FR3124300A1 - Method and device for determining a waiting area for customer pick-up by a taxi vehicle. - Google Patents

Abstract

The present invention relates to a method and device for determining a waiting area for customer pick-up by a taxi vehicle. The method obtains (10), from at least one on-board device of the taxi vehicle, trip data relating to a trip taken by the taxi vehicle from a customer pick-up waiting area where the vehicle taxi parked before making the trip, to a destination requested by a customer taken care of; determines (20) a customer service waiting area from a learning classification model fed as input with the obtained route data; moves (30) the taxi vehicle to the determined customer pick-up waiting area; and updates (40) the classification model by learning from the path datum obtained. Figure for abstract: Figure 1

Description

Method and device for determining a waiting area for customer pick-up by a taxi vehicle.

The present invention relates to methods and devices for controlling a vehicle, in particular an autonomous vehicle, and more particularly to a method and device for determining a waiting area for customer pick-up by a taxi vehicle. The present invention also relates to a computer program comprising instructions for implementing the method, a recording medium readable by a computer on which is recorded a computer program comprising instructions for the execution of the steps of the method and a vehicle comprising a device for determining a customer pick-up waiting area.

Technology background

A taxi vehicle is a vehicle which is intended to be used as a taxi, that is to say to transport a customer from a place of departure to a place of destination. When waiting for a customer to be picked up, a taxi vehicle is parked in an area called a customer pick-up waiting area. A customer pick-up waiting area can be any location accessible by vehicle.

Some taxi vehicles are said to be autonomous because they are equipped with advanced driver assistance system(s), known as ADAS (Advanced Driver-Assistance System). ADAS systems are classified according to different levels of autonomy of a vehicle. For example, the classification established by the SAE (from the English Society of Automotive Engineers ) is made up of six different levels, which range from driving that requires total driver intervention to 100% automated driving.

• Level 0 requires full supervision of all aspects of driving;
• Level 1 provides driver assistance that allows steering or acceleration and deceleration control;
• Level 2 allows partial automation with one or more driver assistance systems that control steering as well as acceleration and deceleration functions;
• Level 3 allows control of all aspects of dynamic driving, but requires the driver to intervene appropriately when asked to intervene;
• Level 4 allows control of all aspects of dynamic driving, even when the driver does not react appropriately; And
• Level 5 enables human control of all aspects of dynamic driving at all times, in all road conditions.

The ADAS systems most commonly implemented in current vehicles allow lane keeping (LKA, from the English "Lane Keeping Assist"), the triggering of an alert during an involuntary lane change (LDW from the English "Lane Departure Warning"), the triggering of imminent collision alert (FCA for "Forward Collision Assist"). Mention may also be made of assistance systems for maintaining the vehicle in a traffic lane (LPA for "Lane Positioning Assist"), semi-automatic lane change systems (SALC for "Semi Automatic Lane Change"), anti-lock braking assistance systems (ABS from the German "Antoblockiertsystem"), emergency braking assistance systems (AEBC from the English "Advances Emergency Braking"), electronic trajectory correction (ESP for Electronic Stability Program in English) or adaptive cruise control (ACC for “Adaptive Cruise Control”).

Such an autonomous taxi vehicle also comprises a navigation aid device responsible for determining a route between a customer pick-up waiting area where the taxi vehicle is parked awaiting a new pick-up, and a a customer's pick-up location, and a journey between the customer's pick-up location and a destination location that has been requested by the customer. The place where the customer is picked up and the place of destination can be provided by a device dismounted from the taxi vehicle such as an application installed on a mobile device such as a smart phone (“smartphone”). When the taxi vehicle does not receive an order to go to a customer pick-up point or when it has just finished a trip, it joins a customer pick-up waiting area that is particularly conducive to new pick-up points such as a train station, airport or taxi rank. The wait in these areas can be extremely long, sometimes several hours, which can affect the profitability of this commercial activity. In addition, a customer pick-up waiting area may be far from the pick-up location for a new customer. The cost of taking care of this customer and the waiting time for this customer before being taken care of can sometimes prove to be extremely long, particularly when traffic conditions are not favorable for the taxi vehicle to reach this Place of support. The taxi driver can thus lose trips for these reasons.

