Reachability analysis for coordinating autonomous vehicles

Abstract

A method performed by a central computer system (1), the method comprising obtaining state information for each of a plurality of clients (2) comprised in respective structural devices (3), at least one of said devices being an autonomous vehicle (4), including, from the respective client of each of said at least one autonomous vehicle, receiving real-time state information indicating a geographical position of the vehicle. The method also comprises, based on the obtained state information, performing reachability analysis to estimate likely future positions of the devices. The method also comprises, based on the performed reachability analysis, determining that a first one (4a) of the at least one autonomous vehicle, of a first one (2a) of the clients, risks a future conflict at the device of a second one (2b / 2c) of the clients. The method also comprises, initiating direct P2P communication (7) between the first client and the second client.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to coordinating a fleet of autonomous vehicles.BACKGROUND

[0002] There is a general need for coordination of a fleet of autonomous vehicles to prevent collisions and promote smooth operation of the fleet.

[0003] US 2013 / 179382 discloses application of probability theory in a computing unit on board a vehicle for motion control, prediction, and state estimation intended to serve driver assistance systems and autonomous vehicle control systems.SUMMARY

[0004] It is an objective of the present invention to provide improved coordination of a fleet of autonomous vehicles.

[0005] In an aspect of the present invention, there is provided a method performed by a central computer system for coordinating a fleet of autonomous vehicles. The method comprises obtaining state information for each of a plurality of clients comprised in respective structural devices, at least one of said structural devices being an autonomous vehicle. The obtaining state information includes, from the respective client of each of said at least one autonomous vehicle, receiving real-time state information indicating a geographical position of the vehicle. The method also comprises, based on the obtained state information, performing reachability analysis to estimate likely future positions of the devices. The method also comprises, based on the performed reachability analysis, determining that a first one of the at least one autonomous vehicle, of a first one of the clients, risks a future conflict at the device of a second one of the clients. The method also comprises, initiating direct P2P communication between the first client and the second client.

[0006] According to another aspect of the present invention, there is provided a central computer system comprising processing circuitry, and storage storing instructions executable by said processing circuitry whereby the central computer system is operative to perform an embodiment of the method of the present disclosure.

[0007] According to another aspect of the present invention, there is provided a control system comprising an embodiment of the central computer system of the present disclosure, and the plurality of clients.

[0008] According to another aspect of the present invention, there is provided a computer program product comprising computer-executable components for causing a central computer system to perform an embodiment of the method of the present disclosure when the computer-executable components are run on processing circuitry comprised in the central computer system.

[0009] In accordance with the present invention, reachability analysis is performed in a central computer system, rather than in each autonomous vehicle, for determining whether to initiate peer-to-peer (P2P) communication, i.e. direct communication which does not go via the central computer system, between any two of the clients. Thus, improved overall coordination of the fleet is achieved.

[0010] It is to be noted that any feature of any of the aspects may be applied to any other aspect, wherever appropriate. Likewise, any advantage of any of the aspects may apply to any of the other aspects. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following detailed disclosure, from the attached dependent claims as well as from the drawings.

[0011] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a / an / the element, apparatus, component, means, step, etc." are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated. The use of "first", "second" etc. for different features / components of the present disclosure are only intended to distinguish the features / components from other similar features / components and not to impart any order or hierarchy to the features / components.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Embodiments will be described, by way of example, with reference to the accompanying drawings, in which: Fig 1 is a schematic block diagram of a control system in accordance with some embodiments of the present invention. Fig 2 is a schematic block diagram of a central computer system in accordance with some embodiments of the present invention. Fig 3 is a schematic block diagram of a structural device in accordance with some embodiments of the present invention. Fig 4 is a schematic flow chart of a method in accordance with some embodiments of the present invention. DETAILED DESCRIPTION

[0013] Embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments are shown. However, other embodiments in many different forms are possible within the scope of the present disclosure. Rather, the following embodiments are provided by way of example so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Like numbers refer to like elements throughout the description.

