudinal axis" refers to a straight line substantially parallel to the lateral sides, including the doors, of the vehicle and substantially parallel to the horizontal plane. The term "lateral axis" or "transverse axis" refers to a straight line perpendicular to the longitudinal axis such that the plane formed by the longitudinal and lateral axes is parallel to the horizontal plane. A longitudinal distance is a distance measured along an axis parallel to the longitudinal axis. A lateral distance is a distance measured along an axis parallel to the lateral axis. The terms "front," "downstream," "rear," and "upstream" refer to the longitudinal axis in the normal direction of travel of the vehicle.

[0024] There figure 1represents 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 the figure 4 In one embodiment, it corresponds to an autonomous driving computer.

[0025] In this description, device 101 is included in the vehicle.

[0026] This 101 device can take the form of a case containing printed circuits, any type of computer or even a mobile phone (“smartphone”).

[0027] 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 below. The device also includes a mass storage 104 for storing data intended to be retained after the implementation of the process.

[0028] 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.

[0029] Device 101 also includes an input interface 106 for receiving data implemented by the method according to the invention and an output interface 107 for transmitting data implemented by the method according to the invention.

[0030] For example, input interface 106 can receive the following data: vehicle position or geographic location, vehicle speed and / or acceleration, target or predetermined positions / speeds / accelerations, engine speed, position and / or travel of the clutch, brake, and / or accelerator pedals, detection of other vehicles or objects, position or geographic location of other detected vehicles or objects, speed and / or acceleration of other detected vehicles or objects, sensor operating states, confidence level of data from or processed by sensors and / or devices similar to device 101. For example, sensors capable of providing data include: GPS (with or without mapping), tachometers, accelerometers, radar, lidar, lasers, ultrasound, cameras, etc.

[0031] In the present invention, the input interface 106 can also receive data from a simple definition map and a geolocation system, such as the distance from the start of a roundabout to the vehicle, the type of road sign, and the distance of a road sign from the vehicle. The input interface 106 can also receive data from a camera mounted on the vehicle, such as the type of road sign and the distance from the start of a roundabout to the vehicle.

[0032] For example, the output interface 107 can transmit data similar to the data received by the input interface 106. In the present invention, the output interface 107 can also transmit a new distance from a roundabout start relative to the vehicle, a command to a speed regulation controller to take the new distance into account.

[0033] [ Fig. 2 [This diagram schematically illustrates a vehicle 230 arriving at a roundabout 200 according to a real-life view. The roundabout 200 has a central island 207 and two traffic lanes 201, 202. The two traffic lanes 201, 202 are separated by road markings 203. Road markings 203 are located in the center of the traffic lanes of the roundabout 200. The arrow 205 indicates a direction of travel.]

[0034] Route 210 provides access to and from roundabout 200. This route has four lanes: 211, 212, 213, and 214. Arrows 215 and 216 indicate the direction of travel. Lanes 211 and 213 are separated by road markings and allow vehicles to enter roundabout 200. Lanes 212 and 214 are also separated by road markings and allow vehicles to exit roundabout 200.

[0035] A second route, 220, also provides access to and from roundabout 200. This second route, 220, has four lanes: 221, 222, 223, and 224. Arrows 225 and 226 indicate the direction of travel. Lanes 221 and 223 are separated by road markings and allow vehicles to exit roundabout 200. Lanes 212 and 214 are also separated by road markings and allow vehicles to enter roundabout 200.

[0036] Vehicle 230 is traveling on the first road 210 in lane 213 in the direction of travel indicated by arrow 215. A double arrow 231 indicates a distance, a longitudinal distance, between vehicle 230, more precisely the origin of a landmark linked to the vehicle, and the start of roundabout 200. At the entrance and upstream of roundabout 200, there is road sign 232. Road sign 232 is located, generally at the roadside, between vehicle 230 and the entrance to the roundabout. A double arrow 233 indicates a longitudinal distance between vehicle 230 and road sign 232.