The object of the present invention is in particular to respond to the aforementioned drawbacks.

An object of the present invention is to adaptively determine a customer pick-up waiting area by a taxi vehicle.

Another object of the present invention is to rationalize the costs and waiting times of customer pick-up by a taxi vehicle.

According to a first aspect, the present invention relates to a method for determining a waiting area for customer pick-up by a taxi vehicle, said method being implemented by at least one processor. The method comprises a step of obtaining, from at least one on-board device of the taxi vehicle, trip data relating to a trip made by the taxi vehicle from a pick-up waiting area customer where the taxi vehicle was parked before making the trip, to a destination requested by a customer being picked up; a step of determining a customer service waiting area from a learning classification model supplied as input by the path datum obtained; a step of moving the taxi vehicle to the determined customer pick-up waiting area; and a step of updating the classification model by learning from the path datum obtained.

According to a specific and non-limiting embodiment, the method further comprises a step of storing at least one path datum for a period of time, and the classification model is updated from said at least one path datum stored during said period of time.

According to a particular and non-limiting embodiment, the classification model is a neural network stored in a memory or a database of the taxi vehicle, and the steps for determining a customer pick-up waiting area and updating the classification model are implemented by at least one computer of the taxi vehicle.

According to a particular and non-limiting embodiment, the classification model is a neural network stored in a memory or a database of a device dismounted from the taxi vehicle, the taxi vehicle sends at least one trip datum to the device dismounted, the dismounted device implements the steps of determining a customer service waiting area and updating the classification model and sends, to the taxi vehicle, information representative of a zone wait time determined from the classification model.

According to a particular and non-limiting example of embodiment, the journey datum relating to a journey made represents one of the following pieces of information or any combination of at least two following pieces of information:
- information representative of traffic conditions along the route taken;
- information representation of a date of the journey made;
- information representative of a departure time of the journey made;
- information representative of an arrival time of the journey made;
- information representative of a pick-up address of the customer taken care of;
- information representative of an address of the place of destination requested by the customer supported;
- information representative of an identity of the customer supported.

According to a particular and non-limiting example of embodiment, at least one command is sent to at least one on-board computer of the taxi vehicle so that the taxi vehicle moves to the determined customer pick-up waiting area, said at least at least one computer providing one or more functions including advanced driving assistance management and/or assisted navigation.

According to a second aspect, the present invention relates to a device for determining a waiting zone for customer pick-up by a taxi vehicle, the device comprising a memory associated with a processor configured for the implementation of the steps of the method according to the first aspect of the present invention.

According to a third aspect, the present invention relates to a vehicle, in particular autonomous, for example of the automobile type, comprising a device according to the second aspect of the present invention.

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

Such a computer program can use any programming language, and 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.

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

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

On the other hand, this recording medium can 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 hertzian radio or by self-directed laser beam or by other ways. The computer program according to the present invention can in particular be downloaded from an Internet-type network.

Alternatively, the recording medium may be an integrated circuit in which the computer program is incorporated, the integrated circuit being adapted to execute or to be used in the execution of the method in question.

Brief description of figures

Other characteristics and advantages of the present invention will emerge from the description of the non-limiting embodiments of the present invention below, with reference to the appended figures 1 to 3, in which:

illustrates a flowchart of the different steps of a method for determining a waiting area for customer pick-up by a taxi vehicle, according to a particular and non-limiting embodiment of the present invention;

schematically illustrates a short-term and long-term memory cell according to a particular and non-limiting embodiment of the present invention; And

schematically illustrates a device for determining a waiting area for customer pick-up by a taxi vehicle according to a particular and non-limiting embodiment of the present invention.

