Method for controlling the speed of a vehicle based on a target object

Description

Technical field

[0001] The present invention relates to methods and devices for regulating the speed of a vehicle, in particular a motor vehicle, based on a target object selected from a list of objects detected by at least one sensor of the vehicle. Technological background

[0002] To improve road safety, some vehicles are equipped with driver assistance systems or functions, known as ADAS (Advanced Driver Assistance System). To ensure the proper functioning of these driver assistance systems, precise knowledge of the environment around the vehicle is necessary.

[0003] One of these ADAS systems commonly used in vehicles is an adaptive cruise control (ACC). An ACC is an electronic device that increases the comfort and safety of vehicle occupants and other users outside the vehicle, whether driving in urban areas, on roads or on motorways. In addition to the classic cruise control functions, an ACC adapts the vehicle's speed based on the distance separating it from the flow of vehicles in front of it. To achieve this, sensors are installed at the front of the vehicle to monitor the flow of vehicles in front of it.If one of the sensors located at the front of the vehicle detects a target vehicle traveling in front of it at a slower speed in its field of action, the ACC regulator adapts the cruise control then subject to a set speed, and reduces the vehicle's speed to maintain a sufficient safety distance from the target vehicle. If necessary, the ACC regulator can activate a brake command. In the event that the target vehicle changes lane or accelerates, the ACC regulator can increase the vehicle's speed until it reaches the set speed. As a reminder, the ACC regulator is a comfort device; the driver can activate and deactivate it as desired. He also has the option of adjusting the speed and distance setpoint and taking control by pressing the brake or accelerator pedal.

[0004] An ACC regulator is associated with a system for perceiving surrounding objects. The vehicle also includes at least one sensor located on the front of the vehicle. These sensors take measurements corresponding to objects located in front of the vehicle. A computer in the vehicle's object perception system merges these measurements to establish a list L of detected objects. The perception system characterizes each detected object. The characterization of an object consists of several attributes including its position in space, its classification and its state of movement. The ACC regulator then selects one of the objects from the list L of detected objects as the target object from which the ACC regulator adapts the vehicle's speed.

[0005] The object perception system and sensors have imperfections that can degrade the performance of the ACC regulator. For example, the physical location in space of detected objects provided by the sensors is not very reliable. Furthermore, the categorization of detected objects can present uncertainties that can bias the ACC regulator. Indeed, the ACC regulator may not react in the same way depending on whether a detected object is categorized as a truck detected at 100m or a bicycle detected at 50m. In addition, a sensor may also fail to detect vehicles that physically exist (false negatives) or detect phantom vehicles, i.e., vehicles that do not physically exist (false positives).

[0006] These false negative and false positive indicators are essential quantities for judging the performance of an ACC regulator, both for highway and city driving. Indeed, for the first, the higher the false negative ratio, the more insecure the driver feels and sometimes, surprised by the vehicle's non-reaction, may be led to intervene by braking suddenly. For the second, the higher the false positive ratio, the more the vehicle decelerates or brakes on targets that physically do not exist, the driver may become tired of these untimely interventions and may deactivate the ACC regulator for life and inform the general public of the poor performance of the device. For these two indicators, the image can be destructive of value, especially if said performances are in deviation from the state of the art of the market.

[0007] Furthermore, the state of the art is known from documents US2008 / 319670A1 and EP3392730A1.

[0008] The present invention aims to overcome at least one of the aforementioned drawbacks. Summary of the invention

[0009] An object of the present invention is to improve the perception of objects located in front of a vehicle.

[0010] Another object of the present invention is to enrich the characterization of the objects of the list L used for the adaptive regulation of the speed of a vehicle.

[0011] Another object of the present invention is to improve adaptive vehicle cruise control.

[0012] Another object of the present invention is to improve road safety.

