METHOD AND DEVICE FOR DETERMINING THE RELIABILITY OF A LOW-RESOLUTION MAP

Description

[0001] The present invention claims priority from French application 2102516 filed on 03 / 15 / 2021.

[0002] The invention is in the field of autonomous vehicle driving assistance systems. In particular, the invention relates to determining the reliability of a low-definition map to make the activation of at least one autonomous vehicle driving assistance system more reliable.

[0003] A "vehicle" means any type of vehicle such as a motor vehicle, a moped, a motorcycle, a storage robot in a warehouse, etc. "Autonomous driving" of an "autonomous vehicle" means any process capable of assisting the driving of the vehicle. The process may thus consist of partially or totally steering the vehicle or providing any type of assistance to a natural person driving the vehicle. The process thus covers all autonomous driving, from level 0 to level 5 in the OICA scale, for International Organization of Motor Vehicle Manufacturers.

[0004] Among the driving assistance systems, there are known, for example, lane keeping devices, lane change devices, adaptive cruise control devices, ...

[0005] A vehicle, comprising one of these devices, comprises numerous sensors such as a camera, a RADAR, a LIDAR, ultrasounds, accelerometers, an inertial unit, position or location sensors, speed sensors, acceleration sensors, etc. Information processing carried out by at least one computer on board the vehicle is known, which makes it possible to perceive the environment. By environment, we mean the exterior and interior of the vehicle. This perception of the environment makes it possible to measure a slope of a road on which the vehicle is traveling and to determine a trajectory of the road on which the vehicle is traveling. Determining the trajectory of the road is, for example, determining the coefficients of at least one polynomial that models the trajectory of the road. For example, the trajectory is divided into several segments or several portions. Each segment or portion is modeled by a polynomial.

[0006] Furthermore, this vehicle also includes a navigation system that includes a means of locating itself and a map. There are different types of mapping. High-definition mapping, called HD mapping, characterizes the lanes and attributes related to the road such as the number of lanes, curvatures of the road, a slope of the road, road signs, etc. Furthermore, with HD mapping, the navigation system, which is connected to servers external to the vehicle by telecommunications links, regularly updates the mapping. Thus, the attributes related to the road are very up-to-date. Furthermore, in HD mapping, the attributes are well positioned (resolution of 1 meter).

[0007] In a SD map, a simple definition, the characterization of the roads is less precise and the attributes are not always well digitized (missing or less precise positioning of the order of several meters). The map is also less regularly updated. If this update is carried out manually and annually from a database of a mapping provider, the data is then on average dated 6 months.

[0008] Document FR3090547 discloses a device for verifying a high-definition map of a motor vehicle. Document CN111767354 discloses a method for evaluating high-precision cartographic accuracy. Document FR3082349 discloses a vehicle-mounted driving assistance system. Document US2019 / 227545 discloses a device and method for assisting vehicle driving. Document US2007 / 299606 discloses a driving assistance system. Document EP2282170 discloses a device for specifying the reliability of information used for driving assistance.

[0009] Through regular updating and attribute accuracy, HD mapping is inherently reliable. Thus, it is known that ADAS systems in a vehicle that include HD mapping use information from the mapping to improve the functionalities of these ADAS systems. For example, these functionalities are able to act on the longitudinal and transverse dynamics of the vehicle by activating a driver assistance system (for example, modifying a set speed, changing the position of the vehicle in the lane, etc.). Unfortunately, the cost of embedding HD mapping is very high compared to the manufacturing cost of a vehicle. If the vehicle has an SD map, it is dangerous to condition activations or modifications of driver assistance system instructions that directly affect the steering and / or speed of the vehicle. SD mapping is not reliable enough.

[0010] In order to use mapping information by a driver assistance system, devices are known that calculate an instantaneous indicator of mapping reliability. In particular, the location accuracy given by a GPS (Global Positioning System) type device is used. However, these devices calculating an instantaneous indicator of mapping reliability, on the one hand, assume that the information to calculate the indicator is continuously available and, on the other hand, remain quite conceptual in implementation. Unfortunately, the perception of the environment requires a large volume of information to be processed, and therefore a high computational load. Thus, in certain use cases (many vehicles around the autonomous vehicle, strong accelerations or decelerations, etc.) or weather conditions, certain perception information is regularly missing or arrives late.Furthermore, perception information from image processing is also regularly missing due to available visibility (for example, a truck may hide a road sign at the side of the road). Thus, the calculations of an instantaneous indicator of mapping reliability periodically when the vehicle is traveling on a road vary abruptly and randomly. The indicator is then unstable, unreliable and unusable, for safety reasons, in driver assistance systems.

