FR3088758A1 - MANAGEMENT OF THE INSERTION OF A VEHICLE IN FRONT OF ANOTHER VEHICLE - Google Patents

Abstract

The invention relates to a method of processing data from at least one sensor of a vehicle, called ego-vehicle (EV), for managing the longitudinal movement of the ego-vehicle undergoing insertion (INS) of a another vehicle, called target vehicle (VC), in front of the ego-vehicle, the method comprising the steps of: - acquisition by the sensor of the ego-vehicle of data relating to the target vehicle, said data comprising movement data of the target vehicle and information relating to the activation of at least one indicator of said target vehicle; generation of a probability of insertion of the target vehicle as a function of said movement data and of said information; - determination of a quantity relating to the longitudinal movement of the ego-vehicle as a function of the probability indicator.

Description

Description

Title of the invention: Management of the insertion of a vehicle in front of another vehicle

The present invention belongs to the field of autonomous vehicles. It relates in particular to a method for managing a situation where a vehicle, called the target vehicle, fits in front of another vehicle, called the ego-vehicle.

It is particularly advantageous in the case of an autonomous motor vehicle traveling on a separate road.

"Vehicle" means any type of vehicle such as a motor vehicle, a moped, a motorcycle, a warehouse storage robot, etc. The term "autonomous driving" of an "autonomous vehicle" means any process capable of assisting the driving of the vehicle. The method may thus consist of partially or completely directing 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 the International Organization of Automobile Manufacturers.

"Road" means any means of communication involving the physical movement of a vehicle. A national, departmental, local, European, international road, a national, European, international highway, a forest path, a route for autonomous storage warehouse systems, etc. are examples of routes.

The road includes at least one roadway. "Roadway" means any physical means capable of supporting the movement of a vehicle. A highway typically includes two carriageways separated by a central reservation.

The roadway includes at least one lane. “Lane” means any portion of roadway assigned to a vehicle queue. A highway pavement typically has at least two lanes of traffic. An insertion lane on the motorway, a single lane in a tunnel, a one-way traffic lane located in a city, etc. are examples of ways.

A lane can be delimited by markings on the ground, but it can also correspond to a path on the road taken by vehicles traveling on the road. Such a lane can be called a "virtual lane" because this lane is not delimited by physical markings but is generated from past trajectories taken by vehicles traveling on the roadway.

Vehicles are frequently equipped with adaptive cruise control. An adaptive cruise control works by regulating the speed of the eco-vehicle based, among other things, on the speed of a target vehicle preceding the eco-vehicle in its lane. The target vehicle preceding the ego vehicle in its lane is called the initial target vehicle, below.

An adaptive cruise control is also known as ACC, for Adptative Cruise Control in English, the French translation being adaptive cruise control.

Current systems do not handle, or very poorly, the situation mentioned above where the target vehicle is inserted in front of the eco-vehicle. Such a situation of insertion of the target vehicle in front of the eco-vehicle is known under the name of "cut-in" situation in English, for overlay in French.

In this situation, illustrated below with reference to Figure 1, the eco-vehicle uses its adaptive cruise control targeting the initial target vehicle. The target vehicle is then inserted between the ego-vehicle and the initial target vehicle, it is detected by the ego-vehicle sensors in charge of adaptive speed regulation and is taken as the new target for the regulation of adaptive speed.

Current adaptive speed control methods detect the target vehicle entering the ego vehicle very late. The adaptive cruise control function then reacts violently with a significant reduction in the speed of the eco-vehicle, which is not pleasant for the occupants of the eco-vehicle.

The present invention improves the situation.

To this end, a first aspect of the invention relates to a method of processing data from at least one sensor of a vehicle, called an ego-vehicle, for managing the longitudinal movement of the ego-vehicle undergoing an insertion of '' another vehicle, called target vehicle, in front of the ego vehicle, the process comprising the steps of:

- acquisition by the eco-vehicle sensor of data relating to the target vehicle, said data comprising movement data of the target vehicle and information relating to the activation of at least one indicator of said target vehicle;

- generation of a probability of insertion of the target vehicle based on said movement data and said information;

- determination of a quantity relating to the longitudinal movement of the eco-vehicle as a function of the probability.

Thus, the cut-in situation of the target vehicle on the eco-vehicle is optimally anticipated.