[0014] Figure 1 illustrates a control system 10 comprising a central computer system 1, e.g. of a computer cloud 5, and a plurality of clients 2, e.g. in the form of software (SW) applications (i.e. apps). The clients 2 are in communication with the central computer system 1, via respective central communications 6, e.g. by each client 2 sending state information to the central computer system 1 via an uplink of the central communication 6 and by the central computer system 1 sending instructions for setting up P2P communication 7 in the downlink of the central communication 6 in response to said state information, thus initiating the P2P communication 7. P2P communication 7 between any two of the clients 2 may be initiated by the central computer system 1 in response to the obtained state information from the clients 2, e.g. by the central computer system 1 sending instructions in the downlink of the central communication 6 of any one or both of the two clients. 2. In the limited and illustrative example of figure 1, three clients are shown, a first client 2a, a second client 2b and a third client 2c, each with a respective central communication 6a, 6b and 6c between the client and the central computer system 1. A P2P communication 7 may be set up between any two of the clients 2, e.g. a P2P communication 7b between the first client 2a and the second client 2b or a P2P communication 7c between the first client 2a and the third client 2c.

[0015] Each of the clients 2 is provided in a respective structural device 3, typically in a computing device in said structural device 3. At least one of the structural devices 3 is an autonomous vehicle 4. Usually, a plurality of the structural devices 3 are autonomous vehicles. For instance, each of the autonomous vehicles 4 of the fleet of autonomous vehicles may be a structural device 3 comprising a client 2. All of the structural devices 3, which each comprises a client 2, may be autonomous vehicles 4. However, in other embodiments, at least one of the structural devices 3 is not an autonomous vehicle, instead being e.g. one or more of stationary infrastructure, webcam, and / or mobile phone.

[0016] For instance, a client 2 may be comprised in stationary infrastructure 3 at a road. A camera or other sensor of the stationary infrastructure 3 may detect the presence of e.g. a pedestrian, cyclist or other road user, which may not itself have a client 2. The central computer system 1 may determine a risk of an autonomous vehicle 4 getting too close, or even colliding, with said road user and thus initiates a P2P communication 7 between the client 2 of the autonomous vehicle 4 and the client 2 of the stationary infrastructure 3 to facilitate the autonomous vehicle 4 obtaining information from the stationary infrastructure 3 enabling the autonomous vehicle to avoid getting too close to the road user.

[0017] In another example, a pedestrian, cyclist or other road user may carry a mobile phone, typically smartphone, 3 having a client 2 running thereon. The central computer system 1 may determine a risk of an autonomous vehicle 4 getting too close, or even colliding, with said road user and thus initiates a P2P communication 7 between the client 2 of the autonomous vehicle 4 and the client 2 of the mobile phone 3 to facilitate the autonomous vehicle 4 obtaining information from the mobile phone 3 enabling the autonomous vehicle to avoid getting too close to the road user, and / or warning the road user via their mobile phone 3.

[0018] However, envisioned to be the most common situation, both clients 2 may be in respective autonomous vehicles 4 of the fleet of vehicles. The central computer system 1 may determine a risk of the autonomous vehicles 4 getting too close to each other, or even colliding, and thus initiates a P2P communication 7 between the respective clients 2 of the autonomous vehicles 4 to facilitate the autonomous vehicle 4 agreeing how to avoid getting too close to each other.

[0019] Each of the autonomous vehicles 4 may be any type of autonomous vehicle, e.g. any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, typically an autonomous car.

[0020] Figure 2 illustrates a central computer system 1, e.g. for cloud computing and / or edge computing. The central computer system 1 comprises processing circuitry 21 e.g. a central processing unit (CPU). The processing circuitry 21 may comprise one or a plurality of processing units in the form of microprocessor(s). However, other suitable devices with computing capabilities could be comprised in the processing circuitry 21, e.g. an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processing circuitry 21 is configured to run one or several computer program(s) or software (SW) 23 stored in a storage 22 of one or several storage unit(s) e.g. a memory. The storage unit is regarded as a computer readable means, forming a computer program product together with the SW 23 stored thereon as computer-executable components and may e.g. be in the form of a Random Access Memory (RAM), a Flash memory or other solid state memory, or a hard disk, or be a combination thereof. The processing circuitry 21 may also be configured to store data in the storage 22, as needed. The central computer system 1 also comprises a communication interface 24, e.g. for providing the respective central communications 6 with each of the clients 2. As mentioned above, the functionalities of the central computer system 1 may be provided by / in a computer cloud 5.

