초록 ▼

The present invention provides a co-operative network of unmanned vehicles that participate in co-operative task allocation. Each unmanned vehicle comprises a computer system with an executive level configured to control motion of the unmanned vehicle and an automatic decision level configured to co

The present invention provides a co-operative network of unmanned vehicles that participate in co-operative task allocation. Each unmanned vehicle comprises a computer system with an executive level configured to control motion of the unmanned vehicle and an automatic decision level configured to communicate with other unmanned vehicles, to receive task descriptions, to participate in task allocation, and to provide descriptions of tasks to be performed to the executive level for execution. Each unmanned vehicle submits a bid for each task it can perform, the bid reflecting an execution cost for the task. The bids are compared and the task effectively auctioned to the unmanned vehicle with a lowest execution cost. Each unmanned vehicle builds a task plan from its allocated tasks, decomposes the associated task descriptions into elementary task descriptions and forwards the elementary task descriptions in a format suitable for the executive level to execute.

대표청구항 ▼

1. A computer system for use in an unmanned vehicle capable of use in a co-operative network of unmanned vehicles, wherein the computer system is programmed to allow autonomous operation of an unmanned vehicle and comprises: an executive level configured to send control signals for controlling propu

1. A computer system for use in an unmanned vehicle capable of use in a co-operative network of unmanned vehicles, wherein the computer system is programmed to allow autonomous operation of an unmanned vehicle and comprises: an executive level configured to send control signals for controlling propulsion and steering of the unmanned vehicle, and to receive a status signal regarding a status of the unmanned vehicle; andan automatic decision level configured to communicate with a ground control station and other unmanned vehicles, to receive task descriptions, to participate in task allocation, and to provide descriptions of tasks to be performed to the executive level for execution, wherein the automatic decision level comprises a task refining module and a task manager module;wherein the task refining module is configured to receive an unallocated task description describing a task to be undertaken by one of the unmanned vehicle in the co-operative network, to determine if the unmanned vehicle is able to perform the task, and to calculate an execution cost for the unmanned vehicle to execute that task; andwherein the task manager module is configured to receive elementary task descriptions, store the elementary task descriptions and forward the elementary task descriptions in a format suitable for the executive level to execute. 2. The computer system of claim 1, wherein the task refining module is further configured to build a task plan comprising an ordered list of tasks allocated to the unmanned vehicle according to a planned order of execution, and to decompose the task descriptions associated with the allocated tasks into elementary task descriptions for the executive level. 3. The computer system of claim 2, wherein the task refining module comprises a task refining toolbox, a plan builder and a plan merger. 4. The computer system of claim 3, wherein the task refining toolbox is configured to decompose task descriptions associated with the allocated tasks into elementary task descriptions for the executive level and to provide elementary tasks to the plan builder. 5. The computer system of claim 4, wherein the plan builder is configured to order the elementary tasks into the task plan that comprises the list of tasks ordered according to a planned order of execution, and to generate a path to be followed to execute the task plan. 6. The computer system of claim 5, wherein the plan merger is configured to communicate with other unmanned vehicles to ensure that the path will not bring the unmanned vehicle into conflict with other unmanned vehicles. 7. The computer system of claim 5, wherein the plan builder is further configured to amend the task plan if conflicts are found. 8. The computer system of claim 1, wherein the task manager module comprises a task manager and a synchronization manager, wherein the task manager is configured to store elementary tasks with associated pre-conditions to be fulfilled before a corresponding task can be executed, the synchronization manager is configured to monitor the status of the unmanned vehicle to determine when the pre-conditions of an elementary task are fulfilled, and the task manager is configured to forward an associated elementary task description to the executive level for execution when the pre-conditions are fulfilled. 9. The computer system of claim 8, wherein the executive level is configured to provide task status data and/or unmanned vehicle status data derived from the status signal, and wherein the synchronization manager is configured to use that data to determine when the pre-conditions are fulfilled. 