Autonomous behaviors for a remote vehicle

• US 20080027590A1
• Filed: 07/16/2007
• Published: 01/31/2008
• Est. Priority Date: 07/14/2006
• Status: Active Grant

• Current Assignee: Flir Detection, Inc. (Teledyne Technologies Incorporated)
• Original Assignee: iRobot Corporation
• Inventors: Jamieson, Joseph, Sawyer, Tyson, Shein, Andrew, Phillips, Emilie, Powers, Aaron
• Granted Patent: US 8,326,469 B2
• Time in Patent Office: Days
• US Class Current: 701/2
• 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

Abstract

A method for enhancing operational efficiency of a remote vehicle using a diagnostic behavior. The method comprises inputting and analyzing data received from a plurality of sensors to determine the existence of deviations from normal operation of the remote vehicle, updating parameters in a reference mobility model based on deviations from normal operation, and revising strategies to achieve an operational goal of the remote vehicle to accommodate deviations from normal operation. An embedded simulation and training system for a remote vehicle. The system comprises a software architecture installed on the operator control unit and including software routines and drivers capable of carrying out mission simulations and training.

Claims

1. A method for operating a remote vehicle using a diagnostic behavior, the method comprising:

inputting and analyzing data received from a plurality of sensors to determine the existence of deviations from normal operation of the remote vehicle;

updating parameters in a reference mobility model based on deviations from normal operation; and

revising strategies to achieve an operational goal of the remote vehicle to accommodate deviations from normal operation.

2. The method of claim 1, wherein the diagnostic behavior is persistent.

3. The method of claim 1, wherein the data received from the plurality of sensors includes preventative sensor data.

4. The method of claim 3, wherein the preventative sensor data includes changes in upcoming terrain.

5. The method of claim 1, wherein the data regards one or more of the remote vehicle'"'"'s environment, the status of the remote vehicle'"'"'s components, and the remote vehicle'"'"'s internal environment.

6. The method of claim 1, further comprising adding a payload capable of collecting the data and dedicated to overseeing data collection from designated sensors of the remote vehicle.

7. The method of claim 6, wherein processing circuits included in the payload are capable of outputting flags indicative of system faults when a sensed state persists for a predetermined period of time.

8. The method of claim 7, further comprising displaying system faults to an operator of the remote vehicle.

9. The method of claim 1, further comprising calculating system faults using sensors already on the vehicle.

10. The method of claim 1, further comprising synthesizing pre-existing sensor data to determine whether a system fault has occurred.

11. The method of claim 1, further comprising performing routines and inputting and analyzing responsive data received from predetermined sensors to determine whether a system fault has occurred.

12. The method of claim 11, wherein analysis and updating are performed by a diagnostic assembly of behavior-level software of the remote vehicle.

13. The method of claim 1, wherein deviations from normal operation include one or more of a flat tire, a low battery, low fuel, jammed tracks, broken flippers, malfunctioning sensors, an overloaded arm, extra payloads, and mud encumbering the vehicle.

14. The method of claim 1, further comprising altering control commands to actuators of the remote vehicle based on the reference mobility model.

15. The method of claim 1, wherein the reference mobility model is stored in the remote vehicle'"'"'s memory.

16. An embedded simulation and training system for a remote vehicle, the system being installed on an operator control unit and comprising:

a software architecture installed on the operator control unit and including software routines and drivers capable of carrying out mission simulations and training, the software routines comprising;

a virtual remote vehicle simulator for generating physical characteristics of a remote vehicle as it moves through a simulated environment and responds to control commands sent by the operator control unit;

a behavior-based control system for generating behavioral characteristics of a remote vehicle;

an environmental simulator for generating sensor events based on a simulated environment;

an integration controller for sending sensor events from the environmental simulator to the behavior-based control system; and

a mission routine suite executed by a central control system of the operator control unit, the mission routine suite including at least one training scenario routine for implementation by the virtual remote vehicle simulator and the environmental simulator,

wherein movement of a remote vehicle through a simulated environment is defined by sensor events generated by the environmental simulator, sensor events generated by actuation of operator controls, behavioral characteristics generated by the behavior-based control system, and physical variables generated by the virtual remote vehicle simulator.

17. The system of claim 16, wherein the virtual remote vehicle simulator defines the physical components of the remote vehicle and provides a simulation of the remote vehicle'"'"'s basic framework.

18. The system of claim 17, wherein the basic framework of the remote vehicle includes physical characteristics, behavioral characteristics, and other features relevant to interaction of the remote vehicle with its external environment and response to operator commands.