Methods of operating an autonomous vehicle

Abstract

The present invention generally relates to a computer-implemented method for operating an autonomous vehicle (100, 102, 104), and in particular to efficient planning of interactions with a service provider (215). The present invention also relates to a corresponding control system (200) and a computer program product.

Description

Technical Field

[0001] The present disclosure generally relates to a computer-implemented method for operating an autonomous vehicle, and more particularly to efficient planning of interactions with service providers. The present disclosure also relates to a corresponding control system and a computer program product. Background Art

[0002] In recent years, there have been tremendous advances in semi-autonomous and fully autonomous operation of vehicles, effectively providing driver assistance and safety features such as adaptive cruise control, pedestrian detection, front and rear collision warnings, lane departure warnings, and general obstacle detection. Such autonomous vehicles typically use multiple sensors that are configured to detect information about the environment surrounding the vehicle. For example, the sensors may implement camera vision and radar or LiDAR technology, and the outputs of the sensors may be combined to form an understanding of the vehicle's environment.

[0003] To ensure that such a vehicle operates in a proper manner, it must, for example, be serviced periodically and / or when a vehicle component indicates that it may be malfunctioning. However, because the autonomous vehicle itself lacks ongoing human interaction, such as for refueling and obtaining assistance with other maintenance issues (such as changing a light bulb or fuse, checking oil level, checking tire pressure, cleaning windows, etc.), in some implementations the autonomous vehicle must ensure that it is properly maintained on its own.

[0004] SE1650341A1 gives an example of such an implementation, in which a method for providing services for an autonomous vehicle is disclosed. Specifically, data is collected from the vehicle and a service demand is determined based on the collected data. If there is a service demand, a query is transmitted to a set of service providers, and an offer is received from at least one service provider in response. The vehicle can then select, for example, the offer that best matches the service demand while ensuring that a predetermined arrival time (for example, for cargo delivery) is fully maintained.

[0005] While the solution given in SE1650341A1 provides improvements in the automatic maintenance of autonomous vehicles, SE1650341A1 is completely silent on how the autonomous vehicle should prioritize its operations to optimize the general operation of the vehicle. Therefore, there seems to be room for further improvements, which also take into account the optimization issues mentioned. Summary of the invention

[0006] According to aspects of the present disclosure, the above-mentioned problems are at least partially alleviated by a computer-implemented method for operating an autonomous vehicle traveling along a predetermined route using a control system, the predetermined route including a predetermined destination and a previously established time of arrival at the destination, the control system including a wireless transceiver and an electronic control unit, wherein the method includes the following steps: using the electronic control unit to identify a service provider arranged within a predetermined distance of the vehicle, the service provider being arranged to provide services to the vehicle to extend the current operation duration (e.g., extended operation of the vehicle); using the wireless transceiver to establish network communications with the service provider; receiving an offer to provide services from the service provider at the electronic control unit; using the electronic control unit to estimate a delay for modifying the route to accept the offer from the service provider; and using the electronic control unit to decide whether to accept the offer based on a combination of the current operation duration, the previously established arrival time, and the estimated delay.

[0007] The present disclosure provides a scheme for matching the "needs" of a vehicle (such as the need for charging, cleaning, a stop or parking, e.g. to avoid arriving at a destination too early, general maintenance or repair, etc.) with offers from service providers, where the service provider is suitable to meet the vehicle's needs. For example, the service provider can be a charging station, a cleaning station, etc. According to the present disclosure, the vehicle can advantageously be arranged to take responsibility for ensuring that it is not in a situation where, for example, the battery is (almost) discharged and the charging station is occupied by other vehicles.

[0008] According to the present disclosure, this is achieved by placing specific emphasis on the step of deciding whether to accept an offer. Generally speaking, the decision is made based on at least the current operation duration (e.g., "how long can the vehicle operate without receiving service"), a previously determined arrival time (e.g., don't arrive too late), and estimated delays if the service is accepted. For example, a transportation task (also defined below as a scheduled operation task) may have a time range defined for when to arrive at the destination. Therefore, if the estimated delay will not postpone the arrival time outside the time range, the offer can be clearly accepted. However, the time range may have been selected to ensure that other delays (such as general traffic delays) are considered. Therefore, the decision must also take these factors into account.

