Back to results
US 12,566,236 B1Granted
Automated sensor noise model tuning
AssigneeZoox, Inc.
InventorsMichael Carsten Bosse, Jeffrey Eric Tolliver
Life of this patent
Estimating the term…
Abstract
Auto-tuning covariances associated with a set of noise models for a variety of sensor modalities and/or perception components such that the covariances are leveled respective to one another may include whitening the covariances and/or error models and determining scalars to apply to the covariances. Determining these scalars may comprise using the residuals that result from generating the set of noise model (e.g., such as may be determined as part of least squares estimation) along with the hat matrix of the process model to determine the scalars. The covariances may iteratively be updated until the scalar adjustments converge or until another end condition is met.
Claims20
A method comprising:
- determining a set of noise models comprising a first noise model and a second noise model, wherein the first noise model is based at least in part on first sensor data from a first sensor of a first sensor modality and the second noise model is based at least in part on second sensor data from a second sensor of a second sensor modality;
- determining, based at least in part on the set of noise models and a set of covariances associated with the set of noise models, a process output, wherein determining the process output comprises determining a portion of the process output that reduces a residual of a set of residuals subject to constraints determined based at least in part on sensor data and tolerances set by the set of noise models and the set of covariances;
- jointly determining a first adjustment to the first noise model and a second adjustment to the second noise model based at least in part on the set of residuals and a hat matrix determined based at least in part on determining the process output;
- determining an updated set of noise models based at least in part on adjusting the set of noise models using the first adjustment and the second adjustment;
- and
- transmitting the updated set of noise models to a vehicle such that the vehicle controls motion of the vehicle based at least in part on the updated set of noise models.
3 more elements
A system comprising:
- one or more processors;
- and
- one or more non-transitory memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising:
- determining a set of noise models comprising a first noise model and a second noise model, wherein the first noise model is based at least in part on first sensor data from a first sensor of a first sensor modality and the second noise model is based at least in part on second sensor data from a second sensor of a second sensor modality;
- determining, based at least in part on the set of noise models and a set of covariances associated with the set of noise models, a process output, wherein determining the process output comprises determining a portion of the process output that reduces a residual of a set of residuals subject to constraints determined based at least in part on sensor data and tolerances set by the set of noise models and the set of covariances;
- jointly determining a first adjustment to the first noise model and a second adjustment to the second noise model based at least in part on the set of residuals and a hat matrix determined based at least in part on determining the process output;
- determining an updated set of noise models based at least in part on adjusting the set of noise models using the first adjustment and the second adjustment;
- and
- transmitting the updated set of noise models to a vehicle such that the vehicle controls motion of the vehicle based at least in part on the updated set of noise models.
6 more elements
A non-transitory computer-readable medium storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:
- determining a set of noise models comprising a first noise model and a second noise model, wherein the first noise model is based at least in part on first sensor data from a first sensor of a first sensor modality and the second noise model is based at least in part on second sensor data from a second sensor of a second sensor modality;
- determining, based at least in part on the set of noise models and a set of covariances associated with the set of noise models, a process output, wherein determining the process output comprises determining a portion of the process output that reduces a residual of a set of residuals subject to constraints determined based at least in part on sensor data and tolerances set by the set of noise models and the set of covariances;
- jointly determining a first adjustment to the first noise model and a second adjustment to the second noise model based at least in part on the set of residuals and a hat matrix determined based at least in part on determining the process output;
- determining an updated set of noise models based at least in part on adjusting the set of noise models using the first adjustment and the second adjustment;
- and
- transmitting the updated set of noise models to a vehicle such that the vehicle controls motion of the vehicle based at least in part on the updated set of noise models.
3 more elements
Dependencies are inferred from the claim text.