Method and device for storing a new lateral position of a lane-keeping system of an autonomous vehicle

Abstract

The invention relates to a method and a device for storing a new lateral position of a lane-keeping system of an autonomous vehicle, the system being activated, the method being implemented by a processor and comprising the steps of: - receiving (201) a lateral position, this position being a measurement of a lateral distance with respect to a traffic lane in which the vehicle is driving; - receiving (202), from a system for monitoring a driver of the vehicle, an indicator of level of attention; - determining (203) a first threshold as a function of the indicator of level of attention; - receiving (204) a level of force applied to the steering wheel; and - once the level of force becomes greater (205) than the first threshold, determining and storing (209) the new lateral position when the level of force then becomes lower (208) than a second threshold.

Description

DESCRIPTION TITLE: Method and device for memorizing a new lateral position of a lane-keeping system for an autonomous vehicle Technical field of the invention

[0001] The present invention claims priority from French application 2306638 filed on June 26, 2023, the content of which (text, drawings, and claims) is incorporated herein by reference. The invention relates to autonomous vehicle driver assistance systems. In particular, the invention concerns a method and device for memorizing a new lateral position of a lane-keeping system for an autonomous vehicle. 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 an "autonomous vehicle" refers to 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 systems designed to assist vehicle driving are also called ADAS (Advanced Driver Assistance Systems), ADAS systems, or driver assistance systems. The lane positioning assist function, also known as LPA or Lane Positioning Assist (Lane Positioning Assist), is a well-known ADAS function.

[0004] The Lane Following Assist (LPA) system identifies the lane markings within which the vehicle is traveling. LPA steers the vehicle within this lane to maintain it in a lateral position selected by the driver. The system uses a camera located at the top of the windshield for this purpose. The system is activated by pressing a dedicated button, which is located near the driver.

[0005] When activated, the Lane Following Assist (LPA) system determines the lateral position chosen by the driver. This position is not necessarily the center of the lane. The lateral position is a lateral deviation between a reference point linked to the vehicle, such as the center of gravity or the midpoint of the front axis, and one of the lane markings (left or right), along a lateral axis. The lateral axis is perpendicular to a longitudinal axis such that a plane formed by the longitudinal and lateral axes is parallel to a horizontal plane of the road. The longitudinal axis is parallel to the normal direction of travel of the vehicle. If the driver activates LPA when the vehicle is, for example, ten centimeters from the right lane marking, the LPA system will maintain the vehicle ten centimeters from the right lane marking.

[0006] As soon as the Lane Departure Warning (LDW) system is activated, a green pictogram appears on a display. This pictogram represents the left and right lane markings. Additionally, the system, through subtle steering adjustments, guides the vehicle and maintains it in the position selected by the driver within the lane.

[0007] The driver must hold the steering wheel correctly. The driver must apply less torque to the steering wheel than a predetermined threshold for the LPA system to detect steering wheel movements. At any time, by applying more torque to the steering wheel than the predetermined threshold, the driver can change the vehicle's position by moving the steering wheel and set a new lateral position. The predetermined threshold depends on the vehicle (size, weight, etc.) and its speed. For example, this threshold, expressed as steering wheel torque, varies from 1 to 1.2 Nm. As soon as the driver feels the vehicle's position is satisfactory, while keeping their hands on the steering wheel, they must release the pressure to allow the system to determine this new position. Releasing the pressure corresponds to approximately -0.2 Nm compared to the predetermined threshold.However, for drivers who hold the steering wheel very rigidly (close to the predetermined initial threshold), the system often determines new lateral positions, resulting in unintentional deviations from the lane center or from the previous position intended by the driver. Furthermore, the driver is unaware of the predetermined threshold level.

[0008] It has been observed that a tired or distracted driver does not hold the steering wheel in the same way as when the driver is not tired or when the driver is attentive to what is happening on the road. When tired, the driver has a "heavy" hand and holds the steering wheel rigidly. When distracted, the driver makes sporadic movements on the steering wheel. In both cases, the system often determines new lateral positions, resulting in unintentional misalignment. Summary of the invention

[0009] One object of the present invention is to remedy the aforementioned problem, in particular to avoid unintentional decentering or shifting in the track.