[0013] According to a first aspect, the present invention relates to a method for regulating the speed of a vehicle based on a target object selected from a list of objects detected by at least one sensor of the vehicle, said method comprising the following steps for each current object in the list of detected objects: obtaining, from at least one sensor of the vehicle, a first attribute of the current object indicating whether the current object has been detected by said at least one sensor; obtaining a second attribute of the current object indicating a confidence level of said at least one sensor which has detected the current object; assigning a first value to a first indicator associated with the current object if the first attribute indicates that the current object has been detected by said at least one sensor of the vehicle and the second attribute indicates a confidence level greater than a first threshold value; assigning a second value, lower than the first value, to the first indicator associated with the current object if the first attribute indicates that the current object has not been detected by said at least one sensor of the vehicle; obtaining a second indicator, associated with the current object, by accumulating values ​​obtained periodically from the first indicator associated with the current object;maintaining the current object in the list of detected objects if the first indicator, associated with the current object, is equal to the first value and if the second indicator, associated with the current object, is greater than a second threshold value; and deleting the current object from the list of detected objects if the second indicator is less than the second threshold value.

[0014] According to a particular and non-limiting example, the first or second value assigned to the first indicator, associated with the current object, is weighted according to the nature of said at least one sensor which detected the current object, a distance which separates the current object from the vehicle and / or a speed of the vehicle.

[0015] According to a particular and non-limiting example, a value of the first indicator, associated with the current object, is weighted according to a lateral distance variance attribute of the object relative to the vehicle.

[0016] According to a particular and non-limiting example, the second indicator, associated with the current object, is obtained by a weighted sum of values ​​obtained periodically from the first indicator associated with the current object.

[0017] According to a particular and non-limiting example, the second indicator, associated with the current object, is obtained by a weighted sum of values ​​obtained periodically from the first indicator associated with the current object, if a sensor which detected the current object is a camera.

[0018] According to a particular and non-limiting example, each weighting of said weighted sum depends on a value assigned to the first indicator and / or a number of sensors having detected the current object and / or a speed of the vehicle.

[0019] According to a second aspect, the present invention relates to a device for regulating the speed of a vehicle based on a target object selected from a list of objects detected by at least one sensor of the vehicle, the device comprising a memory associated with a processor configured to implement the steps of the method according to the first aspect of the invention.

[0020] According to a third aspect, the present invention relates to a vehicle, for example of the automobile type, comprising a device as described above according to the second aspect of the invention.

[0021] According to a fourth aspect, the present invention relates to a computer program which comprises instructions adapted for executing the steps of the method according to the first aspect of the invention, in particular when the computer program is executed by at least one processor.

[0022] Such a computer program may use any programming language, and may be in the form of source code, object code, or intermediate code between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0023] According to a fifth aspect, the invention relates to a computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the method according to the first aspect of the present invention.

[0024] On the one hand, the recording medium can be any entity or device capable of storing the program. For example, the medium may include a storage medium, such as a ROM memory, a CD-ROM or a microelectronic circuit type ROM memory, or a magnetic recording medium or a hard disk.

[0025] Furthermore, this recording medium may also be a transmissible medium such as an electrical or optical signal, such a signal being able to be conveyed via an electrical or optical cable, by conventional or terrestrial radio or by self-directed laser beam or by other means. The computer program according to the invention may in particular be downloaded from a network such as the Internet.

[0026] Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to perform or to be used in performing the method in question. Brief description of the figures

[0027] Other characteristics and advantages of the invention will emerge from the description of the non-limiting exemplary embodiments of the invention below, with reference to figures 1 to 3 annexed, on which: [ Fig. 1] schematically illustrates an example of an environment 1 for implementing the present invention, according to a particular and non-limiting exemplary embodiment of the present invention; [ Fig. 2 ] schematically illustrates a device 2 configured to regulate the speed of a vehicle from a target object selected from a list of objects detected by at least one sensor of the vehicle, according to a particular and non-limiting exemplary embodiment of the present invention; [ Fig. 3 ] illustrates a flowchart of the different steps of a method for regulating the speed of a vehicle based on a target object selected from a list of objects detected by at least one sensor of the vehicle, according to a particular and non-limiting exemplary embodiment of the present invention. Description of examples of implementation

[0028] A method and a device for regulating the speed of a vehicle based on a target object selected from a list of objects detected by at least one sensor of the vehicle will now be described in the following with joint reference to figures 1 to 3 The same elements are identified with the same reference signs throughout the description which follows.