[0011] An object of the present invention is to remedy the aforementioned problem, in particular to make the information, characteristics of the track and attributes, resulting from an SD map more reliable.

[0012] To this end, a first aspect of the invention relates to a method for determining the reliability of a low-definition map to make the activation of at least one driving assistance system of an autonomous vehicle more reliable, said autonomous vehicle traveling on a road and comprising a navigation system and a perception system, the navigation system comprising said map and providing at least one slope and at least one curvature of the road around said vehicle, called mapped slope and mapped curvature, the perception system providing a slope and a trajectory of the road around said vehicle, called measured slope and measured trajectory, said method being updated periodically when said vehicle is traveling on the road and comprising the steps of: Determining a trajectory of the road, called the mapped trajectory, from at least the mapped curvature; Determining a slope indicator indicating a match between the mapped slope and the measured slope, the slope indicator being a number between 0 and 1, the value 1 indicating a strong match and the value 0 indicating a lack of match; Determining a trajectory indicator indicating a match between the mapped trajectory and the measured trajectory, the trajectory indicator being a number between 0 and 1, the value 1 indicating a strong match and the value 0 indicating a lack of match; Calculating a correlation value from the slope indicator and the trajectory indicator; Determining a mapping reliability indicator, reliable or unreliable, the indicator being reliable if the correlation value is greater than a predetermined threshold.

[0013] Thus, if there is good reliability, this means that the mapped data is substantially equal to the measured data. The navigation system then positions the vehicle correctly on the map, and also that the map is locally reliable (from the perception distance). A driver assistance system that controls the longitudinal and / or lateral dynamics of the vehicle can rely on the data from the map.

[0014] The use of both indicators makes an update of the correlation value predictive and reactive. It is predictive thanks to the trajectory indicator which is based on a distant vision of the perception system (between 30 and 300 meters for example). It is reactive thanks to the slope indicator which is based on a very close vision of the vehicle, the measurement of the slope is only known where the vehicle is traveling, or has traveled.

[0015] Furthermore, the reliability is also robust to short random detection and localization errors due to computational overhead. This robustness is due to the calculation of the correlation value and a level-based determination.

[0016] Advantageously, the determination of the mapping reliability indicator is on four levels - strong, medium, insufficient or undefined - the levels being defined according to the correlation value.

[0017] Thus, if previously good reliability was determined, then if the correlation value decreases in the absence of a mapped and / or measured trajectory or slope, we do not move directly to insufficient or indefinite reliability, which risks abruptly stopping a driving aid.

[0018] Advantageously, the slope indicator increases or decreases according to a calculated gradient, the gradient being a function of the difference between the mapped slope and the measured slope.

[0019] Thus, the history is taken into account if previously good reliability was determined, then if the slope indicator decreases we do not move directly to poor reliability or undetermined inconsistency, which risks abruptly stopping a driving aid.

[0020] Advantageously, the trajectory indicator increases or decreases according to a calculated gradient, the gradient being a function of the lateral deviation between the mapped trajectory and the measured trajectory.

[0021] Thus, the history is taken into account if previously good reliability was determined, then if the trajectory indicator decreases we do not move directly to low reliability or undetermined inconsistency, which risks abruptly stopping driving assistance.

[0022] Advantageously, the correlation value is a weighting between the slope indicator and the trajectory indicator.

[0023] Advantageously, the determination of the mapped trajectory is obtained from interpolation of the at least one mapped curvature.

[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 adapted for executing the steps of the method, according to the first aspect of the invention, when said program is executed by at least one processor.

[0027] Other characteristics and advantages of the invention will emerge from the description of the non-limiting embodiments of the invention below, with reference to the appended figures, in which: [ Fig. 1 ] schematically illustrates a device, according to a particular exemplary embodiment of the present invention. [ Fig. 2 ] schematically illustrates a method for determining the reliability of a low-definition map, according to a particular example embodiment of the present invention.

[0028] The invention is described below in its non-limiting application to the case of an autonomous motor vehicle traveling on a road or on a traffic lane. Other applications such as a robot in a storage warehouse or a motorcycle on a country road are also conceivable.