Description of the examples of realization

A method and a device for determining a waiting zone for customer pick-up by a taxi vehicle will now be described in the following with reference in conjunction to FIGS. 1 to 3. The same elements are identified with the same signs of reference throughout the following description.

The present invention relates to a method for determining a waiting area for customer pick-up by a taxi vehicle. A datum called path datum is obtained. The trip datum relates to a trip made by the taxi vehicle from a customer pick-up waiting area where the taxi vehicle was parked before making the trip, to a destination location requested by a customer supported. The route datum therefore relates to the route taken by the taxi vehicle to go from the pick-up waiting area where it was parked to a customer pick-up location and the route taken between this pick-up location of the customer and the place of destination requested by the customer. A new care waiting area is then determined from a learning classification model fed as input by the journey data obtained. The taxi vehicle moves to this new determined pick-up waiting area, and the learning classification model is updated from the journey data obtained.

The present invention makes it possible to adapt the waiting area for picking up a taxi vehicle according to the journeys that this vehicle has made. This adaptation is implemented by a learning classification model which takes journey data as input which may reflect the habits of regular customers, their usual journeys, time slots where these journeys are usually made, addresses of places frequent client pick-up and/or destination. The learning classification model is updated as trips are made by the taxi vehicle and it determines an optimal customer pick-up waiting area in the sense that a pick-up waiting area customer pick-up is determined to minimize the costs of future pick-up trips and to limit the waiting times for these future pick-ups. The management of the taxi vehicle or of a fleet of taxi vehicles is then rationalized both economically and environmentally by moving the taxi vehicle to these optimal customer pick-up waiting areas and by parking this taxi vehicle in these areas. waiting for new customer support.

illustrates a flowchart of the different steps of a method for determining a customer pick-up waiting area by a taxi vehicle, according to a particular and non-limiting embodiment of the present invention;

In a step 10, a path datum is obtained from at least one device on board the taxi vehicle. The journey data relates to a trip made by the taxi vehicle from a customer pick-up waiting area where the taxi vehicle was parked before making the trip, to a destination requested by a customer picked up charge.

According to a particular and non-limiting example of embodiment, the path datum relating to a journey made represents one of the following pieces of information or any combination of at least two of the following pieces of information: a piece of information representative of traffic conditions along the route taken; an information representative of a date of the journey made; an information representative of a departure time of the journey made, information representative of an arrival time of the journey made; an information representative of a customer support address; an information representative of an address of the place of destination requested by the customer supported; an information representative of a supported client identity.

This list of information is not exhaustive.

A journey data can then be represented by a sequence S of at least two pieces of information which can be expressed, for example, by:

This example of sequence S reflects what a sequence could be when all the information is used to update the classification model. This example is not limiting and any other combination of information can be used to form another example sequence S.

According to a particular and non-limiting example of embodiment, traffic conditions along the route taken are obtained from a device dismounted from the taxi vehicle and communicating with a device on board the taxi vehicle via a communication network.

According to a particular and non-limiting embodiment, a date of a trip taken, a departure time of a trip taken and an arrival time of a trip taken are obtained from a calendar and a clock set implemented by at least one on-board computer of the taxi vehicle.

According to a particular and non-limiting exemplary embodiment, a support address of a supported customer and/or an address of a destination location requested by a supported customer are obtained from a on-board navigation of the taxi vehicle.

According to a particular and non-limiting example of embodiment, at least one item of information from the information sequence representing a path datum is obtained by computer input from a graphical part of a user interface such as a touch screen or a keyboard. Said user interface is part of a program implemented by at least one processor of the taxi vehicle or of a mobile device in communication with an on-board device of the taxi vehicle.

According to a particular and non-limiting example of embodiment, at least one item of information from the information sequence representing a path datum is obtained from a software application installed on a mobile device in communication with an on-board device of the taxi vehicle.

The mobile device can be, for example, a portable computer, a tablet or a telephone, for example of the smart type (“smartphone”).

In a step 20, a customer service waiting zone, called ZPEC zone, is determined from a classification model by learning supplied as input by the path datum obtained.