[0029] According to a particular and non-limiting example of embodiment of the invention, a list of objects detected by the object perception system of the vehicle is consolidated by a method comprising the following steps for each current object of the list of detected objects: obtaining, from at least one sensor of the vehicle, a first attribute of the current object indicating whether the current object has been detected by said at least one sensor; obtaining a second attribute of the current object indicating a confidence level of said at least one sensor which has detected the current object; assigning a first value to a first indicator associated with the current object if the first attribute indicates that the current object has been detected by said at least one sensor of the vehicle and the second attribute indicates a confidence level greater than a first threshold value;assigning a second value, lower than the first value, to the first indicator associated with the current object if the first attribute indicates that the current object has not been detected by said at least one sensor of the vehicle; obtaining a second indicator, associated with the object, by accumulating values ​​obtained periodically from said first indicator associated with the current object; maintaining the current object in the list L of detected objects if the first indicator associated with the current object is equal to the first value and if the second indicator associated with the current object is greater than a second threshold value; and deleting the current object from the list of detected objects if the second indicator is less than the second threshold value.;

[0030] The process is implemented by as many sensors as physically exist in the vehicle and which effectively contribute to the ACC regulator.

[0031] The method is advantageous because it allows to significantly reduce false positives in the list of detected objects and a part of false negatives.

[0032] [ Fig. 1 ] schematically illustrates an example of an environment 1 for implementing the present invention, according to a particular and non-limiting exemplary embodiment of the present invention.

[0033] A vehicle (not shown) comprises sensors associated with an object perception system 10 for detecting objects located in front of the vehicle. Some of these objects correspond to candidate target objects but others correspond to phantom objects. The object perception system 10 forms a list L of detected objects by adding a handle of a newly detected object to the list L of detected objects and by removing the handle of an object that must be removed from the list L.

[0034] The sensors may be, for example, millimeter wave radars arranged, in particular, on the front of the vehicle. Each radar is adapted to emit electromagnetic waves and to receive the echoes of these waves returned by one or more objects, in order to detect obstacles and their distances from the vehicle, for example. According to another example, sensors may be one or more LIDAR(s) (from the English "Light Detection And Ranging") and / or one or more cameras (associated or not with a depth sensor) to detect objects in the environment of the vehicle, their distance from the vehicle and possibly their shape or part of their shape (by three-dimensional modeling for example). An object is detected when a position of a point located on this object is obtained by one of these sensors.

[0035] Attributes are associated with each object in the list L of detected objects. For example, each sensor of the object detection system 10 provides an attribute A 1 indicating whether an object has been detected by that sensor, and an attribute A 2 indicating a confidence level NC of that sensor that has detected the object. At least one sensor provides a longitudinal distance attribute Dx that indicates a longitudinal distance of the detected object from the vehicle. The ACC regulator also comprises a trajectory evaluation system 11 that makes it possible to obtain a variance attribute of the lateral distance Dy mentioned above.

[0036] The ACC regulator may also include other systems that allow obtaining other attributes relating to detected objects.

[0037] The ACC regulator also has other systems that allow you to obtain general information about the vehicle such as its speed.

[0038] The vehicle sensors and the object perception system 10 are clocked according to a period, typically 50 ms, to launch new object detections. The list L of detected objects and the attributes associated with these detected objects are then updated periodically.

[0039] The vehicle also comprises a device 2 intended to implement the present invention and described in relation to the figure 2 .

[0040] Device 2 obtains a list L of detected objects and attributes associated with these detected objects from at least one sensor of the vehicle.