[0009] Thus, in preferred embodiments of the present disclosure, the functionality behind the decision making may include a machine learning component, wherein the machine learning component has been previously trained based on data from a large number of vehicles, such as including historical data related to the operation of these vehicles. In a specific preferred embodiment, the machine learning component may also be trained / targeted to penalize a vehicle for, for example, failing to complete a predetermined operational task within a predetermined time frame. Thus, the machine revenue component preferably targets a balance between short-term service costs (e.g., delays involving charging) and the long-term risk of not accepting the offer.

[0010] An example of a long-term cost involving an electric vehicle might be that the state of charge of the vehicle battery falls below a defined minimum charge level. When the battery reaches such a low state of charge, battery stresses can occur that severely limit the battery life, resulting in the battery having to be replaced prematurely, which generally entails increased costs for the vehicle owner. Another example of a long-term cost involving a sensor might be that if the sensor is not cleaned "in time", it is possible that the sensor can no longer be cleaned to work in a normal manner again, in which case, moreover, the sensor must be replaced, which generally entails increased costs for the vehicle owner.

[0011] For example, failure to complete a predetermined operational task could be not charging the vehicle at an early stage and having to wait an undesirably long time to be able to charge at a later stage. For example, a similar example could be illustrated in relation to vehicle washing, where a fault could be defined as not washing the vehicle when required and thus not being able to continue driving, for example because the sensors were covered with dirt (and therefore not working).

[0012] In the context of the present disclosure, it should be understood that the expressions "service provider" and "service" should be interpreted broadly. That is, in the broadest sense, a service provider may be a function that extends the operating duration of a vehicle and its component(s) and / or cargo.

[0013] In some embodiments, the method according to the present disclosure can be performed on a vehicle, for example, using an electronic control unit (ECU) included in the vehicle. However, in some alternative embodiments, a remote server (e.g., a cloud server) can be used to perform at least a portion of the method, wherein the cloud server is connected to the electronic control unit (ECU) included in the vehicle via a network.

[0014] In an embodiment of the present disclosure, the method further comprises the step of operating the vehicle according to the modified route if the offer is accepted. For example, the vehicle is preferably equipped with a wireless transceiver for providing information to the service provider that the offer is accepted, possibly including an estimated time of arrival at the service provider. According to such an embodiment, for example, the service provider can "reserve a location", such as for charging the vehicle. The information can also be used by the service provider to plan the service of the vehicle.

[0015] If possible, the adjusted arrival time at the destination may be provided to a server remote from the vehicle arrangement. As further described below, the server may be part of a mission control arrangement that may be suitable for coordinating a fleet of multiple autonomous vehicles, such as for planning the handling of the vehicle (and other vehicles) at the destination. Obviously, if the vehicle arrives late, it may be desirable to allow mission control arrangements (e.g., for cargo handling at the destination) to be rescheduled so that the vehicle is handled in the most optimal manner upon arrival at the destination. The server itself may be suitable for performing real-time traffic coordination of the fleet, based at least in part on decisions made with respect to the present disclosure.

[0016] It should be understood that in some embodiments, the server may be allowed to overrule decisions made by an electronic control unit included in the vehicle, meaning that the server, a function implemented on the server, or an operator communicating with the server may deny service to the vehicle. For example, such a decision may be made based on knowledge that is not available on the vehicle, whereas the server may, for example, have access to more available information.

[0017] This is of course advantageous if the decision whether to accept an offer requires consideration of an estimated timeline for the availability of the service (perhaps defining a waiting time for receiving the service). Thus, since waiting times may fluctuate over time, it may be desirable to arrange for the functionality behind the decision, for example taking into account historical data for receiving the service at different service providers. Thus, it may be preferable to balance the time required to receive the service now, compared to the time required to receive the service at a later stage.