[0010] To this end, a first aspect of the invention relates to a method for memorizing a new lateral position of a lane-keeping system of an autonomous vehicle, said system being activated, said method being implemented by a processor and comprising the steps of: - Receipt of a lateral position, said position being a measurement of a lateral distance relative to a traffic lane in which said vehicle is traveling; - Reception, from a monitoring system of a driver of said vehicle, of an attention level indicator; - Determination of a first threshold based on said attention level indicator; - Reception of a level of force applied to the steering wheel; Once the effort level becomes greater than the first threshold, determination and memorization of the said new lateral position when the effort level then becomes less than a second threshold.

[0011] Thus, the initial threshold is adjusted according to the driver's level of attention. For a new lateral position to be memorized, a tired or distracted driver must apply more force to the steering wheel than when holding it during the position regulation phase. The driver's level of fatigue or distraction is then taken into account to modify the initial threshold and thus prevent unintentional shifts in center of gravity.

[0012] Advantageously, the determination of said new lateral position is a function of a history of received lateral position values.

[0013] This avoids a new positioning based on an outlier.

[0014] Advantageously, the process further includes a step of detecting an effort level greater than a third threshold, and a step of deactivating said lane-keeping system when the effort level becomes greater than said third threshold.

[0015] Thus, by applying significant force to the steering wheel, the driver can deactivate the system when necessary, for example to change lanes, overtake another vehicle, etc.

[0016] Advantageously, said second threshold is determined based on said attention level indicator.

[0017] Therefore, this second threshold will also be adjusted according to the level of attention to ensure consistent behavior. If the driver grips the steering wheel rigidly, the various thresholds are adjusted accordingly.

[0018] Advantageously, the said third is determined based on the said attention level indicator.

[0019] Thus, this third threshold will also be adjusted according to the level of attention to ensure consistent behavior. If the driver grips the steering wheel rigidly, the different thresholds are adjusted accordingly.

[0020] A second aspect of the invention relates to a device comprising the lane keeping system, the driver monitoring system, and a memory associated with at least one processor configured to implement the method according to the first aspect of the invention.

[0021] The invention also relates to a vehicle incorporating the device.

[0022] 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

[0023] 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:

[0024] [Fig. 1] schematically illustrates a device, according to a particular embodiment of the present invention.

[0025] [Fig. 2] schematically illustrates a method for memorizing a new lateral position of a lane-keeping system of an autonomous vehicle, according to a particular embodiment of the present invention. Detailed description of the invention

[0026] 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.

[0027] 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 2. In one embodiment, it corresponds to an autonomous driving computer.

[0028] In the present invention, the device 101 is included in the vehicle.

[0029] This 101 device can take the form of a case containing printed circuits, any type of computer or even a "smartphone" phone).

[0030] 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 storage 104 for storing data intended to be retained after the implementation of the process.

[0031] 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.

[0032] 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.

[0033] For example, input interface 106 can receive the following data: vehicle position or geographic location, vehicle speed and / or acceleration, setpoint or preset 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, operating states of Sensors, confidence index of data originating 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, driver monitoring systems...

[0034] Driver monitoring systems are well-established and capable of providing an indicator of a driver's attention level. These systems are typically called DMS (Driver Monitoring Systems). They can use image processing from cameras filming the driver's face to, for example, identify blink patterns or other information available in the vehicle (driving time, reaction time to a command, etc.).For example, these levels may be based on the detection of looking away from the road for a consecutive duration of more than 3 s, on the detection of looking away from the road for a cumulative duration of more than 10 s out of 30 s; on the detection of phone use, on the level of fatigue according to the KSS (Karolinska Spleepiness Scale), on the detection of closed eyes for less than 3 s, on the detection of closed eyes for more than 3 s.

[0035] In one example, the input interface receives a lateral position relative to a traffic lane in which the vehicle is traveling, an attention level indicator, a level of force applied to the steering wheel, a first, second, and third threshold of force applied to the steering wheel, ...

[0036] For example, the output interface 107 can transmit data similar to the data received by the input interface 106. The output interface 107 can transmit a new lateral position to be memorized, a first, second, and third set threshold, the result of a test comparing an effort level higher or lower than the first, second, and third set thresholds, a memorization request command, a deactivation command, ...

[0037] Memory 102 can record a history of information received through input interface 106 and a history of information sent through output interface 107.