[0041] Each object in the list L is processed by a process comprising the following set of operations. This object is called the current object.

[0042] Once all the objects in the list L have been processed according to the present invention, the processed list L (L' on the figure 1) is used by the vehicle's ACC regulator to select a target object from the L' list from which the vehicle's speed will be adapted.

[0043] In a first operation, a first attribute A 1 of the current object is obtained from one or more sensors of the vehicle. The attribute A 1 indicates whether the current object has been detected by the sensor(s).

[0044] In a second operation, a second attribute A 2 of the current object is obtained. The second attribute A 2 indicates a confidence level NC of the sensor(s) that detected the current object.

[0045] In a third operation, a first indicator I 1 is associated with the current object. A first value V 1 is assigned to the first indicator I 1 if the first attribute A 1 indicates that the current object has been detected by one or more sensors of the vehicle and the second attribute A 2 indicates a confidence level NC greater than a first threshold value TH 1 . A second value V 2 , lower than the first value V 1 , is assigned to the first indicator I 1 if the first attribute A 1 indicates that the current object has not been detected by the sensor(s) of the vehicle.

[0046] Typically, the first value V 1 is equal to 1 and the second value V 2 is equal to 0.

[0047] In a fourth operation, a second indicator I 2 is associated with the current object. The second indicator I 2 is obtained by accumulating values ​​obtained periodically from the first indicator I 1 associated with the current object. For example, a value of the first indicator I 1 associated with the current object is obtained every 50 ms.

[0048] In a fifth operation, the current object is maintained in the list L of detected objects if the first indicator I 1 , associated with the current object, is equal to the first value V 1 and if the second indicator I 2 , associated with the current object, is greater than a second threshold value TH 2 . The current object is deleted from the list L of detected objects if the second indicator I 2 is less than the second threshold value TH 2 .

[0049] According to a particular and non-limiting embodiment, the first or second value assigned to the first indicator I 1 , associated with the current object, is weighted according to the nature of the sensor(s) which has (have) detected the current object, a distance Dx which separates the current object from the vehicle and / or a speed v of the vehicle.

[0050] This embodiment is particularly advantageous at low vehicle speed because it allows ghost objects to be removed from the list L of detected objects.

[0051] According to a particular and non-limiting embodiment, the first or second value assigned to the first indicator I 1 is weighted by a weighting multiplicative factor W 1 : I 1 ′ = I 1 ∗ W 1 with I 1 ′ the weighted value of the first indicator I 1 .

[0052] According to one example, if the first attribute A1 indicates that a sensor that detected the current object is a camera, it is determined that the current object and the vehicle are separated by a distance within a predetermined distance range, and the vehicle speed is within a predetermined speed range, then the weighting multiplication factor W 1 is equal to 1 and the value of the first indicator I 1 remains unchanged. The weighting factor W 1 may take a value less than 1 if the first attribute A 1 indicates that the current object was not detected by a camera, and / or if it is determined that the current object and the vehicle are separated by a distance that is not within the predetermined distance range, and / or if the vehicle speed is not within the predetermined speed range.

[0053] According to a particular and non-limiting embodiment, the first or second assigned value first indicator I 1 , associated with the current object, is weighted according to the lateral distance variance attribute Dy of the object relative to the vehicle.

[0054] According to a particular and non-limiting embodiment, the value assigned to the first indicator I 1 is weighted by a weighting multiplicative factor W 2 which is equal to 1 when the value of the lateral distance variance attribute Dy of the object relative to the vehicle is less than a threshold value and which is equal to a predetermined value less than 1 when the value of this attribute is greater than this threshold value: I 1 ′ = I 1 ∗ W 2 with I 1 ′ the weighted value of the first indicator I 1 .

[0055] This embodiment is particularly advantageous when the vehicle uses winding roads because it allows the value assigned to the first indicator I 1 to be reduced when the lateral distance variance is relatively large. The impact of this first indicator I 1 is less for the estimation of the second indicator I 2 which therefore remains more stable when crossing sections of winding road.

