Training of vehicles to improve autonomous capabilities
OwnerAshok Krishnaninventor
Life of this patent
Estimating the term…
Abstract
Systems and methods to improve performance, reliability, learning and safety and thereby enhance autonomy of vehicles. Human sensors are used to capture human eye movement, hearing, hand grip and contact area, and foot positions. Event signatures corresponding to human actions, reactions and responses are extracted form these sensor values and correlated to events, status and situations acquired using vehicle and outside environment sensors. These event signatures are then used to train vehicles to improve their autonomous capabilities. Human sensors are vehicle mounted or frame mounted. Signatures obtained from events are classified and stored.
Claims8
A method of determining if an event outside a vehicle operated by a human subject has occurred, the method comprising:
- detecting the occurrence of at least one primary human event selected from an eye event or an aural event, detecting the occurrence of at least one secondary human event selected from a hand event or a foot event, and making a determination that an outside event has occurred if at least one each of a primary human event as well as a secondary human event has occurred, and neither of the primary of secondary human events correlates with an associated map.
A method of determining if an event outside a vehicle operated by a human subject has occurred, the method comprising:
- detecting the occurrence of at least one primary human event selected from (i) an eye event, or (ii) an aural event, detecting the occurrence of at least one primary vehicle event selected from:
- (i) a change in the speed of the vehicle, (ii) a change in the direction of the vehicle;
- and making a determination that an outside event has occurred if at least one primary human event as well as at least one primary vehicle event has occurred, and neither the at least one of primary human events nor the at least one of primary vehicle events correlates with an associated map.
Dependencies are inferred from the claim text.