[0029] There figure 1 represents 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 in charge of at least certain steps of the method described below with reference to the figure 2 In one embodiment, it corresponds to an autonomous driving computer.

[0030] In the present invention, the device 101 is included in the vehicle.

[0031] This device 101 can take the form of a box comprising printed circuits, any type of computer or even a mobile telephone (“smartphone”).

[0032] The device 101 comprises a random access memory 102 for storing instructions for the implementation by a processor 103 of at least one step of the method as described above. The device also comprises a mass memory 104 for storing data intended to be retained after the implementation of the method.

[0033] The device 101 may further comprise a digital signal processor (DSP) 105. This DSP 105 receives data to format, demodulate and amplify, in a manner known per se, this data.

[0034] The device 101 also comprises 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.

[0035] There figure 2 schematically illustrates a method for determining the reliability of a low-definition map, according to a particular exemplary embodiment of the present invention.

[0036] The method is implemented by a device 101 in an autonomous vehicle which comprises at least one driving assistance system. Said autonomous vehicle travels on a road and comprises a navigation system and a perception system.

[0037] Said navigation system comprises said mapping and provides at least one slope and at least one curvature of the road around said vehicle, called mapped slope and mapped curvature. Said perception system provides a slope and a trajectory of the road around said vehicle, called measured slope and measured trajectory.

[0038] When the vehicle is moving, said method is updated periodically, for example every 100 ms, but another value is possible. In one embodiment, the update is also made on a detected event or on a request from one of the driving assistance systems.

[0039] Step 201, DetTrajc, is a step of determining a trajectory of the road, called mapped trajectory, from at least the mapped curvature. In a preferred operating mode, the navigation system provides information around the vehicle in a horizon covering, for example, from 3000 meters in front of the vehicle to -500 meters (therefore behind the vehicle). On this horizon, the map is divided into segments. Each segment represents a portion of the road on which the vehicle is traveling. A portion therefore includes a distance. The at least mapped curvature corresponds to a curvature per segment as well as the length of the segment. Placed end to end, all of the segments represent the road on which the vehicle is traveling at the given horizon.

[0040] Thus, from the curvatures of each segment, a trajectory of the road, called the mapped trajectory, is determined. This determination is carried out, for example, by determining a polynomial calculated from the data of the at least one mapped curvature. In another example, this determination is obtained from interpolation of the at least one mapped curvature.

[0041] Step 2020, Detlp, is a step of determining a slope indicator indicating a match between the mapped slope and the measured slope, the slope indicator being a number between 0 and 1, the value 1 indicating a strong match and the value 0 indicating a lack of match.

[0042] In an operating mode, if the absolute and / or relative difference between the mapped slope, slope provided by the navigation system at the location where the vehicle is traveling, and the measured slope is less than a predetermined threshold, then the slope indicator is equal to 1, otherwise the slope indicator is equal to 0.

[0043] In a preferred operating mode, the slope indicator increases or decreases according to a calculated gradient, the gradient being a function of the difference between the mapped slope and the measured slope. The gradient is a number between -1 and 1. Depending on the difference, a gradient value is chosen. For example, if the difference is less than a threshold, the gradient is equal to 0.002, otherwise, the gradient is equal to -0.002. Thus, at each period, the slope indicator is updated, taking into account the history, which ensures robustness to random measurement errors and / or mapping errors and / or inaccuracies.

[0044] In another operating mode, the gradient is also a function of the variation in the measured slope. In the event of strong acceleration or deceleration, the measured slope is temporarily more heavily affected by errors. For example, the gradient is equal to 0.004 if the variation in the slope is less than another predetermined threshold and if the difference between the mapped slope and the measured slope is less than a predetermined threshold.

[0045] Step 203, Detltraj, is a step of determining a trajectory indicator indicating a match between the mapped trajectory and the measured trajectory, the trajectory indicator being a number between 0 and 1, the value 1 indicating a strong match and the value 0 indicating a lack of match.

[0046] In an operating mode, if the absolute and / or relative lateral deviation between the mapped trajectory and the measured trajectory is less than a predetermined threshold, then the slope indicator is equal to 1, otherwise the slope indicator is equal to 0.

[0047] In a preferred operating mode, the trajectory indicator increases or decreases according to a calculated gradient, the gradient being a function of the lateral deviation between the mapped trajectory and the measured trajectory. The gradient is a number between -1 and 1. Depending on the deviation, a gradient value is chosen. For example, if the deviation is less than a threshold, the gradient is equal to 0.002, otherwise, the gradient is equal to - 0.002. Thus, at each period, the trajectory indicator is updated, taking into account the history, which ensures robustness to random measurement errors and / or mapping errors and / or inaccuracies.