[0056] According to a variant, the value assigned to the first indicator I 1 is weighted by the product of the weighting factors W 1 and W 2 .

[0057] The value assigned to the first indicator I 1 can be weighted by other attributes associated with an object in the list of objects such as attributes relating to the trajectory of the vehicle or a timestamp attribute of the detected objects in the list L of detected objects.

[0058] According to a variant, a current object is deleted from the list L of detected objects as soon as the timestamp of this current object indicates a detection time greater than a threshold value.

[0059] According to a particular and non-limiting embodiment, the second indicator I 2 , associated with a current object from the list L of detected objects, is obtained by a weighted sum of values I 1 n obtained periodically from the first indicator associated with the current object.

[0060] According to a particular and non-limiting embodiment, the value of the second indicator I 2 is weighted by a weighting multiplicative factor W 3 n which depends on each value I 1 n of the first indicator associated with the current object: I 2 = ∑ n I 1 n ∗ W 3 n

[0061] According to a particular and non-limiting embodiment, the weighting factor W 3 n depends on the number of vehicle sensors that detected the current object.

[0062] For example, the weighting factor W 3 n can take a low value, for example 0.1, if no sensor has detected it, that is to say that the object is phantom (in English "seen as virtual"), a slightly higher value, for example 0.3, if only one sensor of the vehicle has detected it (radar or camera), and an even higher value, for example 1, if more than one sensor of the vehicle has detected it.

[0063] This embodiment is advantageous because it makes it possible to anticipate the switching of the first indicator I 1 to the first value V 1 (detection of the object by a vehicle sensor).

[0064] According to a particular and non-limiting embodiment, the weighting factor W 3 n depends on a distance between the vehicle and the current object and / or a vehicle speed.

[0065] For example, the slower the vehicle speed and / or the greater the distance between the vehicle and the current object, the higher the weighting factor W 3 n is close to 0. Conversely, the higher the vehicle speed and / or the shorter the distance between the vehicle and the current object, the higher the weighting factor W 3 n is close to 1.

[0066] Obtaining the second indicator I 2 is thus more or less influenced by the first indicator I 1 depending on the speed of the vehicle and / or the distance separating the vehicle from the current object.

[0067] According to a variant, a second indicator I 2 , associated with a current object, is obtained by a weighted sum of values I 1 n obtained periodically from the first indicator, associated with the current object, if the current object has been detected by a camera.

[0068] The above process is described by modifying a single list L of detected objects. This list L includes elements that correspond to detected objects. Each element relating to a detected object can include an attribute A 1 (first operation), an attribute A 2 (second operation). This element can also include a first indicator I 1 (third operation) and a second indicator I 2 (fourth operation).

[0069] The processed list L is then called list L'. This list L' includes elements that correspond to detected objects. Each element relating to a detected object can include an attribute A 1 (first operation), an attribute A 2 (second operation), a first indicator I 1 (third operation) and a second indicator I 2 (fourth operation).

[0070] In an alternative implementation, the lists L and L' are two separate lists. An element is added to the list L' in the fifth operation whenever the first indicator I 1 , associated with the current object, is equal to the first value V 1 and if the second indicator I 2 , associated with the current object, is greater than a second threshold value TH 2 .

[0071] [ Fig. 2 ] schematically illustrates a device 2 configured to regulate the speed of a vehicle based on a target object selected from a list of objects detected by at least one sensor of the vehicle, according to a particular and non-limiting exemplary embodiment of the present invention.

[0072] Device 2 is embedded in the vehicle.

[0073] Device 2 is for example configured to implement the operations described with regard to the figure 1 and / or steps of the method described with regard to the figure 3Examples of such a device 2 include, but are not limited to, on-board electronic equipment such as a sensor, a vehicle on-board computer, an electronic calculator such as an ECU (“Electronic Control Unit”), a smartphone, a tablet, a laptop. The elements of the device 2, individually or in combination, may be integrated into a single integrated circuit, into several integrated circuits, and / or into discrete components. The device 2 may be implemented in the form of electronic circuits or software (or computer) modules or even a combination of electronic circuits and software modules. According to various particular embodiments, the device 2 is communicatively coupled with other similar devices or systems, for example via a communication bus or through dedicated input / output ports.