[0021] Figure 3 illustrates a structural device 3, e.g. an autonomous vehicle 4, comprising a client 2. The structural device 3 comprises processing circuitry 31 e.g. a central processing unit (CPU). The processing circuitry 31 may comprise one or a plurality of processing units in the form of microprocessor(s). However, other suitable devices with computing capabilities could be comprised in the processing circuitry 31, e.g. an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processing circuitry 31 is configured to run one or several computer program(s) or software (SW) 33 stored in a storage 32 of one or several storage unit(s) e.g. a memory. The storage unit is regarded as a computer readable means, forming a computer program product together with the SW 33 stored thereon as computer-executable components and may e.g. be in the form of a Random Access Memory (RAM), a Flash memory or other solid state memory, or a hard disk, or be a combination thereof. The client 2 may run on the processing circuitry 31 as a result of execution of SW 33 stored in the storage 32. The processing circuitry 31 may also be configured to store data in the storage 32, as needed. The structural device 3 also comprises a communication interface 24, e.g. for the central communication 6 with the central computer system 1 and / or for a P2P communication 7 with any other client 2 in the control system 10. Optionally, the structural device 3 may comprise sensor(s) 35 for detecting or monitoring its surroundings, e.g. another road user as mentioned above. Such sensors 35 may e.g. include any of a camera, a radar and / or a lidar.

[0022] Figure 4 illustrates the method of the present invention. The method is for coordinating a fleet of autonomous vehicles 4, where at least one, typically several or all, of the autonomous vehicles of the fleet are structural devices 3 comprising a client 2. The method is performed in / by a central computer system 1, which central computer system 1 forms a control system 10 together with the clients 2.

[0023] The central control system 1 obtains S1 state information for each of a plurality of clients 2 comprised in respective structural devices 3. Typically, the central computer system 1 receives the state information from the client 2, via a communication 6 with the client 2. The state information for a client 2 is typically information about a state of the device 3, e.g. vehicle 4, comprising the client 2. The state information for a vehicle 4 includes information about a geographical position of the vehicle. The state information may be sent periodically or continuously, preferably continuously, for allowing the central computer system to keep track of the vehicle in real-time. The state information may additionally include other information about the vehicle's state. For instance, state information for a vehicle which is a car may include position coordinates (e.g. GPS position), speed and heading, while state information for an aerial drone may include position coordinates, speed and rotation. In accordance with the method, at least one of the structural devices 3 is an autonomous vehicle 4 of the fleet of vehicles. Typically, a plurality of the structural devices 3 are autonomous vehicles 4. From the respective client 2 of each of said at least one autonomous vehicle 4, real-time state information is received, indicating a geographical position of the vehicle.

[0024] Based on the obtained S1 state information, reachability analysis is performed S2 in the central computer system 1 to estimate likely future positions of the devices 3. For any stationary structural device 3, its future position may already inherently be known, but for mobile structural devices 3, such as autonomous vehicles 4 and / or mobile phones, the reachability analysis is needed to estimate likely future positions of the devices 3. The input to the reachability analysis of a device 3 may be any or all of the state information received from the client 2 in the device, e.g. current position, speed and heading of the device 3 / vehicle 4.

[0025] Based on the performed S2 reachability analysis, it is determined S3 whether a first one 4a of the at least one autonomous vehicle 4, including a first one 2a of the clients 2, risks a future spatial conflict, e.g. collision, at the device 3 of a second one 2b or 2c of the clients 2. A potential future conflict may exist if it is determined based on the reachability analysis that two of the devices 3 may get too close to each other, or even collide with each other, within the next seconds or minutes (depending on the temporal horizon of the reachability analysis). Alternatively, a potential future conflict may involve e.g. a road user which is observed by a device 3 but which does not itself include a client 2. The conflict may be a collision, but may alternatively be another type of conflict resulting from the two devices 3 coming too close to each other. For example, two vehicles 4 may be headed towards the same narrow passage. The reachability analysis may then estimate that they will want to pass the narrow passage at the same time. The central computer system 1 may then initiate P2P communication 7 between the two vehicles 4 (typically the clients 2 thereof) to allow them to decide among themselves which of them should go first through the passage. Without the P2P communication 7, they may not necessarily collide with each other but might e.g. come to a full stop and pass inefficiently.