[0018] Preferably, the step of deciding whether to accept the offer advantageously includes optimizing the operation duration and / or optimizing the time to arrive at the destination. Likewise, the decision scheme should be consistent with the balance of the present disclosure, i.e., when the overall operation duration of the vehicle is reached. For example, even if the vehicle arrives at the destination late, it may be advantageous to receive service now to extend the operation duration itself. That is, in some embodiments, it may be desirable to allow decisions to depend not only on a single task (departure to the destination), but also on, for example, multiple consecutive tasks. Thus, even if the first task is somewhat delayed due to receiving the service, a group of consecutive tasks may be performed in a better manner overall (compared to not receiving the service at a particular point in time).

[0019] In addition, with respect to coordinating fleets, by applying the solution according to the present disclosure, the long-term operating revenue of the fleet can also be maximized for operational failures and / or latest arrival times. For example, operating revenue can be defined as freight transportation revenue minus operating costs such as energy consumption.

[0020] According to another aspect of the present disclosure, a control system is provided, which is suitable for using the control system to operate an autonomous vehicle traveling along a predetermined route, the predetermined route including a predetermined destination and a previously determined time of arrival at the destination, the control system including a wireless transceiver and an electronic control unit, wherein the control system is suitable for: using the electronic control unit to identify a service provider arranged within a predetermined distance of the vehicle, the service provider being arranged to provide services to the vehicle to extend the current operation duration; using the wireless transceiver to establish network communications with the service provider; receiving an offer from the service provider at the electronic control unit to provide the service; using the electronic control unit to estimate a delay for modifying the route to accept the offer from the service provider; and using the electronic control unit to decide whether to accept the offer based on a combination of the current operation duration, the previously determined arrival time, and the estimated delay. This aspect of the present disclosure provides similar advantages as described above with respect to the previous aspects of the present disclosure.

[0021] In a preferred embodiment of the present disclosure, the control system is provided as an onboard component of a vehicle, typically also including the above-mentioned sensors. The vehicle can be, for example, a bus, a truck, a car or any form of construction equipment or work machine. Because the vehicle can be, for example, one of the construction equipment or work machines, the expression "road" used above should be interpreted broadly, including any dedicated area for vehicle operation. In addition, the vehicle can be at least one of a pure electric vehicle (PEV) and a hybrid electric vehicle (HEV).

[0022] However, it will be appreciated that the control system may be implemented, for example, by a server arranged remotely from the vehicle. Such a server may, for example, form part of a so-called "control tower" which is arranged to operate / control a plurality of different vehicles.

[0023] According to another aspect of the present disclosure, a computer program product is provided, including a non-transitory computer-readable medium on which a computer program means is stored, the computer program means being used to operate a control system, the control system being adapted to use the control system to operate an autonomous vehicle traveling along a predetermined route, the predetermined route including a predetermined destination and a previously determined time of arrival at the destination, the control system including a wireless transceiver and an electronic control unit, wherein the computer program product includes: code for using the electronic control unit to identify a service provider arranged within a predetermined distance of the vehicle, the service provider being arranged to provide services to the vehicle to extend the current operation duration; code for using the wireless transceiver to establish network communications with the service provider; code for receiving an offer from the service provider at the electronic control unit to provide the service; code for using the electronic control unit to estimate a delay for modifying the route to accept an offer from the service provider; and code for using the electronic control unit to decide whether to accept the offer based on a combination of the current operation duration, the previously determined arrival time, and the estimated delay. In addition, this aspect of the present disclosure provides similar advantages as described above with respect to the previous aspects of the present disclosure.

[0024] The software executed by the server to perform operations according to the present disclosure can be stored on a computer-readable medium, which is any type of storage device, including a removable non-volatile random access memory, a hard drive, a floppy disk, a CD-ROM, a DVD-ROM, a USB memory, an SD memory card, or one of similar computer-readable media known in the art.

[0025] Further advantages and advantageous features of the disclosure are disclosed in the following description and in the dependent claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Embodiments of the present disclosure cited as examples are described in more detail below with reference to the accompanying drawings.