[0037] The origin of vehicle 230 is a point related to the vehicle. For example, the center of gravity, the center of the front axle, the center of the front bumper, etc.

[0038] A double arrow 234 indicates a lateral distance between the vehicle 230 and a road-related origin 210. This origin may be a road edge. In the example of the figure 2 , this origin corresponds to the shortest distance between the origin of the vehicle and a right edge of Route 210 on which the vehicle is travelling.

[0039] Distances 233 and 234 indicate the vehicle's position relative to road signs. The roundabout entrance is defined as the intersection of a lane of the roundabout's entry road with lane 201, the outer lane of the roundabout. Road signs are located in the immediate vicinity of the roundabout. This immediate vicinity is generally about ten centimeters before the roundabout entrance.

[0040] Road sign 231 is a type of road sign related to an intersection or priority road. This can be a sign or a traffic light. The type of sign must be related to an intersection or priority road. For example, the type of sign is a stop sign, a yield sign, or another intersection or priority sign.

[0041] Advantageously, an intersection or priority sign is also a position sign. A position sign, or position sign, is distinct from an advance warning sign. An advance warning sign indicates a signal in advance. The distance "in advance" is approximate and can be off by as much as 25 meters.

[0042] The type of traffic light must be relevant to an intersection or a priority road. For example, the type of traffic light is a three-color traffic light, or another type of intersection traffic light.

[0043] [ Fig. 3 [This diagram schematically illustrates vehicles 230 and 330 arriving at roundabout 200, based on data from a simple definition map and a geolocation system. It shows the outer edge of roundabout 200, the central reservation 207, the first road 210 and the second road 220, and vehicle 230 of the roundabout.] figure 2 are represented by dotted lines. Dotted line representations are not known from a simple definition map.

[0044] Data from a simple definition map and a geolocation system allows vehicle 230 to be placed on line 301, a thick black line representing a probable future trajectory of the vehicle and corresponding to a past trajectory over a predetermined period. The vehicle's position is represented here by square 330.

[0045] Point 311 represents the position, longitudinal distance along line 301, and therefore also the distance relative to vehicle 330, according to the map, of the start of the roundabout. Point 312 represents the position, longitudinal distance along line 301, and therefore also the distance relative to vehicle 330, according to the map, of one end of the roundabout. Typically, line 301 within the roundabout corresponds to the midpoint of the combined width of all the roundabout's lanes.

[0046] A double arrow 331 indicates a distance between vehicle 330 and the start of roundabout 311 provided by data from a simple definition map and a geolocation system.

[0047] A road sign 332 represents road sign 232 on line 301. A double arrow 333 indicates a distance between vehicle 330 and road sign 332.

[0048] There figure 2 and the figure 3 allow us to illustrate the positioning error of the beginning of a roundabout using data from a simple definition map and a geolocation system and comparison with the "real".

[0049] [ Fig. 4[The diagram schematically illustrates a method for controlling the speed regulation of an autonomous vehicle, according to a particular embodiment of the present invention. The method manages the acceleration of said vehicle 230 as it approaches the roundabout 200. The method is implemented by a processor 103. The method comprises several steps.]

[0050] Step 400, Dist1, is a determination step, based on data from a simple definition map and a geolocation system, of an initial distance, relative to the vehicle, from the start of the roundabout. In the "real" world, the initial distance is reference 231 in Figure 2. According to the data, the initial distance is reference 331 in the figure 3 .

[0051] It is known that data processing from a simple definition map associated with a geolocation system makes it possible to provide, in relation to the vehicle and on possible future trajectories of the vehicle, a type of road, roundabout for example, the presence of road signs and their type, ... This information is given in relation to a distance from the vehicle.