[0026] In case it is determined that there is a risk of a future spatial conflict, P2P communication 7 is initiated S4 between the first client 2a and the second client 2b or 2c. The initiation S4 may include sending instructions, e.g. including credentials, to the first and / or second client 2 to set up the P2P communication 7. By means of the P2P communication 7, the clients may exchange information and decide amongst themselves, e.g. without involving the central computer system 1, how to avoid the conflict.

[0027] In some embodiments of the present invention, the method is performed as cloud computing and / or edge computing by the central computer system 1.

[0028] In some embodiments of the present invention, the real-time state information also includes motion parameters e.g. indicating a velocity and / or heading of the vehicle 4.

[0029] In some embodiments of the present invention, the obtaining S1 of the state information further comprises obtaining information about a future geographical and / or motion goal of the first autonomous vehicle 4a, wherein the reachability analysis is performed S2 also based on said goal information. A motion goal may be a goal for any motion parameter such as a velocity and / or heading of the vehicle 4. With information about a geographical and / or motion goal for the vehicle, the central computer system 1 will have additional information which can be input to the reachability analysis for estimating the future positions of the vehicle 4.

[0030] In some embodiments of the present invention, the first autonomous vehicle (4a) is any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, preferably an autonomous car.

[0031] In some embodiments of the present invention, the risked future conflict is a risked future collision. In some embodiments, the risked future collision is with the device 3b or 3c of the second client 2b or 2c. Alternatively, in some other embodiments, the risked future collision is with a person (e.g. road user) or object observed by sensor(s) 35 of the device 3b or 3c of the second client 2b or 2c.

[0032] In some embodiments of the present invention, the device 3b of the second client 2b is a second autonomous vehicle 4b. In some embodiments, the second autonomous vehicle 4b is any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, preferably an autonomous car.

[0033] In some embodiments of the present invention, the structural devices 3 include, in addition to the at least one autonomous vehicle 4, at least one of: stationary infrastructure, webcam(s), and mobile phone(s).

[0034] The present disclosure has mainly been described above with reference to a few embodiments. However, as is readily appreciated by a person skilled in the art, other embodiments than the ones disclosed above are equally possible within the scope of the present disclosure, as defined by the appended claims.

Examples

Embodiment Construction

[0013]Embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments are shown. However, other embodiments in many different forms are possible within the scope of the present disclosure. Rather, the following embodiments are provided by way of example so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Like numbers refer to like elements throughout the description.

[0014]Figure 1 illustrates a control system 10 comprising a central computer system 1, e.g. of a computer cloud 5, and a plurality of clients 2, e.g. in the form of software (SW) applications (i.e. apps). The clients 2 are in communication with the central computer system 1, via respective central communications 6, e.g. by each client 2 sending state information to the central computer system 1 via an uplink of the central communication 6 and by the central computer system 1...

TECHNICAL FIELD

[0001] The present disclosure relates to coordinating a fleet of autonomous vehicles.BACKGROUND

[0002] There is a general need for coordination of a fleet of autonomous vehicles to prevent collisions and promote smooth operation of the fleet.

[0003] US 2013 / 179382 discloses application of probability theory in a computing unit on board a vehicle for motion control, prediction, and state estimation intended to serve driver assistance systems and autonomous vehicle control systems.SUMMARY

[0004] It is an objective of the present invention to provide improved coordination of a fleet of autonomous vehicles.

[0005] In an aspect of the present invention, there is provided a method performed by a central computer system for coordinating a fleet of autonomous vehicles. The method comprises obtaining state information for each of a plurality of clients comprised in respective structural devices, at least one of said structural devices being an autonomous vehicle. The obtaining state information includes, from the respective client of each of said at least one autonomous vehicle, receiving real-time state information indicating a geographical position of the vehicle. The method also comprises, based on the obtained state information, performing reachability analysis to estimate likely future positions of the devices. The method also comprises, based on the performed reachability analysis, determining that a first one of the at least one autonomous vehicle, of a first one of the clients, risks a future conflict at the device of a second one of the clients. The method also comprises, initiating direct P2P communication between the first client and the second client.