[0027] In the attached picture:

[0028] Figure 1A Showing the truck, Figure 1B Showing the bus, Figure 1C A wheel loader is shown in which a control system according to the present disclosure may be housed;

[0029] Figure 2 shows a conceptual control system according to a currently preferred embodiment of the present disclosure;

[0030] Figure 3 providing an illustration of the operation of the control system for directing the vehicle to the service provider; and

[0031] Figure 4 Processing steps for carrying out the method according to the present disclosure are shown. DETAILED DESCRIPTION

[0032] The present disclosure is described more fully below with reference to the accompanying drawings, which illustrate currently preferred embodiments of the present disclosure. However, the present disclosure may be embodied in many different forms and should not be construed as being limited to the embodiments given herein; rather, these embodiments are provided for thoroughness and completeness and to fully convey the scope of the present disclosure to those skilled in the art. Throughout the text, the same reference numerals represent the same elements.

[0033] Referring to the accompanying drawings (specifically Figure 1A ), showing an exemplary vehicle, here shown as a truck 100, in which a control system 200 according to the present disclosure (such as Figure 2 Of course, in Figure 1B The bus 102 shown, Figure 1C In the illustrated wheel loader 104 , automobile, etc., the control system 200 may be implemented in a slightly different manner.

[0034] For example, the vehicle can be one of an electric vehicle or a hybrid vehicle, or a gas, gasoline or diesel vehicle. The vehicle includes an electric motor (for an electric vehicle or a hybrid vehicle) or an engine (such as an internal combustion engine, for a gas, gasoline or diesel vehicle). The vehicle can also be manually operated, including fully manually operated or semi-automatically operated.

[0035] Figure 2 A conceptual and exemplary embodiment of a control system 200 according to the present disclosure is shown, typically provided as an onboard component of a vehicle 100, 102, 104. The control system 200 includes an electronic control unit (ECU) 202 and a transceiver 204 connected to the ECU 202.

[0036] For reference, ECU 202 may be represented as a general purpose processor, a dedicated processor, a circuit containing a processing component, a group of distributed processing components, a group of distributed computers configured for processing, a field programmable gate array (FPGA), etc. The processor may be or include any number of hardware components for performing data or signal processing or executing computer code stored in a memory. The memory may be one or more devices for storing data and / or computer code for completing or helping to complete the various methods described in this specification. The memory may include volatile memory or non-volatile memory. The memory may include a database component, an object code component, a script component, or any other type of information structure for supporting various activities of this specification. According to an exemplary embodiment, any distributed or local memory device may be used with the system and method of this specification. According to an exemplary embodiment, the memory is communicatively connected to the processor (e.g., via a circuit or any other wired, wireless or network connection) and includes computer code for performing one or more processes described herein.

[0037] The ECU 202 is also provided with an interface, for example, for allowing communication with a first sensor 206 and a second sensor 208 that generate data related to the current operation of the vehicle 100, 102, 104. Such sensors 206, 208 may include anything from a fuel level sensor, a tire pressure sensor, an oil level sensor, etc., and the data generated can be used directly to determine whether service is required (e.g., adjusting tire pressure or oil level). Of course, other sensors are also possible and are within the scope of the present disclosure. In some embodiments, it can be determined whether service is required by comparing the data from each sensor with at least one predetermined threshold. For example, if the tire pressure is below a predetermined threshold, then it may be necessary to increase the pressure of this tire (or replace the tire). Therefore, service is required to perform such an action.

[0038] The ECU 202 may also be connected to another ECU 210 using, for example, a CAN bus (or similar existing or future communication means), wherein the other ECU 210 may in turn be connected to other sensors or itself be adapted to determine whether the vehicle requires service.

[0039] ECU 202 may also communicate using transceiver 204, for example, with a service provider 215 (or multiple service providers) and / or server 202. As described above, server 220 may be a mission control server, for example, managing logistics operations associated with multiple vehicles.

[0040] In some embodiments, server 102 can be viewed as a central "control center" that provides entities such as transportation providers with a means to pass instructions to vehicles 100, 102, 106 for transporting scheduled cargo from a pick-up location (origin) to a destination, which can travel along a route that has been determined by server 220 to a drop-off location (destination).

[0041] The communication between the transceiver 204 and the service provider 215 and / or the server 202 may be by means of a network connection, such as using the Internet. In some embodiments, the transceiver 204 is adapted to allow communication using WLAN, CDMA, GSM, GPRS, 3 / 4 / 5G mobile communications or similar technologies, for example. Other future wireless communication protocols are also possible and are within the scope of the present disclosure.