[0052] For example, a vehicle is traveling on a national highway and heading towards a roundabout whose starting point is 1000 m from the vehicle. An advance "yield" sign is 325 m from the start of the roundabout, with a supplementary sign indicating that the roundabout is 300 m away. A position "yield" sign is 0.20 m from the start of the roundabout. In this example, data from a simple definition map and a geolocation system can provide: a new type of road at 1005 m, which determines the start of the roundabout at 1005 m; a first type of road sign being a "yield" sign at a first distance of 675 m from the vehicle, the road sign corresponding to the advance sign; a second type of road sign being a "yield" sign at a second distance of 999 m from the vehicle, the road sign corresponding to a position sign. The data can also provide a type and distance of road signage not related to an intersection or priority road such as a speed limit, or other.

[0053] Step 410, Type 1, is a determination step, based on data from a simple definition map and a geolocation system, of a first type of a first road sign.

[0054] In the example above, said first type can be the first first type and / or the second first type.

[0055] Step 420, Dist2, is a determination step, based on data from a simple definition map and a geolocation system, of a second distance, relative to said vehicle, from said first road sign when said first type relates to an intersection or a priority road.

[0056] Therefore, if the first type of sign is not related to an intersection or a priority road, the second distance is not determined. This allows for filtering, and thus excluding, road signs not related to an intersection or a priority road, in order to reduce computational load.

[0057] In the example above, said second distance can be the first second distance and / or the second second distance.

[0058] In a procedure, a step 450, NewDist, is a step for determining a new starting distance of said roundabout based on said first distance, said first type and said second distance.

[0059] Several methods can be used to determine this new distance. In one method, quite simply, the new distance is equal to the second distance. In another method, the difference between the first and second distances is taken into account to determine the new distance. Also, for example, based on the first method, a new distance is calculated only for certain types of road signs. This allows, for example, the exclusion of advance signs. The determination of the new distance can also be adjusted according to the type of sign or traffic light. Indeed, a position sign is generally placed at the very beginning of the roundabout, while a traffic light is generally placed 1 or 2 meters from the start of the roundabout to, for example, allow space for a pedestrian crossing.

[0060] In the example above, for instance, the first second distance is not taken into account because the first type of signage corresponds to an advance warning sign. However, since the second type of sign, a "yield" position sign, relates to an intersection or a priority road and is of a specific position, the new distance can be equal to the second second distance, i.e., 999 m, if the difference between the first and second distances is small (on the order of 5 m, but other values ​​are possible).

[0061] Step 430, Type 2, is a step to determine, from data from a camera mounted on said vehicle, a second type of a second road sign.

[0062] Step 440, Dist3, is a step of determining, from data from a camera on board said vehicle, a third distance, relative to said vehicle, from said second road sign when said second type relates to an intersection or a priority road.

[0063] It is known that a camera mounted on a vehicle, through appropriate image processing, is capable of identifying and characterizing objects located within the camera's field of vision. For example, the data can include the presence of road signs, their type, and their distance from the vehicle.

[0064] It is also known that an onboard camera can only provide reliable and accurate data for objects detected within approximately 200 meters. This 200-meter distance depends on the camera's characteristics (resolution, etc.) and image processing. Other values ​​are possible.

[0065] In the example above, we will assume that the vehicle is now approximately 150 meters from the start of the roundabout. Data from a simple definition map and a geolocation system, along with data from a camera mounted on the vehicle, can provide: a new type of road at 155 m, which determines the start of the roundabout at 155 m; a first type of road sign being a "yield" sign at a second distance of 149 m from the vehicle, the road sign corresponding to a position sign; and a second type of road sign being a "yield" sign at a third distance of 150 m from the vehicle, the road sign corresponding to a position sign.

[0066] Step 450, New Dist, is a step for determining a new starting distance for said roundabout based on said first distance, said first type, and said second distance. An example, in the absence of camera data, was described above.

[0067] Advantageously, the determination of the new starting distance of the roundabout is also based on the second type and the third type of distance. Thus, data from the camera is also taken into account. To determine the new distance, the first type of distance, the second type of distance, and the third type of distance will be considered.