[0006] According to another aspect of the present invention, there is provided a central computer system comprising processing circuitry, and storage storing instructions executable by said processing circuitry whereby the central computer system is operative to perform an embodiment of the method of the present disclosure.

[0007] According to another aspect of the present invention, there is provided a control system comprising an embodiment of the central computer system of the present disclosure, and the plurality of clients.

[0008] According to another aspect of the present invention, there is provided a computer program product comprising computer-executable components for causing a central computer system to perform an embodiment of the method of the present disclosure when the computer-executable components are run on processing circuitry comprised in the central computer system.

[0009] In accordance with the present invention, reachability analysis is performed in a central computer system, rather than in each autonomous vehicle, for determining whether to initiate peer-to-peer (P2P) communication, i.e. direct communication which does not go via the central computer system, between any two of the clients. Thus, improved overall coordination of the fleet is achieved.

[0010] It is to be noted that any feature of any of the aspects may be applied to any other aspect, wherever appropriate. Likewise, any advantage of any of the aspects may apply to any of the other aspects. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following detailed disclosure, from the attached dependent claims as well as from the drawings.

[0011] Generally, all terms used in the claims are to be interpreted according to their ordinary meaning in the technical field, unless explicitly defined otherwise herein. All references to "a / an / the element, apparatus, component, means, step, etc." are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any method disclosed herein do not have to be performed in the exact order disclosed, unless explicitly stated. The use of "first", "second" etc. for different features / components of the present disclosure are only intended to distinguish the features / components from other similar features / components and not to impart any order or hierarchy to the features / components.BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Embodiments will be described, by way of example, with reference to the accompanying drawings, in which: Fig 1 is a schematic block diagram of a control system in accordance with some embodiments of the present invention. Fig 2 is a schematic block diagram of a central computer system in accordance with some embodiments of the present invention. Fig 3 is a schematic block diagram of a structural device in accordance with some embodiments of the present invention. Fig 4 is a schematic flow chart of a method in accordance with some embodiments of the present invention. DETAILED DESCRIPTION

[0013] Embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments are shown. However, other embodiments in many different forms are possible within the scope of the present disclosure. Rather, the following embodiments are provided by way of example so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Like numbers refer to like elements throughout the description.

[0014] Figure 1 illustrates a control system 10 comprising a central computer system 1, e.g. of a computer cloud 5, and a plurality of clients 2, e.g. in the form of software (SW) applications (i.e. apps). The clients 2 are in communication with the central computer system 1, via respective central communications 6, e.g. by each client 2 sending state information to the central computer system 1 via an uplink of the central communication 6 and by the central computer system 1 sending instructions for setting up P2P communication 7 in the downlink of the central communication 6 in response to said state information, thus initiating the P2P communication 7. P2P communication 7 between any two of the clients 2 may be initiated by the central computer system 1 in response to the obtained state information from the clients 2, e.g. by the central computer system 1 sending instructions in the downlink of the central communication 6 of any one or both of the two clients. 2. In the limited and illustrative example of figure 1, three clients are shown, a first client 2a, a second client 2b and a third client 2c, each with a respective central communication 6a, 6b and 6c between the client and the central computer system 1. A P2P communication 7 may be set up between any two of the clients 2, e.g. a P2P communication 7b between the first client 2a and the second client 2b or a P2P communication 7c between the first client 2a and the third client 2c.

[0015] Each of the clients 2 is provided in a respective structural device 3, typically in a computing device in said structural device 3. At least one of the structural devices 3 is an autonomous vehicle 4. Usually, a plurality of the structural devices 3 are autonomous vehicles. For instance, each of the autonomous vehicles 4 of the fleet of autonomous vehicles may be a structural device 3 comprising a client 2. All of the structural devices 3, which each comprises a client 2, may be autonomous vehicles 4. However, in other embodiments, at least one of the structural devices 3 is not an autonomous vehicle, instead being e.g. one or more of stationary infrastructure, webcam, and / or mobile phone.