For example, a ZPEC zone can indicate a public or private place or a district of a city or a remarkable natural site. The classification model can provide a ZPEC zone according to traffic conditions along journeys made, for time slots during which journeys were made, according to dates of journeys made, according to addresses of customer pick-up locations and/or locations of destinations and/or according to supported customer identities.

According to a variant, the learning classification model is supplied as input by the journey datum obtained and by information representative of a location of at least one electric vehicle charging station.

According to a particular and non-limiting example of embodiment, information representative of a location of at least one electric vehicle charging station is obtained from a device dismounted from the taxi vehicle and communicating with an on-board device of the taxi vehicle via a communications network.

According to a particular and non-limiting example of embodiment, information representative of a location of at least one electric vehicle charging station is obtained from an on-board device of the taxi vehicle such as a navigation system using a map.

In a step 30, the taxi vehicle moves to the determined ZPEC zone.

For example, a ZPEC zone, obtained at the output of the classification model, is represented by information representative of geographic coordinates obtained by a GPS-type satellite positioning system (from the English "Global Positioning System", in French global positioning system ).

According to a particular and non-limiting embodiment, when a ZPEC zone is determined in step 20, the information representative of a ZPEC zone feeds a navigation system which then determines the geographical coordinates of the ZPEC zone. The geographical coordinates obtained are then brought to the attention of the driver of the taxi vehicle, who then moves the taxi vehicle to the determined ZPEC zone.

According to a particular and non-limiting example of embodiment, when a ZPEC zone is determined in step 20, at least one command can be sent to at least one on-board computer of the taxi vehicle so that the taxi vehicle moves up to the ZPEC zone, said at least one computer ensuring one or more functions such as for example the management of advanced driving assistance (ADAS system) possibly combined with assisted navigation (navigation assistance system).

In a step 40, the learning classification model is updated from the path datum obtained.

According to a variant, the learning classification model is updated from the journey datum obtained and, optionally, from information representative of a location of at least one electric vehicle charging station.

According to a particular and non-limiting embodiment, the learning classification model is a neural network.

According to a particular and non-limiting embodiment, the neural network is of the LSTM (Long Short Term Memory) type ( Sepp Hochreiter and Jürgen Schmidhuber, Long short-term memory". Neural Computation. 9 (8): 1735 1780.doi :10.1162/neco.1997.9.8.1735.PMID 9377276 ).

An LSTM type neural network is made up of interconnected cells (neurons) interacting non-linearly. The output of a cell is a nonlinear combination of its inputs. The LSTM type neural network according to the present invention is provided for determining a ZPEC zone.

schematically illustrates a short-term and long-term memory cell according to a particular and non-limiting embodiment of the present invention.

The idea associated with a short-term and long-term memory neural network is that each cell is linked to two internal states; one says hidden state ( ) and the other says cell state ( ) which plays the role of memory. The transition from an entry state from a cell at a time instant (t-1) to an output state at a following time instant t is done by transfer with constant gain and equal to 1. In this way the errors are propagated to the previous steps (up to 1000 steps in the past) without phenomenon of disappearance of gradient. The state of the cell can be modified through a gate that authorizes or blocks the update (input gate ). Similarly, a gate controls whether the cell state is communicated at the cell output (output gate ). Cells can also use a gate to reset the state of the cell (forget gate ).

According to an example, considering the following initial values: And , and considering an activation function of these sigmoid-like cells and hyperbolic tangent , the states of the reset, output and update gates as well as the hidden, cell and output states are given by:

where o is an operator symbolizing the Hadamard matrix product (term to term product) and , , , are weights (parameters) and are offset values (parameters).

Alternatively, other functions may be used.

According to a particular and non-limiting embodiment, the neural network is a “sequence-to-sequence” type network: the input of this neural network is fed by a sequence S representative of a journey datum , and, optionally, by information representative of a location of at least one electric vehicle charging station.