[0042] As mentioned above, the control system 200 is preferably provided as an onboard component of the vehicle 100, 102, 104. However, the calculations performed in accordance with the present disclosure may alternatively be distributed, for example between the vehicle 100, 102, 104 and a computing means included in the server 220. Thus, the vehicle 100, 102, 104 may be arranged to make decisions independently, or in conjunction with the server 220.

[0043] Further references Figure 3 , while performing an approach according to the present disclosure, for example, the vehicle 100 travels along a first portion 304 of a route 302. The vehicle 100 has identified that, for example, a first sensor 206 comprised by the vehicle 100 has malfunctioned due to undesired dirt at its sensing surface. For example, the sensor 206 may be a camera and the sensor surface may be a lens comprised by the camera. The ECU 202 may have identified that an image acquired by the camera has an undesired quality below a normal quality level, and therefore the lens must be cleaned in order to be able to produce images of normal (expected) image quality again. Therefore, the ECU 202 determines that the vehicle requires service (in this embodiment, the service is a cleaning service).

[0044] As the vehicle 100 travels along the route 302, it maintains a predetermined distance from the service provider 215 and establishes network communication therewith. In some embodiments, the predetermined distance may be implemented as an area 320 surrounding the service provider 215. The vehicle 100 will then receive an offer to provide a service from the service provider 215. The location of the service provider 215 is such that the vehicle 100 must make a detour to the service provider 215, that is, if the service provider 215 is visited to receive the service, the vehicle 100 will be at least slightly delayed. Figure 3 In the embodiment of the present invention, the service provider is a cleaning station suitable for providing the required cleaning service to a specific type of vehicle 100.

[0045] The vehicle 100 must now decide whether to accept the offer from the service provider 215. Figure 3 As shown in the second portion 306 of route 306 , the vehicle 100 must make this decision before detouring to the service provider 215 .

[0046] According to the present disclosure, the decision making is preferably implemented as a machine learning component on the ECU 202. As described above, it is advantageous to tune the machine learning component so that it can balance the need to continue to operate the vehicle 100 while not arriving at the destination too late (or completing the task within a predetermined time frame).

[0047] Generally, the decision is made based on at least the current operation duration (e.g., "how long can the vehicle operate without receiving service"), a previously determined arrival time (e.g., don't arrive too late), and an estimated delay in receiving service.

[0048] Thus, for example, machine learning-based decision making can be implemented so that a decision not to accept a service does not result in an immediate (i.e., at time t i+1 More precisely, it may have longer-term effects. For example, it is foreseeable within the scope of the present disclosure that a decision is made not to provide a service to vehicle 100 even though vehicle 100 relatively needs the service.

[0049] However, when the vehicle 100 is reconsidered for service, the vehicle 100 urgently needs the service but it is not easy to receive the service in a timely manner at this time, for example because another service provider that later appears along the route 302 is blocked by another vehicle. In the context of machine learning, in the long run, this can be achieved by assigning rewards and penalties for delays to faulty operations. According to such an embodiment, historical data related to the service provider 215 and the specific road 302 can be used to train the decision component implemented by machine learning. Of course, it should be understood that rewards (as opposed to penalties) may also be included if the vehicle arrives in time or at least arrives within a predetermined time range. In some embodiments of the present disclosure, it is preferred to train the machine learning component, for example in a "virtual environment" to allow for sufficient testing and / or simulation before application to vehicles and / or fleets.

[0050] Therefore, in accordance with the present disclosure, it is preferred to provide the machine learning component with sufficient training data to learn to balance the short-term service costs with the long-term risks of not receiving the service. In addition, it is preferred to tune the machine learning component so that it can "understand" that from the perspective of the fleet, a particular service is less favorable when there is a risk of hindering subsequent vehicles and / or the risk of the service causing the task progress to be stranded is too great.

[0051] Based on the above, the ECU 202 makes a decision as to whether to accept the offer from the service provider 215 and controls the vehicle 100 to select the detour 308 portion of the route 302. If the offer is not accepted, the ECU 202 controls the vehicle 100 to continue along the third portion 310 of the route 302. Regardless of whether the offer from the service provider 215 is accepted, the vehicle 100 takes the last portion 312 of the route 302 as the intended destination.