[0038] [Fig. 2] schematically illustrates a method for memorizing a new lateral position of a lane-keeping system of an autonomous vehicle, according to a particular embodiment of the present invention.

[0039] The lane keeping assist system is activated. A lateral position is memorized. The system regulates the vehicle's lateral position relative to the left or right side of the lane in which the vehicle is traveling, so that the vehicle's lateral position converges towards the memorized lateral position.

[0040] Step 201, RxPos, is a lateral position reception step, said position being a measurement of a lateral distance relative to a traffic lane in which the vehicle is traveling. The lane-keeping system is capable of measuring the vehicle's lateral position. This measurement can come from also an environmental perception system around the vehicle or another ADAS system or device type 101.

[0041] Step 202, RXAtn, is a step involving the reception, from a driver monitoring system of said vehicle, of an attention level indicator. These driver monitoring systems are known. These systems are capable of providing a driver attention level indicator. The indicator can be a multi-state indicator, such as a state corresponding to low attention, a state corresponding to medium attention, and a state corresponding to high attention. The indicator can also be a percentage level of attention, with, for example, 0% signifying no attention and 100% signifying full attention. The indicator can take other forms and / or values.

[0042] Step 203, DetSi, determines an initial threshold based on the aforementioned attention level indicator. This initial threshold is called the memorization initiation threshold. It is used in Step 205, described below. This initial threshold determines whether the level of effort received in Step 205 is greater than a predetermined level, the predetermined level being defined by this threshold.

[0043] In lane-keeping systems, only this first threshold is predetermined. The predetermined threshold depends on the vehicle (size, weight, etc.) and the vehicle speed. For example, this threshold, expressed as steering wheel torque, varies from 1 to 1.2 Nm. Other values ​​are possible. Other units are possible; for example, the level of force applied to the steering wheel can be a function of rack displacement, the force applied to the rack, the angle of rotation of a tension bar located on the steering column, etc.

[0044] In the present invention, the first threshold is a function of the driver's level of fatigue or attention. For example, the lower the level of attention, the higher the first threshold determined. In this example, the level of effort is assumed to be a steering wheel torque. If the level of attention corresponds to a high, medium, or low level of attention, respectively, the first threshold determined is approximately 1 Nm, 1.2 Nm, and 1.4 Nm, respectively. Advantageously, the first threshold determined is expressed in a unit corresponding to the level of effort applied to the steering wheel. In another example, when a medium level of attention is detected, the first threshold is approximately 120% of the first threshold for a high level of attention. When a low level of attention is detected, the first threshold is approximately 140% of the first threshold for a high level of attention.

[0045] Advantageously, a second threshold is determined based on the aforementioned attention level indicator. This second threshold is called the memorization end threshold. It is determined similarly to the first threshold. However, the second threshold is determined such that it is less than or equal to the first threshold. In the example above, if the attention level corresponds to high, medium, and low attention, respectively, the second threshold determined is approximately 0.8 Nm, 1.0 Nm, and 1.2 Nm, respectively. Other values ​​are possible. In another example, the The second threshold for a high level of attention, respectively for a medium and low level of attention, is approximately -20% of the value of the first threshold for a high level of attention, respectively for a medium and low level of attention.

[0046] Advantageously, a third threshold is determined based on the aforementioned attention level indicator. This third threshold is called the lane-keeping system's deactivation or stopping threshold. This third threshold is determined similarly to the first threshold. However, the third threshold is determined in such a way that it is higher than the first threshold. In the example above, if the attention level corresponds to high, medium, and low attention, respectively, the third threshold is approximately 2 Nm, 2.4 Nm, and 2.8 Nm, respectively. Other values ​​are possible. In another example, the third threshold for high, medium, and low attention levels, respectively, is approximately 200% of the first threshold value.

[0047] Step 204, RxCvol, is a step for receiving the level of force applied to the steering wheel. Typically, the force level corresponds to an absolute value of the steering wheel torque expressed in Nm. Advantageously, the force level is obtained after it has undergone filtering techniques to avoid outliers. Other units are possible; for example, the force level applied to the steering wheel can be a function of rack displacement, the force level on the rack, the angle of rotation of a tension bar located on the steering column, etc. In a procedure, the force level can be specified, and in this case, the following tests are adapted accordingly, as is customary for a person skilled in the art.

