System validation

• US 8,989,945 B2
• Filed: 05/17/2011
• Issued: 03/24/2015
• Est. Priority Date: 05/19/2010
• Status: Active Grant

• Current Assignee: BAE Systems Plc
• Original Assignee: BAE Systems Plc
• Inventors: Callow, Glenn Michael
• Primary Examiner(s): To, Tuan C.
• Assistant Examiner(s): Hilgendorf, Dale W
• Application Number:
  US13/698,835
• Publication Number:
  US 20130073138A1
• Time in Patent Office: 1,407 Days
• Field of Search: 701/23, 701/24, 701/27
• US Class Current: 701/24
• CPC Class Codes: G05B 13/04 involving the use of models or simulators
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G06N 5/00 Computing arrangements using knowledge-based models

Abstract

A method and apparatus for evaluating capabilities of a system (e.g. an autonomous vehicle) with respect to the performance of a task, the method including: providing a first model corresponding to the task; providing a further model corresponding to the system; providing a plurality of mappings from one model to another model; determining whether there exists a transformation trace either (i) from the first model to the further model, or (ii) from the further model to the first model, wherein each transformation trace includes one or more of the specified mappings; and evaluating the capabilities of the system with respect to the task dependent upon the existence of the transformation trace.

Claims

1. A method performed on an autonomous vehicle designed to operate in a plurality of environments, the method comprising:

(a) validating, via one or more systems onboard the autonomous vehicle, capabilities of the autonomous vehicle designed to operate in the plurality of environments with respect to a task to be performed in a current environment, the validation of capabilities including;

providing a first model, the first model corresponding to the task to be performed and the current environment;

providing a further model, the further model corresponding to designed features of the autonomous vehicle;

providing a plurality of mappings from one model to another model;

determining whether there exists a transformation trace either (i) from the first model to the further model, or (ii) from the further model to the first model, wherein each transformation trace comprises one or more of the specified mappings; and

evaluating the capabilities of the autonomous vehicle with respect to the task to be performed in the current environment, the evaluation outcome being dependent upon existence of the transformation trace;

(b) validating the first and further models for the task to be performed in the current environment based on the existence of the transformation trace between the first and further models;

(c) inputting data corresponding to a result of step (a) and (b) into other systems of the autonomous vehicle; and

(d) performing a specified action of the autonomous vehicle, when the validated transformation trace exists and the capability of the autonomous vehicle with respect to the task to be performed in the current environment is verified.

2. The method according to claim 1, comprising:

providing, via one or more sensors, data about environmental conditions in which the autonomous vehicle is operating.

3. The method according to claim 1, comprising:

providing, via one or more sensors, information about actions that may be performed by the autonomous vehicle.

4. The method according to claim 1, wherein evaluating the capabilities of the autonomous vehicle with respect to the task comprises:

determining whether the autonomous vehicle is capable of performing the task in the current environment.

5. The method according to claim 4, wherein it is determined that the autonomous vehicle is capable of performing the task in the current environment if the transformation trace exists.

6. The method according to claim 1, comprising:

specifying a second further model, the second further model corresponding to the autonomous vehicle;

wherein

the determining whether there exists a transformation trace includes;

determining whether there exists either;

(i) a transformation trace from the first model to the second further model and a transformation trace from the second further model to the further model;

or

(ii) a transformation trace from the further model to the second further model and a transformation trace from the second further model to the first model; and

each transformation trace includes one or more of the specified mappings.

7. The method according to claim 1, wherein:

a first meta-model provides a basis for the first model;

a second meta-model provides a basis for the further model; and

the determining whether there exists a transformation trace includes;

determining whether there exists a transform or mapping from the first meta-model to the second meta-model;

wherein

a transform or mapping from the first meta-model to the second meta-model provides a basis for the transformation trace either (i) from the first model to the further model, or (ii) from the further model to the first model.

8. The method according to claim 1, wherein the first model is a Computation Independent Model.

9. The method according to claim 1, wherein a further model is one of the following:

(i) a Platform Independent Model, or (ii) a Platform Specific Model.

10. The method according to claim 1, wherein the method is implemented using Planning Domain Definition Language.

11. The method according to claim 1, wherein:

there are two further models;

one of the two further models is a Platform Independent Model; and

the other of the two further models is a Platform Specific Model.

12. Apparatus for mounting onboard an autonomous vehicle designed to operate in at least one environment, the apparatus configured for validating capabilities of the autonomous vehicle with respect to a task to be performed in a current environment, the apparatus comprising:

one or more processors arranged to;

determine whether there exists a transformation trace either (i) from a first model to a further model, or (ii) from the further model to the first model, and each transformation trace comprising one or more of a plurality of mappings; and

evaluate the capabilities of the autonomous vehicle with respect to the task to be performed in the current environment, the evaluation outcome being dependent upon the existence of the transformation trace;

wherein

the first model corresponds to the task to be performed in the current environment;

the further model corresponds to designed features of the autonomous vehicle; and

the plurality of mappings are specified from one model to another model;

validate the first and further models for the task to be performed in the current environment based on the existence of the transformation trace between the first and further models; and

perform a specified action of the autonomous vehicle, when the validated transformation trace exists and the capability of the autonomous vehicle with respect to the task to be performed in the current environment is verified.

13. The apparatus according to claim 12, in combination with the autonomous vehicle wherein the apparatus is mounted.

14. A machine readable storage medium for storing a program or at least one of a plurality of programs in non-transitory form, for placement into a computer system, such that when executed will cause the computer system to perform the functions of:

(a) validating, via one or more systems onboard an autonomous vehicle designed to operate in at least one environment, capabilities of the autonomous vehicle with respect to a task to be performed in a current environment, the evaluating of capabilities including;

providing a first model, the first model corresponding to the task to be performed in the current environment;

providing a further model, the further model corresponding to designed features of the autonomous vehicle;

providing a plurality of mappings from one model to another model;

determining whether there exists a transformation trace either (i) from the first model to the further model, or (ii) from the further model to the first model, wherein each transformation trace comprises one or more of the specified mappings; and

evaluating the capabilities of the autonomous vehicle with respect to the task to be performed in the current environment, the evaluation outcome being dependent upon existence of the transformation trace;

(b) validating the first and further models for the task to be performed in the current environment based on the existence of the transformation trace between the first and further models;

(c) inputting data corresponding to a result of step (a) and (b) into other systems of the autonomous vehicle; and

(d) performing a specified action of the autonomous vehicle, when the validated transformation trace exists and the capability of the autonomous vehicle with respect to the task to be performed in the current environment is verified.

15. The machine readable medium according to claim 14, wherein the program or plurality of programs are arranged on a computer system such that when executed by the computer system or one or more processors will cause the computer system or the one or more processors to perform the functions of the stored program.