[0052] In summary and with further reference Figure 4 , the present disclosure relates to a computer-implemented method for operating an autonomous vehicle 100, 102, 104 along a predetermined route 302 using a control system 200, the predetermined route 302 including a predetermined destination and a previously determined time of arrival at the destination, the control system 200 including a wireless transceiver 204 and an electronic control unit 202, wherein the method includes the following steps: S1, using the electronic control unit 202 to identify a service provider 215 arranged within a predetermined distance of the vehicle 100, 102, 104, the service provider 215 being arranged to provide services to the vehicle 100, 102, 104 to extend a current operation duration; S2, using the wireless transceiver 204 to establish network communications with the service provider 215; S3, receiving at the electronic control unit 202 an offer from the service provider 215 to provide the service; S4, using the electronic control unit 215 to estimate a delay for modifying the route to accept the offer from the service provider 215; and S5, using the electronic control unit 202, deciding whether to accept the offer based on a combination of the current operation duration, the previously determined arrival time, and the estimated delay. Furthermore, the present disclosure relates to a corresponding control system and a computer program product.

[0053] The present disclosure provides a scheme for matching the "needs" of a vehicle 100, 102, 104 (e.g., needing to be charged, cleaned, etc.) with offers from a service provider 215 that is suitable for meeting the vehicle's needs. The service provider 215 may be, for example, a charging station, a cleaning station, a parking spot for the vehicle 100, 102, 104 to stop / park (e.g., to avoid arriving at a destination too early), a station that provides general maintenance or repairs, etc. According to the present disclosure, the vehicle 100, 102, 104 may advantageously be adapted to be responsible for ensuring that it does not stop working, for example, when the battery is (almost) discharged and the charging station is occupied by other vehicles.

[0054] The present disclosure contemplates methods, devices, and program products for implementing various operations on any machine-readable medium. Embodiments of the present disclosure can be implemented using existing computer processors, or by special-purpose computer processors for appropriate systems incorporated for this purpose or other purposes, or by hard-wired systems. Embodiments within the scope of the present disclosure include program products, which include machine-readable media for carrying machine-executable instructions or data structures or storing machine-executable instructions or data structures thereon. Such machine-readable media can be any available media that can be accessed by a general-purpose computer or a special-purpose computer or other machine with a processor.

[0055] As an example, such machine-readable medium can include RAM, ROM, EPROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or can be used to carry or store required program code in the form of machine-executable instructions or data structures, and can be accessed by a general or special-purpose computer or other machine with a processor. When information is transmitted or provided to a machine through a network or other communication connection (hard wiring, wireless or a combination of hard wiring or wireless), the machine appropriately regards the connection as a machine-readable medium. Therefore, any such connection is appropriately referred to as a machine-readable medium. The above combination is also included in the scope of machine-readable media. Machine-executable instructions, for example, include instructions and data that cause a general-purpose computer, a special-purpose computer or a special-purpose processing machine to perform a specific function or a functional group.

[0056] Although the accompanying drawings can show a specific order of method steps, the order of the steps may be different from the order shown. In addition, two or more steps may be performed simultaneously or partially simultaneously. Such variations will depend on the selected software and hardware systems and the designer's choice. All of these variations are encompassed within the scope of the present disclosure. Similarly, software implementation methods can be accomplished by having standard programming techniques with rule-based logic and other logic to complete various connection steps, processing steps, comparison steps, and decision steps.

[0057] Furthermore, although the present disclosure has been described with reference to specific exemplary embodiments, many different alterations, modifications and the like will become apparent to those skilled in the art.

[0058] By studying the drawings, the specification and the appended claims, those skilled in the art can understand and implement variations of the disclosed embodiments when practicing the disclosure claimed for protection. In addition, in the claims, the word "comprising" does not exclude other elements or steps, and the indefinite article "a" or "an" does not exclude a plurality.