[0016] For instance, a client 2 may be comprised in stationary infrastructure 3 at a road. A camera or other sensor of the stationary infrastructure 3 may detect the presence of e.g. a pedestrian, cyclist or other road user, which may not itself have a client 2. The central computer system 1 may determine a risk of an autonomous vehicle 4 getting too close, or even colliding, with said road user and thus initiates a P2P communication 7 between the client 2 of the autonomous vehicle 4 and the client 2 of the stationary infrastructure 3 to facilitate the autonomous vehicle 4 obtaining information from the stationary infrastructure 3 enabling the autonomous vehicle to avoid getting too close to the road user.

[0017] In another example, a pedestrian, cyclist or other road user may carry a mobile phone, typically smartphone, 3 having a client 2 running thereon. The central computer system 1 may determine a risk of an autonomous vehicle 4 getting too close, or even colliding, with said road user and thus initiates a P2P communication 7 between the client 2 of the autonomous vehicle 4 and the client 2 of the mobile phone 3 to facilitate the autonomous vehicle 4 obtaining information from the mobile phone 3 enabling the autonomous vehicle to avoid getting too close to the road user, and / or warning the road user via their mobile phone 3.

[0018] However, envisioned to be the most common situation, both clients 2 may be in respective autonomous vehicles 4 of the fleet of vehicles. The central computer system 1 may determine a risk of the autonomous vehicles 4 getting too close to each other, or even colliding, and thus initiates a P2P communication 7 between the respective clients 2 of the autonomous vehicles 4 to facilitate the autonomous vehicle 4 agreeing how to avoid getting too close to each other.

[0019] Each of the autonomous vehicles 4 may be any type of autonomous vehicle, e.g. any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, typically an autonomous car.

[0020] Figure 2 illustrates a central computer system 1, e.g. for cloud computing and / or edge computing. The central computer system 1 comprises processing circuitry 21 e.g. a central processing unit (CPU). The processing circuitry 21 may comprise one or a plurality of processing units in the form of microprocessor(s). However, other suitable devices with computing capabilities could be comprised in the processing circuitry 21, e.g. an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processing circuitry 21 is configured to run one or several computer program(s) or software (SW) 23 stored in a storage 22 of one or several storage unit(s) e.g. a memory. The storage unit is regarded as a computer readable means, forming a computer program product together with the SW 23 stored thereon as computer-executable components and may e.g. be in the form of a Random Access Memory (RAM), a Flash memory or other solid state memory, or a hard disk, or be a combination thereof. The processing circuitry 21 may also be configured to store data in the storage 22, as needed. The central computer system 1 also comprises a communication interface 24, e.g. for providing the respective central communications 6 with each of the clients 2. As mentioned above, the functionalities of the central computer system 1 may be provided by / in a computer cloud 5.

[0021] Figure 3 illustrates a structural device 3, e.g. an autonomous vehicle 4, comprising a client 2. The structural device 3 comprises processing circuitry 31 e.g. a central processing unit (CPU). The processing circuitry 31 may comprise one or a plurality of processing units in the form of microprocessor(s). However, other suitable devices with computing capabilities could be comprised in the processing circuitry 31, e.g. an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or a complex programmable logic device (CPLD). The processing circuitry 31 is configured to run one or several computer program(s) or software (SW) 33 stored in a storage 32 of one or several storage unit(s) e.g. a memory. The storage unit is regarded as a computer readable means, forming a computer program product together with the SW 33 stored thereon as computer-executable components and may e.g. be in the form of a Random Access Memory (RAM), a Flash memory or other solid state memory, or a hard disk, or be a combination thereof. The client 2 may run on the processing circuitry 31 as a result of execution of SW 33 stored in the storage 32. The processing circuitry 31 may also be configured to store data in the storage 32, as needed. The structural device 3 also comprises a communication interface 24, e.g. for the central communication 6 with the central computer system 1 and / or for a P2P communication 7 with any other client 2 in the control system 10. Optionally, the structural device 3 may comprise sensor(s) 35 for detecting or monitoring its surroundings, e.g. another road user as mentioned above. Such sensors 35 may e.g. include any of a camera, a radar and / or a lidar.

[0022] Figure 4 illustrates the method of the present invention. The method is for coordinating a fleet of autonomous vehicles 4, where at least one, typically several or all, of the autonomous vehicles of the fleet are structural devices 3 comprising a client 2. The method is performed in / by a central computer system 1, which central computer system 1 forms a control system 10 together with the clients 2.