On the one hand, the flashing activation information is simple to process in that it does not involve situational analysis (interpretation of a predictable attitude of an object by an artificial intelligence algorithm). It is nevertheless very relevant (clear and appropriate indication of the will of the driver of the target vehicle) and has a very favorable availability rate (percentage of cases where a driver will use his turn signal in such a situation).

On the other hand, such information makes it possible to contextualize movement data, which has the effect of giving a very relevant contextualized probability value.

"In front of the eco-vehicle" means any area upstream of the eco-vehicle in the direction of movement of the eco-vehicle. For example, it can be a predetermined area located in front of the front bumper of the eco-vehicle, an area where the sensor of the eco-vehicle is able to detect an object, etc.

"Longitudinal" means the direction of the vehicle forwards and backwards, as opposed to "lateral" which relates to movements to the right or to the left of the vehicle.

In one embodiment, its magnitude relative to the longitudinal movement of the eco-vehicle is the longitudinal acceleration. In another embodiment, the quantity relating to the longitudinal movement of the eco-vehicle is the longitudinal speed.

In one embodiment, the method further comprises a prior step of determining a trajectory of the ego-vehicle and the generation step comprises the sub-steps of determining a predictable duration before the target vehicle either on the trajectory of the ego-vehicle from movement data and calculation of the probability from the foreseeable duration and information.

In a particular embodiment, the movement data comprise a lateral speed of the target vehicle and in which the foreseeable duration is obtained from said lateral speed and from the trajectory of the ego-vehicle.

Integrating the probability, and therefore the determination of longitudinal acceleration, the foreseeable duration before insertion makes it possible to fine-tune the optimal braking / deceleration to be applied to the ego-vehicle to optimize the comfort compromise for passengers and respect for safety distances.

In one embodiment, the step of determining the longitudinal acceleration comprises the sub-steps of:

o if the probability is greater than a predetermined value, selection of the target vehicle as the target of an adaptive cruise control;

o determination of longitudinal acceleration by adaptive speed regulation.

Thus, the insertion of the target vehicle is anticipated in a simple and effective manner.

In another embodiment, the step of determining the longitudinal acceleration comprises the sub-steps of:

o determination of a target vehicle tracking percentage based on the probability;

o generation of a minimum longitudinal acceleration instruction from an adaptive cruise control targeting the target vehicle;

o weighting the minimum longitudinal acceleration instruction from the percentage of follow-up to determine the longitudinal acceleration.

Here, the insertion of the target vehicle is fine-tuned, with continuous and fine adaptation to the insertion of the target vehicle.

A second aspect of the invention relates to a computer program comprising instructions for implementing the method according to the first aspect of the invention, when these instructions are executed by a processor.

A third aspect of the invention relates to a device for processing data from at least one sensor of a vehicle, called ego-vehicle, for managing the longitudinal movement of the ego vehicle undergoing insertion of another vehicle, called target vehicle, in front of the ego-vehicle, the device comprising:

- the eco-vehicle sensor for the acquisition of data relating to the target vehicle, said data comprising movement data of the target vehicle and information relating to the activation of at least one indicator of said target vehicle;

- at least one processor and one memory configured to perform the operations of:

o generation of a probability of insertion of the target vehicle based on said movement data and said information;

o determination of a quantity relating to the longitudinal movement of the ego-vehicle as a function of the probability.

A fourth aspect of the invention relates to a vehicle comprising the device according to the third aspect of the invention.

The accompanying drawings illustrate the invention:

[Fig. 1] illustrates a context of application of the invention;

[Fig. 2] illustrates a process according to the invention;

[Fig. 3] illustrates a device, according to an embodiment of the invention.

The invention is described below in its non-limiting application, in the case of an autonomous motor vehicle traveling on a motorway comprising two carriageways separated by a central reservation and each comprising two lanes. Other applications such as a bus on a dedicated lane or even a motorcycle on a country road are also possible.

In addition, the invention is described below for the determination of a quantity relating to the longitudinal movement of the eco-vehicle within the framework of the determination of a target for the adaptive cruise control. Other applications of the determination of such a quantity are also conceivable, apart from the adaptive regulation of an ego-vehicle. For example, such a quantity can be determined as one of the target quantities for the autonomous driving of the eco-vehicle.

Figure 1 illustrates a motorway carriageway with two lanes, a left lane L and a right lane R with the same traffic direction (from bottom to top of the figure).

The left channel L comprises an ego-vehicle EV, an initial target vehicle VCI and a target vehicle VC.