[0074] The device 2 comprises one (or more) processor(s) 20 configured to execute instructions for carrying out the steps of the method and / or for executing the instructions of the software(s) embedded in the device 2. The processor 20 may include integrated memory, an input / output interface, and various circuits known to those skilled in the art. The device 2 further comprises at least one memory 21 corresponding for example to a volatile and / or non-volatile memory and / or comprises a memory storage device which may comprise volatile and / or non-volatile memory, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

[0075] The computer code of the embedded software(s) comprising the instructions to be loaded and executed by the processor is for example stored in the first memory 21.

[0076] According to a particular and non-limiting exemplary embodiment, the device 2 comprises a block 22 of interface elements for communicating with external devices, for example a remote server or the “cloud”, embedded sensors such as radar or cameras. A list of detected objects and attributes associated with these detected objects can be exchanged between the device 2 and these external devices. The interface elements of the block 22 comprise one or more of the following interfaces: RF radio frequency interface, for example Bluetooth ® or Wi-Fi ®, LTE (Long-Term Evolution), LTE-Advanced; USB interface (Universal Serial Bus); HDMI interface (High Definition Multimedia Interface); LIN interface (Local Interconnect Network).

[0077] According to another particular and non-limiting exemplary embodiment, the device 2 comprises a communication interface 23 which makes it possible to establish communication with other on-board devices (such as, for example, radars, cameras, an object detection system 10, a trajectory evaluation system 11 or even an ACC regulator) via a communication channel 24. A list of detected objects and attributes associated with these detected objects can be exchanged between the device 2 and these on-board devices. The communication interface 23 corresponds for example to a transmitter configured to transmit and receive information and / or data via the communication channel 24.The communication interface 23 corresponds for example to a wired network of the CAN (Controller Area Network), CAN FD (Controller Area Network Flexible Data-Rate), FlexRay or Ethernet type.

[0078] According to a particular and non-limiting exemplary embodiment, the device 2 can provide carrier output signals, for example of a list of detected objects, to one or more external devices, such as a display screen, one or more speakers and / or other peripherals respectively via output interfaces not shown.

[0079] [ Fig. 3] illustrates a flowchart of the different steps of a method 3 for regulating the speed of a vehicle based on a target object selected from a list of objects detected by at least one sensor of the vehicle, according to a particular and non-limiting exemplary embodiment of the present invention.

[0080] The method is for example implemented by a device 2 on board the vehicle.

[0081] A list L of detected objects and associated attributes are obtained. The attributes associated with these detected objects are obtained from at least one sensor associated with the object perception system 10 of the vehicle.

[0082] Each object in the list L is processed by a following set of steps. This object is called the current object. The processed list is referenced L' on the figure 1 .

[0083] In a first step 30, a first attribute A 1 of the current object is obtained from at least one sensor of the vehicle. The attribute A 1 indicates whether the current object has been detected by said at least one sensor.

[0084] In a second step 31, a second attribute A 2 of the current object is obtained. The second attribute A 2 indicates a confidence level NC of said at least one sensor which detected the current object.

[0085] In a third step 32, a first indicator I 1 is associated with the current object. A first value V 1 is assigned to the first indicator I 1 if the first attribute A 1 indicates that the current object has been detected by at least one sensor of the vehicle and the second attribute A 2 indicates a confidence level NC greater than a first threshold value TH 1 . A second value V 2 , lower than the first value V 1 , is assigned to the first indicator I 1 if the first attribute A 1 indicates that the current object has not been detected by said at least one sensor of the vehicle.