[0068] For example, the types can be used to disregard the second or third distance. Also, if the first and second types are different, the second or third distance can be prioritized depending on the confidence placed in the camera measurements. The third distance will be preferred if the camera measurements are consistent over several meters, as the data from a single-definition map may no longer be up-to-date. Several options are available for determining this new distance. One example is to use the third distance as the new distance.Another example is to take as the new distance the average between the second and third distances, if the difference between the first and second distances is less than a predetermined threshold and if the difference between the first and third distances is less than the same predetermined threshold or another predetermined threshold.

[0069] Step 460, Regul, regulates the vehicle's speed based on the new roundabout start distance. Simply put, the cruise control is controlled by inputting the new distance. Because this distance is more reliable than the roundabout start position provided by the mapping, the cruise control requires fewer corrections once the vehicle reaches the roundabout start. This results in a smoother and more pleasant driving experience for the vehicle's occupants.

[0070] The present invention is not limited to the embodiments described above by way of example; it extends to other variations. For example, the method has been described as a sequence of steps. Some steps may be performed in parallel or in a different sequence. Also, some steps may be performed iteratively for each road sign present in the map before the start of the roundabout and / or for each road sign detected by the camera before the start of the roundabout.

[0071] Advantageously, when data from a simple definition map and a geolocation system provide the type and distance of several primary road signs, the road sign whose type relates to an intersection or priority road and which has the shortest distance to the vehicle is taken into account. This avoids iterations and reduces the computational load.

[0072] Advantageously, when data from a camera mounted on the vehicle provides the type and distance of several secondary road signs, the road sign whose type relates to an intersection or priority road and which has the shortest distance from the vehicle is taken into account. This also avoids iterations and reduces the computational load.

Claims

1. Method of controlling a speed regulation of an autonomous vehicle to manage an acceleration of said vehicle arriving at a roundabout, said method being implemented by a processor (103) and comprising the steps of: • determining, from data derived from a single definition mapping and a geolocation system, a first distance (400), by report to said vehicle, a beginning of said roundabout, a first type (410) of a first road sign, and a second distance (420), by report to said vehicle, of said first road sign when said first type relates to an intersection or a priority route; • determining a new beginning distance (450) of said roundabout based on said first distance, on said first type and on said second distance; • regulating (460) the vehicle speed from said new roundabout beginning distance.

2. Method according to claim 1, wherein the method further comprises a step of determining (430), from data from a camera on board said previous vehicle, a second type of a second road sign, a step of determining (440), from data from a camera on board said vehicle, a third distance, by report to said vehicle, of said second road sign when said second type relates to an intersection or to a priority route, and wherein the determination of said new beginning distance (450) of said roundabout is, in addition, based on said second type and on said third distance.

3. Method as claimed in claim 1, wherein a road sign whose type relates to an intersection or priority sign is a stop sign, a stop sign, or another intersection or priority, or wherein a road sign whose type relates to an intersection or priority road is a traffic light or another intersection light.

4. Method according to claim previous, wherein an intersection or priority sign is also a position signalling panel.

5. Method as claimed in claim 1, wherein, when data from a previous mapping and a geolocation system provide a type and a distance of several first road signs, the road sign, the type of which relates to an intersection or to a priority route, having the smallest distance by report to said vehicle, is taken into account.

6. Method as claimed in claim 1, wherein, when data from a camera on board said previous vehicle provides a type and a distance of several second road signs, the road sign, the type of which relates to an intersection or to a priority route, having the smallest distance by report to said vehicle, is taken into account.

7. Device (101) comprising a single definition mapping, a geolocation system, a camera, a memory (102) associated with at least one processor (103) configured to implement the method according to one of the previous claims.

8. Vehicle comprising the device according to the previous claim.

9. Computer plan comprising instructions which, when the plan is executed by the device (101) according to claim 7, lead the latter to implement the method according to one of claims 1 to 6.