[0023] The central control system 1 obtains S1 state information for each of a plurality of clients 2 comprised in respective structural devices 3. Typically, the central computer system 1 receives the state information from the client 2, via a communication 6 with the client 2. The state information for a client 2 is typically information about a state of the device 3, e.g. vehicle 4, comprising the client 2. The state information for a vehicle 4 includes information about a geographical position of the vehicle. The state information may be sent periodically or continuously, preferably continuously, for allowing the central computer system to keep track of the vehicle in real-time. The state information may additionally include other information about the vehicle's state. For instance, state information for a vehicle which is a car may include position coordinates (e.g. GPS position), speed and heading, while state information for an aerial drone may include position coordinates, speed and rotation. In accordance with the method, at least one of the structural devices 3 is an autonomous vehicle 4 of the fleet of vehicles. Typically, a plurality of the structural devices 3 are autonomous vehicles 4. From the respective client 2 of each of said at least one autonomous vehicle 4, real-time state information is received, indicating a geographical position of the vehicle.

[0024] Based on the obtained S1 state information, reachability analysis is performed S2 in the central computer system 1 to estimate likely future positions of the devices 3. For any stationary structural device 3, its future position may already inherently be known, but for mobile structural devices 3, such as autonomous vehicles 4 and / or mobile phones, the reachability analysis is needed to estimate likely future positions of the devices 3. The input to the reachability analysis of a device 3 may be any or all of the state information received from the client 2 in the device, e.g. current position, speed and heading of the device 3 / vehicle 4.

[0025] Based on the performed S2 reachability analysis, it is determined S3 whether a first one 4a of the at least one autonomous vehicle 4, including a first one 2a of the clients 2, risks a future spatial conflict, e.g. collision, at the device 3 of a second one 2b or 2c of the clients 2. A potential future conflict may exist if it is determined based on the reachability analysis that two of the devices 3 may get too close to each other, or even collide with each other, within the next seconds or minutes (depending on the temporal horizon of the reachability analysis). Alternatively, a potential future conflict may involve e.g. a road user which is observed by a device 3 but which does not itself include a client 2. The conflict may be a collision, but may alternatively be another type of conflict resulting from the two devices 3 coming too close to each other. For example, two vehicles 4 may be headed towards the same narrow passage. The reachability analysis may then estimate that they will want to pass the narrow passage at the same time. The central computer system 1 may then initiate P2P communication 7 between the two vehicles 4 (typically the clients 2 thereof) to allow them to decide among themselves which of them should go first through the passage. Without the P2P communication 7, they may not necessarily collide with each other but might e.g. come to a full stop and pass inefficiently.

[0026] In case it is determined that there is a risk of a future spatial conflict, P2P communication 7 is initiated S4 between the first client 2a and the second client 2b or 2c. The initiation S4 may include sending instructions, e.g. including credentials, to the first and / or second client 2 to set up the P2P communication 7. By means of the P2P communication 7, the clients may exchange information and decide amongst themselves, e.g. without involving the central computer system 1, how to avoid the conflict.

[0027] In some embodiments of the present invention, the method is performed as cloud computing and / or edge computing by the central computer system 1.

[0028] In some embodiments of the present invention, the real-time state information also includes motion parameters e.g. indicating a velocity and / or heading of the vehicle 4.

[0029] In some embodiments of the present invention, the obtaining S1 of the state information further comprises obtaining information about a future geographical and / or motion goal of the first autonomous vehicle 4a, wherein the reachability analysis is performed S2 also based on said goal information. A motion goal may be a goal for any motion parameter such as a velocity and / or heading of the vehicle 4. With information about a geographical and / or motion goal for the vehicle, the central computer system 1 will have additional information which can be input to the reachability analysis for estimating the future positions of the vehicle 4.

[0030] In some embodiments of the present invention, the first autonomous vehicle (4a) is any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, preferably an autonomous car.

[0031] In some embodiments of the present invention, the risked future conflict is a risked future collision. In some embodiments, the risked future collision is with the device 3b or 3c of the second client 2b or 2c. Alternatively, in some other embodiments, the risked future collision is with a person (e.g. road user) or object observed by sensor(s) 35 of the device 3b or 3c of the second client 2b or 2c.