In the situation described here in Figure 1, the EV eco-vehicle uses an adaptive cruise control targeting the initial target vehicle VCI. In particular, and although numerous methods of adaptive speed regulation are available, adaptive speed regulation can regulate the movement of the EV eco-vehicle longitudinally by maintaining a constant distance Δ between EV and VCI. The target vehicle VC then comes to be inserted according to an insertion maneuver INS between the EV eco-vehicle and the initial target vehicle VCI.

The method according to the invention, for which an embodiment is described below with reference to FIG. 2, relates to the processing of data from sensor C for managing the longitudinal movement of the EV ego vehicle undergoing the INS insertion of the target vehicle VC.

FIG. 2 illustrates the method, according to an embodiment of the invention.

Information TS relating to the activation of at least one indicator of the target vehicle VC, a lateral speed V_VC of the target vehicle and a positioning P_VC of the target vehicle are data acquired by the sensor C of the EV eco-vehicle.

The eco vehicle sensor C is at least one of the following:

- a radar ;

- a lidar;

- a camera, for example a multifunction video camera, CVM;

- a communication system configured to receive information from at least one other vehicle, an infrastructure, a user terminal, etc. ;

- a laser;

- etc.

The raw data acquired by sensor C is processed and merged when multiple sensors are used.

In step 24, the sensor C acquires a speed V_VCI of the initial target vehicle VCI and a position P_VCI of the initial target vehicle VCI. This data is used in step 26 to determine the trajectory TRAJ, a function of V_VCI and P_VCI. The trajectory TRAJ is the trajectory of the EV ego vehicle based on an adaptive speed regulation targeting the initial target vehicle VCI. Such a determination is conventionally a matter of adaptive speed regulation.

In one embodiment, the speed V_VCI and the position P_VCI used to determine TRAJ are the instantaneous speed / position of VCI (it is approximated that these values are valid in the future). In another embodiment, the speed used to determine TRAJ is calculated by taking into account a history of the speeds of VCI. In other embodiments, methods based for example on neural networks to anticipate the speed and / or position of VCI are used to determine TRAJ.

Once the trajectory TRAJ has been determined, a foreseeable duration Δ_Τ before the target vehicle VC is on the trajectory TRAJ of the ego-vehicle EV is determined in step 22. To do this, a distance D (P_VC <-> TRAJ) between the target vehicle VC and the trajectory TRAJ is calculated.

In one embodiment, the distance D (P_VC <-> TRAJ) is the distance between the position of the vehicle VC and an orthogonal projection of this position on the trajectory TRAJ, or on a central point of the trajectory TRAJ (case where the TRAJ trajectory is a corridor). In another embodiment, the distance D (P_VC <-> TRAJ) is the distance between the position of the vehicle VC and an estimated meeting point projected onto the trajectory TRAJ determined from a method of estimating the position of VC (for example approximation of the projected point if the lateral acceleration of VC increases).

The foreseeable duration is obtained by a formula of the type:

[Math. 1]

D (P_VC θ TRAJ)

In step 28, a probability P of insertion of the target vehicle is determined as a function of the foreseeable duration Δ_Τ and of the information TS. For example, the function from which P is determined is configured so that the values of P are high for large values of Δ_Τ combined with TS information returning an indication of activation of the flashing light. On the contrary, for low values of Δ_Τ combined with TS information returning an absence of indication of activation of the flashing, low P values can be provided.

In step 30, a quantity V_EV relating to the longitudinal movement of the eco-vehicle as a function of the probability indicator is determined. This is typically the longitudinal speed and / or the longitudinal acceleration. V_EV is then typically supplied to the components (powertrain, brakes, etc.) of the vehicle in charge of controlling said quantity relating to the longitudinal movement of the eco-vehicle.

In one embodiment, if the probability is greater than a predetermined value, the target vehicle is selected as the target of an adaptive cruise control to determine the quantity relating to the longitudinal movement by the adaptive cruise control.

In another embodiment, step 30 includes the sub-steps (not shown), of:

o determination of a target vehicle tracking percentage based on the probability; o generation of a minimum longitudinal acceleration instruction from an adaptive cruise control targeting the target vehicle;

o weighting the minimum longitudinal acceleration instruction from the percentage of follow-up to determine the longitudinal acceleration.

Thus, the greater the probability, the more the system will achieve deceleration or braking equivalent to a situation with VC present on the trajectory TRAJ (at a speed and distance corresponding to those of the target vehicle which is likely to come on our trajectory).

The lower the probability, the more the system will react on VC which risks coming on the TRAJ trajectory by a weak and late deceleration.