Furthermore, the output of this neural network is a sequence of at least one piece of information relating to a ZPEC zone determined by the neural network as a function of the input sequence S. The classification model can output a single piece of information relating to the ZPEC zone. It can also provide a sequence of information, each piece of information relating to the ZPEC zone. The ZPEC zone selected in step 20 may be the one that is closest in distance to the taxi vehicle.

During step 40 (learning phase), the neural network learns to determine a ZPEC zone by being updated from input sequences S representative of path data , and, optionally, information representative of locations of electric vehicle charging stations.

Thus, as the neural network is updated from new input sequences S, the determination of the ZPEC zone is refined so as to determine an optimal ZPEC zone in the sense that this zone minimizes the costs of future pick-up journeys and limits waiting times for future pick-ups depending on traffic conditions along journeys made, time slots during which journeys were made, dates of journeys made, addresses of customer pick-up locations and/or locations of destinations and/or identities of picked-up customers.

Furthermore, when information representative of a location of at least one electric vehicle charging station is also taken into account when updating the neural network, the determination of the ZPEC zone is refined in such a way to take into account the energy resources of the taxi vehicle and its possibility of being able to reach the determined ZPEC zone.

A classic neural network learning algorithm is used for learning. The principle of this learning algorithm is that the neural network learns the values of the parameters (weights) of the cells by backpropagation of the error gradient, i.e. the algorithm gradually calculates the values of the parameters of so as to minimize a cost function C for each of the short-term and long-term memory cells starting from the outputs of the neural network.

According to a particular and non-limiting example of embodiment, the cost function C is a weighted linear combination of an evaluation function F1 of a financial cost of taking care of a customer located in a place of care at starting from a current position of the taxi vehicle, and from an evaluation function F2 of the time to go from the current position of the taxi vehicle to the place where the customer is picked up.

with a and b weighting coefficients determined to give a relative importance to the functions F1 and F2 in the evaluation of the cost function C. For example, a=b=0.5.

According to a particular and non-limiting example of embodiment, the cost function C is given by:

With c a weighting coefficient which can be a function of the current available resources of the taxi vehicle and F3 a proximity evaluation function of an electric vehicle charging station.

This cost function can be minimized using a classical gradient descent algorithm such as the ADAM supervised gradient descent algorithm ( Kingma & Ba (2015) Adam: A Method for Stochastic Optimization. Proceedings of the International Conference for Learning Representations , San Diego (ICLR) ).

During step 20 (inference phase), the neural network is identical to the neural network in the learning phase (step 40) and the input of the neural network is fed by a sequence S representative of a data obtained in step 10, and possibly information representative of a location of at least one electric vehicle charging station.

The neural network is then capable of determining a ZPEC zone as a function of a sequence S (and possibly information representative of a location of at least one electric vehicle charging station) as input even if this sequence (or this information representative of a location of at least one electric vehicle charging station) was not used during training of the neural network.

According to a variant, the LSTM-type neural network comprises a single cell and only uses bounding box coordinates as input.

As a variant, the LSTM-type neural network comprises several cells.

According to a particular and non-limiting example of embodiment, in a step 50, the path datum is stored for a period of time and the classification model is updated (step 40) at the end of said period of time.

According to a particular and non-limiting embodiment, the neural network is stored in a memory or a database of the taxi vehicle and steps 20 and 40 are implemented by at least one computer of the taxi vehicle.

According to a particular and non-limiting embodiment, the neural network is stored in a memory or a database of a device dismounted from the taxi vehicle, the taxi vehicle transmits at least one trip datum intended for the device disembarked from the taxi vehicle, said dismounted device implements steps 20 and 40 and transmits, intended for the taxi vehicle, information representative of a ZPEC pick-up waiting area determined from a classification model.