[0086] In a fourth step 33, a second indicator I 2 is associated with the current object. The second indicator I 2 is obtained by accumulating values ​​obtained periodically from the first indicator I 1 associated with the current object.

[0087] In a fifth step 34, the current object is maintained in the list L of detected objects if the first indicator I 1 , associated with the current object, is equal to the first value V 1 and if the second indicator I 2 , associated with the current object, is greater than a second threshold value TH 2 . The current object is deleted from the list L of detected objects if the second indicator I 2 is less than the second threshold value TH 2 .

[0088] According to a variant, the variants and examples of the operations described in relation to the figure 1 apply to the process steps of the figure 3 .

[0089] Of course, the present invention is not limited to the exemplary embodiments described above but extends to a method for regulating the speed of a vehicle based on a target object selected from a list of objects detected by at least one sensor of the vehicle, which would include secondary steps without thereby departing from the scope of the present invention. The same would apply to a device configured for implementing such a method.

[0090] The invention also relates to a vehicle, for example an automobile or more generally a motor vehicle, comprising the device 2 of the figure 2 .

Claims

1. A method for controlling the speed of a vehicle from a target object selected from a list of objects detected by at least one sensor of the vehicle, said method comprising the following steps for each current object of the list of detected objects: - obtaining (30), from at least one sensor of the vehicle, a first attribute (A1) of the current object indicating whether the current object has been detected by said at least one sensor; - obtaining (31) a second attribute (A2) of the current object indicating a level of confidence (NC) of said at least one sensor which has detected the current object; - assigning (32) a first value (V1) to a first indicator (I1) associated with the current object if the first attribute (A1) indicates that the current object has been detected by said at least one sensor of the vehicle and that the second attribute (A2) indicates a level of confidence (NC) greater than a first threshold value (TH1); - assigning (32) a second value (V2), lower than the first value (V1), to the first indicator (I1) associated with the current object if the first attribute (A1) indicates that the current object has not been detected by said at least one sensor of the vehicle; - obtaining (33) a second indicator (I2), associated with the current object, by cumulating values obtained periodically from the first indicator (I1) associated with the current object; - keeping (34) the current object in the list of detected objects if the first indicator (I1), associated with the current object, is equal to the first value (V1) and if the second indicator (I2), associated with the current object, is greater than a second threshold value (TH2); and - deletion (34) of the current object from the list of detected objects if the second indicator (I2) is less than the second threshold value (TH2).

2. Method according to claim 1, wherein the first or second value assigned to the first indicator (I1), associated with the current object, is weighted according to the nature of said at least one sensor that has detected the current object, a distance that separates the current object from the vehicle and / or a speed of the vehicle.

3. Method according to claim 1, wherein the first or second value assigned to the first indicator (I1), associated with the current object, is weighted according to an attribute of lateral distance variance (Dy) of the object by report to the vehicle.

4. Method according to claim 1, wherein the second indicator (I2), associated with the current object, is obtained by a weighted sum of values ( I 1 n ) obtained periodically from the first indicator associated with the current object.

5. Method according to claim 4, wherein the second indicator (I2), associated with the current object, is obtained by a weighted sum of values ( I 1 n ) obtained periodically from the first indicator associated with the current object, if a sensor which has detected the current object is a camera.

6. Method according to claim 4 or 5, wherein each balance of said weighted sum depends on a value assigned to the first indicator and / or on a quantity of sensors having detected the current object and / or on a speed of the vehicle.

7. Computer plan including instructions for implementing the method according to any one of the previous claims, when these instructions are executed by a processor.

8. Computer-readable recording medium on which a computer plan is recorded, comprising instructions for executing the steps of the method according to one of claims 1 to 6.

9. Device (2) for regulating the speed of a vehicle from a target object selected from a list of objects detected by at least one sensor of the vehicle, said device (2) comprising a memory (21) associated with at least one processor (20) configured for implementing the steps of the method according to any one of claims 1 to 6.

10. Vehicle comprising the device (2) according to claim 9.