Zoox, Inc.

Derek Adams

Michael Carsten Bosse

Jesse Sol Levinson

Daniel Miller

Brice Rebsamen

Elena Stephanie Stumm

Patrick Blaes

Ryan McMichael

Joseph Patrick Warga

Christopher William Labadie

Daniel Glenn Johnson

Anubhav Thakur

Austin In-Jei Yi

Aleksandrs Ecins

Peter Thomas Mitros

Ashutosh Gajanan Rege

Nitesh Shroff

Bertrand Robert Douillard

Guillermo Duenas Arana

Nathaniel Jon Kaiser

Chengzhi Winston Liu

Ian Baldwin

Veeresh Taranalli

Siddharth Ratapani Navin

Johannes Edren

Francesco Papi

Till Kroeger

David Burdick Berman

Taylor Andrew Arnicar

Eric Andre Senant

Gregory D Kravit

Anne-Claire Elisabeth Marie Le Hénaff

Weihung Ko

Agis Iakovos Mesolongitis

Zakieh Sadat Hashemifar

Yan Cui

Techniques are described herein for determining correction coefficients for steering wheel angles according to a steering component of a vehicle. The techniques comprise redefining the problem of determining the correction into terms of turn angle and crab angle of the vehicle, which both directly depends on leading and trailing steering angles, taking advantage of techniques for estimation of the turn angle based on non-steering parameters/measurements. By redefining the problem, at least one of a scale or bias term for the correction may be calculated to be used in a linear model for estimating a crab angle of the vehicle.

Wheel steering calibration

Techniques for efficiently generating systems are disclosed herein. Abstract system definitions can define the various functions of a system and/or the fitness requirements of the system. Components capable of implementing the aspects of the abstract system can be determined and systems configured to perform the functions of the abstract system are determined. The fitness of these systems can be evaluated to determine whether they meet the fitness requirements of the abstract system. If not, an algorithm is used to iteratively adjust the configurations and components of the systems until the fitness criteria is met.

Computational framework for automatic high assurance system design

Techniques for integrating sensor data into a scene or map based on statistical data of captured environmental data are discussed herein. The data may be stored as a multi-resolution voxel space and the techniques may comprise first applying a pre-alignment or localization technique prior to fully integrating the sensor data.

System for aligning sensor data with maps comprising covariances

Generating a map associated with an environment may include collecting sensor data received from one or more vehicles and generating a set of links to align the sensor data. A mesh representation of the environment may be generated from the aligned sensor data. A system may determine a proposed link to add, a proposed link deletion, and/or a proposed link alteration, and receive a modification comprising instructions to add, delete, or modify a link. Responsive to receiving a modification, the system may re-align a window of sensor data associated with the modification. The modification and/or sensor data associated therewith may be collected as training data for a machine learning model, which may be trained to generate link modification proposals and/or determine sensor data that may be associated with a poor sensor data alignment.

Correction of sensor data alignment and environment mapping

Techniques for a pose component that may determine a pose are described herein. A pose may refer to the inertial pose or position of a vehicle which may be updated in real-time or near real-time. For example, the techniques may include receiving a plurality of input signals at a pose component and monitoring the plurality of input signals. The pose component may determine, based on the monitoring of the plurality of input signals, a particular pose update algorithm of a plurality of pose update algorithms for determining the pose and determine, using the particular pose update algorithm, the pose based the plurality of input signals and IMU measurements associated with a primary IMU.

Pose component

Techniques for determining a probability that a first sensor is miscalibrated with respect a second sensor are discussed herein. For example, a computing device may receive calibrated extrinsics of a camera to a lidar, determine a plurality of sets of perturbed extrinsics based on the calibrated extrinsics, determine respective costs for perturbed extrinsics of the plurality of sets of perturbed extrinsics based on image data captured by the camera, the plurality of sets of perturbed extrinsics, and lidar data captured by the lidar, and determine a local maxima score for the calibrated extrinsics based at least in part on the respective costs for the perturbed extrinsics of the plurality of sets of perturbed extrinsics and a cost of the calibrated extrinsics. The computing device may then determine a probability that the camera is miscalibrated based on a Bayes probability and the local maxima score.