This exemplary embodiment is advantageous because it makes it possible to pool the journey data obtained following journeys made by a fleet of taxi vehicles, and to use this pooled journey data to update a single neural network accessible by all of the fleet vehicles. The neural network then learns more quickly because it is confronted with a larger number of trip data compared to the number of trip data obtained by a single taxi vehicle. The ZPEC zone determination is also improved because the determination of these zones is all the more optimal as the learning of the neural network is done on a large number of variations of the path data.

schematically illustrates a device for determining a waiting area for customer pick-up by a taxi vehicle according to a particular and non-limiting embodiment of the present invention.

The device 6 corresponds for example to a device on board the taxi vehicle, for example a computer.

The device 6 is for example configured for the implementation of at least one of the steps of the method described with regard to the . Examples of such a device 6 include, but are not limited to, on-board electronic equipment such as a vehicle's on-board computer, an electronic computer such as an ECU (“Electronic Control Unit”). The elements of device 6, individually or in combination, can be integrated in a single integrated circuit, in several integrated circuits, and/or in discrete components. The device 6 can be made in the form of electronic circuits or software (or computer) modules or else a combination of electronic circuits and software modules.

Device 6 comprises one (or more) processor(s) 60 configured to execute instructions for carrying out at least one of the steps of the method and/or for executing the instructions of the software or software embedded in device 6. Processor 60 may include onboard memory, an input/output interface, and various circuits known to those skilled in the art. The device 6 further comprises at least one memory 61 corresponding for example to a volatile and/or non-volatile memory and/or a database and/or comprises a memory storage device which can comprise volatile and/or non-volatile memory volatile, such as EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash, magnetic or optical disk.

According to a particular and non-limiting embodiment, the memory 61 can memorize at least one path datum obtained over a period of time.

According to a particular and non-limiting embodiment, the memory 61 stores a network of neurons.

The computer code of the on-board software or software comprising the instructions to be loaded and executed by the processor is for example stored on the memory 61.

According to different particular and non-limiting examples of embodiment, the device 6 is coupled in communication with other similar devices or systems and/or with communication devices, for example a TCU (from the English “Telematic Control Unit” or in French "Telematic Control Unit"), for example via a communication bus or through dedicated input/output ports.

According to a particular and non-limiting example of embodiment, the device 6 is in communication with a device dismounted from the tax vehicle via a communication network for exchanging data such as data relating to road traffic conditions, trip data, information representative of customer care waiting areas.

According to a particular and non-limiting example of embodiment, the device 6 comprises a block 62 of interface elements for communicating with external devices, for example with the device dismounted from the taxi vehicle, other nodes of the ad hoc network. Block 62 interface elements include one or more of the following interfaces:

- RF radio frequency interface, for example of the Wi-Fi® type (according to IEEE 802.11), for example in the 2.4 or 5 GHz frequency bands, or of the Bluetooth® type (according to IEEE 802.15.1), in the band frequency at 2.4 GHz, or of the Sigfox type using UBN radio technology (Ultra Narrow Band, in French ultra narrow band), or LoRa in the 868 MHz frequency band, LTE (from English " Long-Term Evolution” or in French “Evolution à long terme”), LTE-Advanced (or in French LTE-advanced);

- USB interface (from the English "Universal Serial Bus" or "Universal Serial Bus" in French);

- HDMI interface (from the English “High Definition Multimedia Interface”, or “Interface Multimedia Haute Definition” in French);

- LIN interface (from English “Local Interconnect Network”, or in French “Réseau interconnecté local”).

Data is for example loaded to the device 6 via the block 62 interface using a Wi-Fi® network such as according to IEEE 802.11, an ITS G5 network based on IEEE 802.11p or a mobile network such as a 4G network (or 5G) based on the LTE (Long Term Evolution) standard defined by the 3GPP consortium, in particular an LTE-V2X network.

According to another particular and non-limiting example of embodiment, the device 6 comprises a communication interface 63 which makes it possible to establish communication with other devices (such as other computers of the on-board system) via a communication channel 64. The communication interface 63 corresponds for example to a transmitter configured to transmit and receive information and/or data via the communication channel 64. The communication interface 63 corresponds for example to a CAN-type wired network (of the 'English "Controller Area Network" or in French "Réseau de Contrôleurs"), CAN FD (from English "Controller Area Network Flexible Data-Rate" or in French "Réseau de Contrôleurs à Flow de Data Flexible"), FlexRay ( standardized by ISO 17458) or Ethernet (standardized by ISO/IEC 802-3).