[0048] In another operating mode, the gradient is a function of a combination of the deviation between the mapped trajectory and the measured trajectory for each segment. The greater the number of deviations below a threshold, the higher the gradient.

[0049] Step 204, CalcCor, is a step of calculating a correlation value from the slope indicator and the trajectory indicator. Advantageously, the correlation value is a weighting between the slope indicator and the trajectory indicator. The correlation value is a number between 0 and 1. For example, the correlation value is equal to 40% of the slope indicator added to 60% of the trajectory indicator. The percentages given are for example purposes; other values ​​are possible. Ideally, the percentage of the slope indicator is lower than the trajectory indicator, the trajectory indicator being more robust. The percentage may also be a function of other parameters, such as at least one threshold of the variation of the measured slope.

[0050] Step 205, DetFia, is a step for determining a mapping reliability indicator, reliable or unreliable, the indicator being reliable if the correlation value is greater than a predetermined threshold. Advantageously, the determination of the mapping reliability indicator is on four levels - strong, average, insufficient or undefined - the levels being defined according to the correlation value. If the trajectory indicator and the slope indicator vary according to a gradient, the history is taken into account. Thus, if the correlation value is close to 1 this means that for a duration of several tens of seconds the slope and trajectory indicators are close to 1 and that therefore there is a very good agreement between the mapping and the environment.The mapping is therefore reliable and it will certainly be reliable over the next tens of seconds even if there are strong accelerations / decelerations of the vehicle which degrade the slope measurements, and if there are steering wheel movements to avoid which disrupt the determination of the trajectory measured by the perception device.

[0051] The present invention is not limited to the embodiments described above as examples; it extends to other variants. For example, numerical values ​​have been given in particular for the gradients. Other values ​​are possible and depend, for example, on the update period of the procedure.

Claims

1. A method of determining the reliability of a low resolution cartography to reliably activate at least one driver assistance system of an autonomous vehicle, the autonomous vehicle traveling on a road and comprising a navigation system and a perception system, the navigation system comprising the cartography and providing at least one slope and at least one curvature of the road around the vehicle, the slope being mapped and the curvature being mapped, the perception system providing a slope and a path of the road around the vehicle, the slope being measured and the path being measured, the method being characterized in that it is performed to regularly update when the vehicle is traveling on the road, and to perform the following steps: · Determination (201) of a so-called cartographic lane, starting from at least the cartographic curvature; · Determination (202) of an inclination indicator indicating a match between the inclination imaged and the measured inclination, wherein the inclination indicator is a number between 0 and 1 and the value 1 indicates a strong match and the value 0 indicates a non-match; · Determination (203) of a trajectory indicator indicating a match between the trajectory imaged and the trajectory measured, wherein the trajectory indicator is a number between 0 and 1 and the value 1 indicates a strong match and the value 0 indicates a mismatch; · Calculation (204) of a correlation value from the slope indicator and the trajectory indicator; · Determination (205) of a reliable or unreliable indicator of the reliability of the mapping, the indicator being reliable if the correlation value exceeds a predetermined threshold value.

2. Method according to Claim 1, in which the determination (205) of the reliability indicator of the image is carried out on four levels - strong, medium, inadequate or undefined - the levels being defined as a function of the correlation value.

3. A method as claimed in any preceding claim, wherein the slope indicator increases or decreases according to a calculated gradient, the gradient being a function of the deviation between the mapped slope and the measured slope.

4. A method as claimed in any preceding claim, wherein the trajectory indicator increases or decreases according to a calculated gradient, the gradient being a function of the lateral deviation between the imaged trajectory and the measured trajectory.

5. A method as claimed in any preceding claim, wherein the correlation value is a weight between the slope indicator and the path indicator.

6. A method as claimed in any preceding claim, wherein the determination of the imaged path is obtained from interpolation of the at least one imaged curvature.

7. Apparatus (101) comprising a memory (102) associated with at least one processor (103) configured to perform the method of any preceding claim.

8. A vehicle comprising the device according to the preceding claim.

9. A computer program comprising instructions adapted to perform the steps of the method of any one of claims 1 to 6 when the program is executed by at least one processor (103).