Claims

1. A computer-implemented method for operating an autonomous vehicle along a predetermined route (302) using a control system (200), the predetermined route (302) including a predetermined destination and a previously established time of arrival at the destination, the control system (200) comprising a wireless transceiver (204) and an electronic control unit (202), wherein: The method comprises the following steps: - S1: using the electronic control unit (202) to identify a service provider (215) arranged within a predetermined distance from the autonomous vehicle, the service provider (215) being arranged to provide a service to the autonomous vehicle to extend a current operation duration; - S2: using the wireless transceiver (204) to establish network communication with the service provider (215); - S3: receiving, at the electronic control unit (202), an offer from the service provider (215) to provide the service; - S4: using the electronic control unit (202) to estimate a delay for modifying the route to accept the offer from the service provider (215); and - S5: using a machine learning component included with the electronic control unit (202), deciding whether to accept the offer based on a combination of the current operation duration, the previously established arrival time and the estimated delay, wherein the machine learning component has been previously trained based on historical data involving operations of a large number of vehicles.

2. The method according to claim 1, further comprising the steps of: If the offer is accepted, the autonomous vehicle is operated according to the modified route.

3. The method according to claim 2, further comprising the steps of: The wireless transceiver (204) is used to provide information to the service provider (215) that the offer is accepted.

4. The method according to claim 3, wherein: The information provided to the service provider (215) includes an estimated time of arrival at the service provider (215).

5. The method according to claim 2, further comprising the steps of: The wireless transceiver (204) is used to provide an adjusted time of arrival at the destination to a remotely located server.

6. The method according to claim 1, wherein: The step of deciding whether to accept the offer is further based on an estimated timeline for availability of the service.

7. The method according to claim 6, wherein: The estimated schedule of availability of the service defines a waiting time for receiving the service.

8. The method according to claim 7, wherein: The waiting time fluctuates over time.

9. The method according to claim 1, wherein: The step of deciding whether to accept the offer may include optimizing the duration of the operation and / or optimizing the time to reach the destination.

10. The method according to claim 1, wherein: The service provider (215) is at least one of a charging station and a cleaning station for the autonomous driving vehicle.

11. A control system adapted to operate an autonomous vehicle along a predetermined route using a control system, the predetermined route including a predetermined destination and a previously established time of arrival at the destination, the control system comprising a wireless transceiver (204) and an electronic control unit (202), wherein: The control system is suitable for: - using the electronic control unit (202) to identify a service provider (215) arranged within a predetermined distance from the autonomous vehicle, the service provider (215) being arranged to provide a service to the autonomous vehicle to extend the current operation duration; - using the wireless transceiver (204) to establish network communications with the service provider (215); - receiving, at the electronic control unit (202), an offer from the service provider (215) to provide the service; - using the electronic control unit (202) to estimate a delay for modifying the route to accept the offer from the service provider (215); as well as - using a machine learning component included with the electronic control unit (202), deciding whether to accept the offer based on a combination of the current operation duration, the previously established arrival time and the estimated delay, wherein the machine learning component has been previously trained based on historical data involving operations of a large number of vehicles.

12. The control system according to claim 11, wherein: The control system is further adapted to: If the offer is accepted, the autonomous vehicle is operated according to the modified route.

13. The control system according to claim 12, wherein: The control system is further adapted to: The wireless transceiver (204) is used to provide information to the service provider (215) that the offer is accepted.

14. The control system according to claim 13, wherein: The information provided to the service provider (215) includes an estimated time of arrival at the service provider (215).

15. The control system according to claim 11, wherein: The control system is further adapted to: The wireless transceiver (204) is used to provide an adjusted time of arrival at the destination to a remotely located server.

16. The control system according to claim 11, wherein: The decision whether to accept the offer is further based on an estimated timeline for availability of the service.

17. The control system according to claim 16, wherein: The estimated schedule of availability of the service defines a waiting time for receiving the service.

18. The control system according to claim 17, wherein: The waiting time fluctuates over time.

19. The control system according to claim 11, wherein: Deciding whether to accept the offer includes optimizing the duration of the operation and minimizing the time to reach the destination after a previously established time.

20. The control system according to claim 11, wherein: The service provider (215) is at least one of a charging station and a cleaning station for the autonomous driving vehicle.

21. An autonomous driving vehicle comprising a control system according to claim 11.

22. The autonomous driving vehicle of claim 21, wherein: A vehicle is a working machine, bus or truck.

Images