[0048] The level of effort on the steering wheel can be determined by various systems, such as the LPA system, another ADAS system, an electronic steering assistance device, ...

[0049] Step 205, Cvol>S1, is a test step if the effort level exceeds the first threshold. As long as the test is negative, the procedure does not proceed to step 206. Step 205 is performed regularly, periodically or not, at least every millisecond to every second, preferably around 50 to 200 ms, but other values ​​are possible. When the test is positive, a sequence for memorizing a new lateral position is initiated by proceeding to step 206.

[0050] Step 206, Cvol>S3, is a detection step for when the driver's effort level exceeds a third threshold. This third threshold can be predetermined or determined in step 203. As soon as the effort level exceeds this third threshold, the system proceeds to step 207. Step 207, Stp, is a deactivation step for the lane-keeping system when the effort level exceeds this third threshold. A significant amount of force applied to the steering wheel indicates the driver's intention to take control of the vehicle, for example, to change lanes, and therefore the lane-keeping system must be deactivated.

[0051] Stage 208, Cvol <S2, est une étape de test si le niveau d’effort devient inférieur audit deuxième seuil. Ledit deuxième seuil peut être prédéterminé ou determined in step 203. Between steps 205 and 208, by applying a level of effort above the first threshold, the LPA system allows the driver to modify the vehicle's trajectory. This trajectory modification is slight since the level of effort is below the third threshold. When the level of effort then falls below the second threshold, the system proceeds to step 209.

[0052] Step 209, MemPos, is a step for determining and memorizing the new lateral position. By determining the second threshold based on the level of attention in a manner similar to the determination of the first threshold, the system becomes more coherent and understandable to the driver holding the steering wheel rigidly. Furthermore, the third threshold is also adapted similarly to the determination of the first threshold. In the present invention and in the illustrated example, the relative difference between the first and second thresholds, and between the first and third thresholds, is determined according to the level of attention, thus making the system adaptable to the driver's level of fatigue and attention.

[0053] Advantageously, the determination of said new lateral position is a function of a history of received lateral position values, thus allowing for smoother behavior.

[0054] The present invention is not limited to the embodiments described above by way of example: it extends to other variants.

[0055] For example, the process has been described as a sequence of steps. Some steps can be carried out in parallel or in a different sequence.

[0056] Data is received by device 101. The reception of this data is received regularly, periodically or not, at least every millisecond to every second, preferably around 50 to 200 ms, but other values ​​are possible.

[0057] Data is determined by device 101. These determinations are made regularly, periodically or not, at least every millisecond to every second, preferably around 50 to 200 ms, but other values ​​are possible. These determinations can be performed with all or part of the received data.

[0058] Further details of the tests have been provided. The invention is not limited to the form of these tests, and extends to any other type of test performing the same function (statistical tests, etc.).

Claims

CLAIMS 1. Method for storing a new lateral position of a lane keeping system of an autonomous vehicle, said system being activated, said method being implemented by a processor (103) and comprising the steps of: - Receiving (201) a lateral position, said position being a measurement of a lateral distance relative to a traffic lane in which said vehicle is traveling; - Reception (202), from a monitoring system of a driver of said vehicle, of an attention level indicator; - Determination (203) of a first threshold as a function of said attention level indicator; - Reception (204) of a level of force applied to the steering wheel; - Once the level of effort becomes higher (205) than said first threshold, determination and storage (209) of said new lateral position when the level of effort then becomes lower (208) than a second threshold.

2. Method according to claim 1, in which the determination (209) of said new lateral position is a function of a history of received lateral position values.

3. Method according to one of the preceding claims, in which the method further comprises a step of detecting a level of force greater than a third threshold, and a step of deactivating (207) said lane keeping system when the level of force becomes greater than said third threshold.

4. Method according to any one of the preceding claims, wherein in said second threshold is determined (203) as a function of said attention level indicator.

5. Method according to one of claims 3 to 4, wherein said third threshold is determined (203) as a function of said attention level indicator.

6. Device (101) comprising the lane keeping system, the driver monitoring system, and a memory (102) associated with at least one processor (103) configured to implement the method according to one of the preceding claims.

7. Vehicle comprising the device according to the preceding claim.

8. Computer program comprising instructions which, when the program is executed by the device (101) according to claim 6, cause the latter to implement the method according to one of claims 1 to 5.

Images