In one embodiment, calibrable maps defining the level of deceleration and the start of braking as a function of the probability values are used.

FIG. 3 represents an example of device D included in the EV eco-vehicle. This device D can be used as a centralized device responsible for at least certain steps of the method described above with reference to FIG. 2.

This device D can take the form of a box comprising printed circuits, of any type of computer or even of a smartphone.

The device D comprises a random access memory 1 for storing instructions for the implementation by a processor 2 of at least one step of the methods as described above. The device also includes a mass memory 3 for storing data intended to be kept after the implementation of the method.

The device D can also include a digital signal processor (DSP) 4. This DSP 4 receives data to format, demodulate and amplify, in a manner known per se, this data.

The device also comprises an input interface 5 for the reception of the data implemented by methods according to the invention and an output interface 6 for the transmission of the data implemented by the methods.

The present invention is not limited to the embodiments described above by way of examples; it extends to other variants.

Thus, an embodiment has been described above in which the eco-vehicle operated on a motorway comprises two carriageways of two lanes, the carriageways being separated by a central platform. The invention can also be implemented for other types of roads, such as national roads with a single carriageway comprising two lanes, motorways with separate carriageways, each carriageway comprising 6 lanes, etc.

Equations and calculations have also been detailed. The invention is not limited to the form of these equations and calculations, and extends to any type of other mathematically equivalent form [Claim 1] Method for processing data from at least one sensor (C) of a vehicle, called ego-vehicle (EV), for movement management

Claims (1)

Longitudinal claims of the eco-vehicle undergoing insertion (INS) of another vehicle, called target vehicle (VC), in front of the eco-vehicle, the method comprising the steps of: - Acquisition (20) by the sensor of the ego-vehicle of data relating to the target vehicle, said data comprising movement data of the target vehicle and information relating to the activation of at least one indicator of said target vehicle; - generation (28) of a probability of insertion of the target vehicle based on said movement data and said information; - determination (30) of a quantity relating to the longitudinal movement of the eco-vehicle as a function of the probability indicator. [Claim 2] Method according to claim 1, in which the quantity relating to the longitudinal movement of the eco-vehicle is the longitudinal acceleration. [Claim 3] Method according to claim 1, in which the quantity relating to the longitudinal movement of the eco-vehicle is the longitudinal speed. [Claim 4] Method according to one of the preceding claims, further comprising a preliminary step of determining a trajectory of the ego-vehicle, and in which the generation step comprises the sub-steps of: x determination ( 22) of a foreseeable duration before the target vehicle is on the trajectory of the ego-vehicle from the movement data; x calculation (28) of the probability from the foreseeable duration and from the information. [Claim 5] Method according to claim 4, in which the movement data comprise a lateral speed of the target vehicle, a positioning of the target vehicle and in which the foreseeable duration is obtained from said lateral speed, of the positioning of the target vehicle and of the trajectory of the ego-vehicle. [Claim 6] Method according to one of the preceding claims, in which the step of determining the longitudinal acceleration comprises the substeps of: x if the probability is greater than a predetermined value, selection of the target vehicle as the target of an adaptive cruise control; x determination of longitudinal acceleration by adaptive speed regulation. [Claim 7] Method according to one of claims 1 to 5, in which the step of determining the longitudinal acceleration comprises the substeps of: x determination of a target vehicle tracking percentage based on the probability; x generation of a minimum longitudinal acceleration instruction from an adaptive cruise control targeting the target vehicle; x weight the minimum longitudinal acceleration instruction from the follow-up percentage to determine the longitudinal acceleration. [Claim 8] Computer program comprising instructions for implementing the method according to any one of the preceding claims, when these instructions are executed by a processor (2). [Claim 9] Device (D) for processing data from at least one sensor of a vehicle, called ego-vehicle, for managing the longitudinal movement of the ego-vehicle undergoing insertion of another vehicle, called target vehicle, in front of the ego-vehicle, the device comprising: - the ego-vehicle sensor (C) for the acquisition of data relating to the target vehicle, said data comprising movement data of the target vehicle and information relating to the activation of at least one indicator of said target vehicle ; - at least one processor (2) and a memory (1) configured to perform the operations of: x generation of a probability of insertion of the target vehicle based on said movement data and said information; x determination of a quantity relating to the longitudinal movement of the ego-vehicle as a function of the probability. [Claim 10] Vehicle (EV) comprising the device according to claim 9.