According to a particular and non-limiting example of embodiment, the device 6 can supply output signals to one or more external devices, such as a display screen 65, touch-sensitive or not, one or more loudspeakers 66 and/or other peripherals 67 (projection system) via output interfaces 68 respectively,69 and 70. According to a variant, one or the other of the external devices is integrated into the device 6.

Of course, the present invention is not limited to the exemplary embodiments described above but extends to methods which use a classification model other than LSTM type neural networks, such as for example the XGBoost models ( Tianqi Chen and Carlos Guestrin. Xgboost. Proceedings of Conference on Knowledge Discovery and Data Mining, Aug URL http://dx.doi.org/10.1145/2939672.2939785.) or GRU (Gated Recurrent Unit), as well as configured devices for the implementation of such methods.

Furthermore, the present invention is not limited to the exemplary embodiments described above but extends to a method for determining a waiting area for customer pick-up by a taxi vehicle which would include secondary steps without depart from the scope of the present invention. The same would apply to a device configured for the implementation of such a method.

The present invention also relates to a vehicle, for example automobile or more generally an autonomous land motor vehicle, comprising the device 6 of the .

Claims (10)

Method for determining a waiting area for customer pick-up by a taxi vehicle, said method being implemented by at least one processor and comprising the following steps:
- obtaining (10), from at least one on-board device of the taxi vehicle, trip data relating to a trip made by the taxi vehicle from a customer pick-up waiting area where the taxi vehicle parked before making the trip, to a destination requested by a customer taken care of;
- determination (20) of a waiting area for customer care from a learning classification model supplied as input by the path datum obtained;
- Displacement (30) of the taxi vehicle to the determined customer pick-up waiting area; And
- updating (40) of the classification model by learning from the path datum obtained. Method according to claim 1, which further comprises a step (50) of storing at least one path datum for a period of time, and the classification model is updated from said at least one path datum stored during said period of time. Method according to claim 1 or 2, in which the classification model is a neural network stored in a memory or a database of the taxi vehicle, and the steps of determining (20) a waiting area for customer loading and updating (40) of the classification model are implemented by at least one computer of the taxi vehicle. Method according to claim 1 or 2, in which the classification model is a neural network stored in a memory or a database of a device dismounted from the taxi vehicle, the taxi vehicle sends at least one trip datum to the device disembarked, the disembarked device implements the steps of determining (20) a customer pick-up waiting area and updating (40) the classification model and sends, to the taxi vehicle, a information representative of a care waiting area determined from the classification model. Method according to one of the preceding claims, in which the journey datum relating to a journey made represents one of the following items of information or any combination of at least two of the following items of information:
- information representative of traffic conditions along the route taken;
- information representation of a date of the journey made;
- information representative of a departure time of the journey made;
- information representative of an arrival time of the journey made;
- information representative of a pick-up address of the customer taken care of;
- information representative of an address of the place of destination requested by the customer supported;
- information representative of an identity of the customer supported. Method according to one of the preceding claims, in which at least one command is sent to at least one on-board computer of the taxi vehicle so that the taxi vehicle moves to the determined customer pick-up waiting area, said at least one computer providing one or more functions including advanced driving assistance management and/or assisted navigation. Computer program comprising instructions for implementing the method according to any one of the preceding claims, when these instructions are executed by a processor. Computer-readable recording medium on which is recorded a computer program comprising instructions for carrying out the steps of the method according to one of Claims 1 to 6. Device for determining a waiting area for customer pick-up by a taxi vehicle, said device comprising a memory associated with at least one processor configured for the implementation of the steps of the method according to any one of claims 1 at 6. Vehicle comprising the device according to claim 9.