Online agent predictions using semantic maps
AssigneeToyota Research Institute, Inc.
InventorsMarcus HAMMOND, Tyler William Packard, Randall ST ROMAIN, II
Life of this patent
Estimating the term…
Abstract
A method for controlling a vehicle based on a prediction from a semantic map is presented. The method includes receiving a snapshot of an environment from one or more sensors. The method also includes generating the semantic map based on the snapshot and predicting an action of a dynamic object in the snapshot based on one or more surrounding objects. The method still further includes controlling an action of the vehicle based on the predicted action.
Claims18
A method for controlling a vehicle based on a prediction from a semantic map, comprising:
- receiving a snapshot of an environment from at least one sensor;
- generating the semantic map based on the snapshot;
- predicting an action of a dynamic object in the snapshot based on at least one surrounding object;
- and
- controlling an action of the vehicle based on the predicted action.
An apparatus for controlling a vehicle based on a prediction from a semantic map, the apparatus comprising:
- a memory;
- and
- at least one processor coupled to the memory, the at least one processor configured:
- to receive a snapshot of an environment from at least one sensor;
- to generate the semantic map based on the snapshot;
- to predict an action of a dynamic object in the snapshot based on at least one surrounding object;
- and
- to control an action of the vehicle based on the predicted action.
A non-transitory computer-readable medium having program code recorded thereon for controlling a vehicle based on a prediction from a semantic map, the program code executed by a processor and comprising:
- program code to receive a snapshot of an environment from at least one sensor;
- program code to generate the semantic map based on the snapshot;
- program code to predict an action of a dynamic object in the snapshot based on at least one surrounding object;
- and
- program code to control an action of the vehicle based on the predicted action.
Dependencies are inferred from the claim text.