Back to results
US 12,603,000 B1Granted
Prediction errors region based aggregation
AssigneeZoox, Inc.
InventorsMahsa Ghafarianzadeh, Ruitao Yi
Life of this patent
Estimating the term…
Abstract
Techniques for determining and aggregating prediction error are described herein. A prediction may be determined for an object within a region based on first sensor data. A prediction error may be determined based on a difference between the prediction and second sensor data. The prediction error may be associated with the region and aggregated by a same region. The aggregated prediction error may be used to determine an expansion of service into the region.
Claims20
A system comprising:
- one or more processors;
- and
- one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:
- receiving first sensor data captured by a first vehicle located within a region at a first time, the first sensor data indicating an object;
- determining, using a machine-learned model, a predicted state associated with the object, the predicted state comprising at least a pose of the object at a second time or a maneuver performed by the object;
- receiving second sensor data captured by the first vehicle at the second time, the second sensor data indicating the object;
- determining, based at least in part on the second sensor data, a state of the object at the second time;
- determining a prediction error based at least in part on a difference between the predicted state and the state of the object at the second time;
- determining to associate the prediction error with the region;
- determining, based at least in part on associating the prediction error with the region, a prediction error metric;
- determining, based at least in part on comparing the prediction error metric to at least one of a first threshold associated with expansion of service or a second threshold associated with disengagement of service, to at least one of:
- expand service associated with a fleet of autonomous vehicles comprising the first vehicle into the region, or
- increase a number of vehicles in the fleet that are permitted to operate in the region, wherein the second threshold is higher than the first threshold;
- and
- instructing, based on determining to expand service or to increase the number of vehicles, a second vehicle in the fleet to generate a trajectory traversing the region, wherein the second vehicle in the fleet is configured to traverse the region based at least in part on the trajectory.
12 more elements
A method comprising:
- receiving first data captured at a first time, the first data indicating an object;
- determining a predicted state associated with the object;
- receiving second data captured at a second time, the second data indicating the object;
- determining, based at least in part on the second data, a state of the object at the second time;
- determining a prediction error based at least in part on a difference between the predicted state and the state of the object at the second time;
- determining to associate the prediction error with a region;
- determining a first total prediction error based at least in part on the prediction error and one or more other prediction errors of the region;
- determining, based at least in part on the first total prediction error, a prediction error metric;
- determining, based at least in part on comparing the prediction error metric to at least one of a first error threshold or a second error threshold higher than the first error threshold, to at least one of:
- expand service associated with a fleet of vehicles into the region, or
- increase a number of vehicles in the fleet that are permitted to operate in the region;
- and
- instructing, based at least in part on determining to at least one of expand service or to increase the number of vehicles, an individual vehicle in the fleet to generate a trajectory traversing the region, wherein the individual vehicle in the fleet is configured to traverse the region based at least in part on the trajectory.
10 more elements
One or more non-transitory computer-readable media storing instructions executable by a processor, wherein the instructions, when executed, cause the processor to perform operations comprising:
- receiving first data captured at a first time, the first data indicating an object;
- determining a predicted state associated with the object;
- receiving second data captured at a second time, the second data indicating the object;
- determining, based at least in part on the second data, a state of the object at the second time;
- determining a prediction error based at least in part on a difference between the predicted state and the state of the object at the second time;
- determining to associate the prediction error with a region;
- determining a first total prediction error based at least in part on the prediction error and one or more other prediction errors of the region
- determining, based at least in part on the first total prediction error, a prediction error metric;
- determining, based at least in part on comparing the prediction error metric to at least one of a first threshold or a second threshold higher than the first threshold, to at least one of:
- expand service associated with a fleet of vehicles into the region, or
- increase a number of vehicles in the fleet that are permitted to operate in the region;
- and
- permitting, based at least in part on determining to at least one of expand service or to increase the number of vehicles, a vehicle associated with the fleet to traverse the region, wherein the vehicle was previously prohibited from traversing the region.
10 more elements
Dependencies are inferred from the claim text.