Back to results
US 11,454,701 B2Granted
Real-time and dynamic calibration of active sensors with angle-resolved doppler information for vehicles
AssigneePony AI Inc.
InventorsCyrus F. Abari, Harsh Mohan, Haomin Wang
Life of this patent
Estimating the term…
Abstract
Provided herein is a system on a vehicle, the system comprising an active Doppler sensor; one or more processors; and a memory storing instructions that, when executed by the one or more processors, causes the system to perform: obtaining a Doppler signature from each of one or more entities; and calibrating the active Doppler sensor based on the Doppler signature from at least a portion of the one or more entities.
Claims17
A system on a vehicle comprising:
- an active Doppler sensor;
- one or more processors;
- and
- a memory storing instructions that, when executed by the one or more processors, causes the system to perform:
- obtaining a Doppler velocity from each of one or more entities;
- individually determining whether each of the one or more entities is stationary, wherein the one or more entities determined to be stationary comprise another vehicle, a road sign, a curb, or a tree;
- removing any of the entities determined not to be stationary;
- forming one or more clusters, each of the clusters comprising at least a portion of the entities determined to be stationary and defining a relationship between a location of one of the entities with respect to the active Doppler sensor and the Doppler velocity of the respective one of the entities;
- fitting, to each of the one or more clusters, a signal model defining the Doppler velocity in relation to a mounting offset angle of the active Doppler sensor and a mounting location of the active Doppler sensor;
- determining a degree of fit of the signal model to each of the one or more clusters;
- and
- removing any of the clusters having a degree of fit lower than a threshold while keeping remaining clusters;
- calibrating the active Doppler sensor based on at least a portion of the remaining clusters;
- acquiring data using the calibrated active Doppler sensor;
- and
- processing the acquired data.
13 more elements
A method implemented by a system including an active Doppler sensor, one or more processors and storage media storing machine-readable instructions, the method comprising:
- obtaining a Doppler velocity from each of one or more entities;
- individually determining whether each of the one or more entities is stationary, wherein the one or more entities determined to be stationary comprise another vehicle, a road sign, a curb, or a tree;
- removing any of the entities determined not to be stationary;
- forming one or more clusters, each of the clusters comprising at least a portion of the entities determined to be stationary and defining a relationship between a location of one of the entities with respect to the active Doppler sensor and the Doppler velocity of the respective one of the entities;
- fitting, to each of the one or more clusters, a signal model defining the Doppler velocity in relation to a mounting offset angle of the active Doppler sensor and a mounting location of the active Doppler sensor;
- determining a degree of fit of the signal model to each of the one or more clusters;
- and
- removing any of the clusters having a degree of fit lower than a threshold while keeping remaining clusters;
- calibrating the active Doppler sensor based on at least a portion of the remaining clusters;
- acquiring data using the calibrated active Doppler sensor;
- and
- processing the acquired data.
9 more elements
A non-transitory computer readable medium comprising instructions that, when executed, cause one or more processors to perform:
- obtaining a Doppler velocity from each of one or more entities;
- individually determining whether each of the one or more entities is stationary, wherein the one or more entities determined to be stationary comprise another vehicle, a road sign, a curb, or a tree;
- removing any of the entities determined not to be stationary;
- forming one or more clusters, each of the clusters comprising at least a portion of the entities determined to be stationary and defining a relationship between a location of one of the entities with respect to the active Doppler sensor and the Doppler velocity of the respective one of the entities;
- fitting, to each of the one or more clusters, a signal model defining the Doppler velocity in relation to a mounting offset angle of the active Doppler sensor and a mounting location of the active Doppler sensor;
- determining a degree of fit of the signal model to each of the one or more clusters;
- and
- removing any of the clusters having a degree of fit lower than a threshold while keeping remaining clusters;
- calibrating the active Doppler sensor based on at least a portion of the remaining clusters;
- acquiring data using the calibrated active Doppler sensor;
- and
- processing the acquired data.
9 more elements
Dependencies are inferred from the claim text.