Sensor calibration validation

Techniques for representing a scene or map based on statistical data of captured environmental data are discussed herein. In some cases, the data (such as covariance data, mean data, or the like) may be stored as a multi-resolution voxel space that includes a plurality of semantic layers. In some instances, individual semantic layers may include multiple voxel grids having differing resolutions. Multiple multi-resolution voxel spaces may be merged to generate combined scenes based on detected voxel covariances at one or more resolutions.

Using maps comprising covariances in multi-resolution voxels

Techniques are discussed for modifying map elements associated with map data. Map data can include three-dimensional data (e.g., LIDAR data) representing an environment, while map elements can be associated with the map data to identify locations and semantic information associated with an environment, such as regions that correspond to driving lanes or crosswalks. A trajectory associated with the map data can be updated, such as when aligning one or more trajectories in response to a loop closure, updated calibration, etc. The transformation between a trajectory and an updated trajectory can be applied to map elements to warp the map elements so that they correspond to the updated map data, thereby providing automatic and accurate techniques for updating map elements associated with map data.

Modifying map elements associated with map data

Techniques described herein comprise receiving, from a first measurement system associated with a vehicle, first measurement data taken at a first time and second measurement data taken at a second time, different from the first time. Third measurement data taken at the first time and fourth measurement data taken at the second time is received from a second measurement system associated with the vehicle. A probability is determined that an error has occurred in the vehicle based on the first, second, third and fourth measurement data; and the vehicle is controlled based at least in part on the determined probability.

Error estimation systems and methods

Techniques associated with generating and maintaining sparse geographic and map data. In some cases, the system may maintain a factor graph comprising a plurality of nodes. In some cases, the nodes may comprise pose data and sensor data associated with an autonomous vehicle at the geographic position represented by the node. The nodes may be linked based on shared trajectories and shared sensor data.

System for sparsely representing and storing geographic and map data

Perception sensors of a vehicle can be used for various operating functions of the vehicle. A computing device may receive sensor data from the perception sensors, and may calibrate the perception sensors using the sensor data, to enable effective operation of the vehicle. To calibrate the sensors, the computing device may project the sensor data into a voxel space, and determine a voxel score comprising an occupancy score and a residual value for each voxel. The computing device may then adjust an estimated position and/or orientation of the sensors, and associated sensor data, from at least one perception sensor to minimize the voxel score. The computing device may calibrate the sensor using the adjustments corresponding to the minimized voxel score. Additionally, the computing device may be configured to calculate an error in a position associated with the vehicle by calibrating data corresponding to a same point captured at different times.

Sensor perturbation

A sensor pod system includes one or more sensor pods with a plurality of sensors configured to collect data from an environment. A sensor pod may have an effective field of view created by individual sensors with overlapping fields of view. The sensor pod system may include sensors of different types and modalities. Sensor pods of the sensor pod system may be modularly installed on a vehicle, for example, an autonomous vehicle and collect and provide data of the environment during operation of the vehicle.

Sensor pod assembly

Systems and methods for calibrating multiple inertial measurement units on a system include calibrating a first of the inertial measurement units relative to the system using a first calibration model, and calibrating the remaining inertial measurement unit(s) relative to the first inertial measurement unit using a second calibration model. The calibration of the remaining inertial measurement unit(s) to the first inertial measurement unit can be based on a rigid body model by aligning a rotational velocity of the first inertial measurement unit with a rotational velocity of the remaining inertial measurement unit(s).

Calibrating multiple inertial measurement units

Techniques described are related to determining when a discrepancy between data of multiple sensors (e.g., IMUs) might be attributable to a sensor error, as opposed to operating conditions, such as sensor bias or noise. For example, the sensor data is passed through one or more filters (e.g., bandpass filter) that model the bias or noise, and the filtered data may then be compared for consistency. In some examples, consistency may be based on residuals or some other metric describing discrepancy among the filtered sensor data.

Growing community of inventors

Santa Clara, CA, United States of America

Derek Adams