Human-Supervised Autonomous Systems Performance and Safety Monitoring Methods and Apparatus
AssigneeEdge Case Research, Inc.
InventorPhilip J. Koopman, Jr.
Life of this patent
Estimating the term…
Abstract
Human supervisor failures in autonomous system operations are detected. Perception sensor data input is obtained from a sensor. A violation of a safety envelope by at least one external object is detected within the perception sensor data input. A response to the violation of the safety envelope is triggered. The safety envelope has predetermined dimensions that are based upon an expected time to mitigate the violation of the safety envelope.
Claims20
A system for detecting human supervisor failures in autonomous system operations comprising a memory or other data storage facility and one or more processors configured to perform the steps of:
- obtaining perception sensor data input from one or a plurality of sensors;
- detecting, within the perception sensor data input, a violation of a safety envelope by at least one external object;
- and
- triggering one or more responses to the violation of the safety envelope;
- wherein the safety envelope has predetermined dimensions that are based upon an expected time to mitigate the violation of the safety envelope.
A computer-implemented method for detecting human supervisor failures in autonomous system operations comprising:
- obtaining perception sensor data input from a sensor for measuring interactions between an external object and a safety envelope;
- detecting, within the perception sensor data input, a violation of the safety envelope by the external object;
- and
- triggering a response to the violation of the safety envelope with the response being based upon an expected time to mitigate the violation of the safety envelope.
Dependencies are inferred from the claim text.