10. The computer system of claim 8, wherein the task refining module is configured to receive a pre-allocated task description describing a task specifically allocated to the unmanned vehicle in addition to tasks allocated through an auction, to build a task plan comprising an ordered list of tasks allocated to the unmanned vehicle, including both pre-allocated tasks and tasks allocated by auction, according to a planned order of execution. 11. The computer system of claim 1, wherein the automatic decision level further comprises a task allocation module, the task allocation module being configured: (a) to operate as a bidder in an auction by forwarding the execution cost as a bid to another unmanned vehicle and, if successful, to receive a task allocation message informing the unmanned vehicle that it won the auction and so has been allocated the task; and(b) to operate as an auctioneer by receiving bids from other unmanned vehicles where each bid corresponds to the execution cost for the associated unmanned vehicle to execute the task, and to select the bid with a lowest execution cost and to send a task allocation message to the other unmanned vehicle associated with the selected bid to inform that unmanned vehicle that it has been allocated the task. 12. An unmanned vehicle capable of use in a co-operative network of unmanned vehicles, comprising a computer system programmed to allow autonomous operation of the unmanned vehicle, wherein the computer system comprises: an executive level configured to send control signals for controlling propulsion and steering of the unmanned vehicle, and to receive a status signal regarding a status of the unmanned vehicle; andan automatic decision level configured to communicate with a ground control station and other unmanned vehicles, to receive task descriptions, to participate in task allocation, and to provide descriptions of tasks to be performed to the executive level for execution, wherein the automatic decision level comprises a task refining module and a task manager module;wherein the task refining module is configured to receive an unallocated task description describing a task to be undertaken by one of the unmanned vehicle in the co-operative network, to determine if the unmanned vehicle is able to perform the task, and to calculate an execution cost for the unmanned vehicle to execute that task; andwherein the task manager module is configured to receive elementary task descriptions, store the elementary task descriptions and forward the elementary task descriptions in a format suitable for the executive level to execute. 13. The unmanned vehicle of claim 12, further comprising a sensor operable to sense information regarding a status of the unmanned vehicle. 14. The unmanned vehicle of claim 13, further comprising a perception system with surveillance sensors for gathering data and a data fusion engine to fuse data provided by the surveillance sensors. 15. A network comprising a plurality of unmanned vehicles according to claim 14, wherein the unmanned vehicles have a common design of automatic decision level and differing designs of executive levels. 16. A network comprising a plurality of unmanned vehicles according to claim 14, wherein the unmanned vehicles are configured to communicate with each other via automatic decision levels. 17. A method of operating a network of unmanned vehicles, each unmanned vehicle comprising a computer system programmed to allow autonomous operation of the unmanned vehicle that is divided into an executive level configured to control motion of the unmanned vehicle and an automatic decision level configured to communicate with a ground control station and other unmanned vehicles and to provide descriptions of tasks to be performed to the executive level for execution, the method comprising: transmitting a set of task descriptions to the unmanned vehicles;each unmanned vehicle determining if the unmanned vehicle is able to perform a task, and calculating an execution cost for the unmanned vehicle to execute the task;allocating the tasks by holding an auction to allocate each task in which each bid corresponds to the execution cost of the unmanned vehicle to perform the task, the bid with a lowest execution cost is selected, and a winning unmanned vehicle is notified of their successful bid;each unmanned vehicle building a task plan comprising an ordered list of tasks allocated to the unmanned vehicle according to a planned order of execution, decomposing the task descriptions associated with the allocated tasks into elementary task descriptions for the executive level, and providing the elementary task descriptions to the executive level in a format suitable for the executive level to execute the task; andeach unmanned vehicle executing the tasks it has been allocated. 18. The method of claim 17, comprising each unmanned vehicle using its task plan to generate a path to be followed to execute the task plan, the unmanned vehicles sharing descriptions of their paths and ensuring that the paths will not cause conflicts between the unmanned vehicles. 19. The method of claim 17, wherein some tasks have associated pre-conditions to be fulfilled before execution of the task, the method comprising the unmanned vehicles sharing task status information, and an unmanned vehicle using shared task status information to determine that the pre-conditions of an allocated task of the unmanned vehicles have been fulfilled and executing that task.