Back to results
US 11,237,556 B2Granted
Autonomous vehicle
AssigneeKnowm Inc
InventorAlex Nugent
Life of this patent
Estimating the term…
Abstract
An autonomous vehicle includes one or more sensors that measures the distance to and/or other properties of a target by illuminating the target with light. The sensor(s) provides sensor data indicative of one or more surface manifolds. Point data is generated with respect to the surface manifold(s). AHaH (Anti-Hebbian and Hebbian) based mechanism performs an AHaH-based feature extraction operation on the point data for compression and processing thereof.
Claims20
An autonomous vehicle, comprising:
- at least one sensor associated with said autonomous vehicle, wherein said at least one sensor measures a distance to and/or other properties of a target by illuminating said target with light, wherein said at least one sensor provides sensor data indicative of at least one surface manifold and wherein point data is generated with respect to said at least one surface manifold;
- and
- an AHaH (Anti-Hebbian and Hebbian) based mechanism that performs an AHaH-based feature extraction operation on said point data for compression and processing thereof, wherein at least one voxel of a point cloud composed of said point data is scanned to recover said compressed binary label which represents prototypical surface patches with respect to said at least one surface manifold.
An autonomous vehicle, comprising:
- at least one sensor associated with said autonomous vehicle, wherein said at least one sensor measures a distance to and/or other properties of a target by illuminating said target with light, wherein said at least one sensor provides sensor data indicative of at least one surface manifold and wherein point data is generated with respect to said at least one surface manifold;
- and
- an AHaH (Anti-Hebbian and Hebbian) based mechanism that performs an AHaH-based feature extraction operation on said point data for compression and processing thereof, said AHaH based mechanism acting on a plurality of synaptic weights, said synaptic weights formed of memristors.
An autonomous vehicle, comprising:
- at least one sensor associated with said autonomous vehicle, wherein said at least one sensor measures a distance to and/or other properties of a target by illuminating said target with light, wherein said at least one sensor provides sensor data indicative of at least one surface manifold and wherein point data is generated with respect to said at least one surface manifold;
- and
- a liquid state machine forming spatial-temporal encoding of said point data;
- and
- an AHaH (Anti-Hebbian and Hebbian) based mechanism that performs an AHaH-based feature extraction operation on said spatial-temporal encoding for compression and processing thereof, wherein said AHaH based mechanism acts on synaptic weights formed from memristors.
2 more elements
Dependencies are inferred from the claim text.