[0032] In some embodiments of the present invention, the device 3b of the second client 2b is a second autonomous vehicle 4b. In some embodiments, the second autonomous vehicle 4b is any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, preferably an autonomous car.

[0033] In some embodiments of the present invention, the structural devices 3 include, in addition to the at least one autonomous vehicle 4, at least one of: stationary infrastructure, webcam(s), and mobile phone(s).

[0034] The present disclosure has mainly been described above with reference to a few embodiments. However, as is readily appreciated by a person skilled in the art, other embodiments than the ones disclosed above are equally possible within the scope of the present disclosure, as defined by the appended claims.

Examples

Embodiment Construction

[0013]Embodiments will now be described more fully hereinafter with reference to the accompanying drawings, in which certain embodiments are shown. However, other embodiments in many different forms are possible within the scope of the present disclosure. Rather, the following embodiments are provided by way of example so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Like numbers refer to like elements throughout the description.

[0014]Figure 1 illustrates a control system 10 comprising a central computer system 1, e.g. of a computer cloud 5, and a plurality of clients 2, e.g. in the form of software (SW) applications (i.e. apps). The clients 2 are in communication with the central computer system 1, via respective central communications 6, e.g. by each client 2 sending state information to the central computer system 1 via an uplink of the central communication 6 and by the central computer system 1...

Claims

1. A method performed by a central computer system (1) for coordinating a fleet of autonomous vehicles, the method comprising: obtaining (S1) state information for each of a plurality of clients (2) comprised in respective structural devices (3), at least one of said devices being an autonomous vehicle (4), including from the respective client (2) of each of said at least one autonomous vehicle (4), receiving real-time state information indicating a geographical position of the vehicle; based on the obtained (S1) state information, performing (S2) reachability analysis to estimate likely future positions of the devices (3); based on the performed (S2) reachability analysis, determining (S3) that a first one (4a) of the at least one autonomous vehicle (4), of a first one (2a) of the clients (2), risks a future conflict at the device (3) of a second one (2b / 2c) of the clients (2); and initiating (S4) direct peer-to-peer, P2P, communication (7) between the first client (2a) and the second client (2b / 2c).

2. The method of claim 1, wherein the method is performed as cloud computing or edge computing by the central computer system (1).

3. The method of any preceding claim, wherein the real-time state information also includes motion parameters e.g. indicating a velocity and / or heading of the vehicle (4).

4. The method of any preceding claim, wherein the obtaining (S1) state information further comprises obtaining information about a future geographical and / or motion goal of the first autonomous vehicle (4a), wherein the reachability analysis is performed (S2) also based on said goal information.

5. The method of any preceding claim, wherein the first autonomous vehicle (4a) is any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, preferably an autonomous car.

6. The method of any preceding claim, wherein the risked future conflict is a risked future collision.

7. The method of claim 6, wherein the risked future collision is with the device (3b / 3c) of the second client (2b / 2c).

8. The method of claim 6, wherein the risked future collision is with a person or object observed by sensors (35) of the device (3b / 3c) of the second client (2b / 2c).

9. The method of any preceding claim, wherein the device (3b) of the second client (2b) is a second autonomous vehicle (4b).

10. The method of claim 9, wherein the second autonomous vehicle (4b) is any one of an autonomous car, an autonomous truck, an autonomous mining vehicle, an autonomous boat, an autonomous underwater vehicle, an autonomous robot e.g. a walking robot, or an autonomous aerial drone, preferably an autonomous car.

11. The method of any preceding claim, wherein the structural devices (3) include, in addition to the at least one autonomous vehicle (4), at least one of: stationary infrastructure, webcams, and mobile phones.

12. A central computer system (1) comprising: processing circuitry (21); and storage (22) storing instructions (23) executable by said processing circuitry whereby the central computer system (1) is operative to perform the method of any preceding claim.

13. A control system (10) comprising: the central computer system (1) of claim 12; and the plurality of clients (2).

14. A computer program product (22) comprising computer-executable components (23) for causing a central computer system (1) to perform the method of any one of claims 1-11 when the computer-executable components are run on processing circuitry (21) comprised in the central computer system.

Images