Abstract: The disclosed technology provides solutions for evaluating sensor calibration algorithms and in particular, for evaluating calibration mechanisms used in autonomous vehicle (AV) deployments. The disclosed technology encompasses a process that includes steps for determining calibration parameters for a sensor mounted to an autonomous vehicle (AV), determining a fault injection offset for at least one of the one or more calibration parameters, and modifying at least one of the one or more calibration parameters based on the fault injection offset. The process may additionally include steps for collecting sensor data from the sensor and evaluating a calibration algorithm associated with the sensor based on the fault injection offset and sensor data. Systems and machine-readable media are also provided.

Abstract: System, methods, and computer-readable media for a calibration check process of sensors on an autonomous vehicle (AV) via a drive-through environment mapped with a series of targets. The targets are used to check the calibration of the sensors on the AV as a quality check before the AV is determined fit to drive autonomously. Supervising a calibration process that collects data from the sensors on the AV based on exposure to a series of targets or augmented camera targets. The collected data may be used for extrinsic calibration aimed to determine that extrinsic parameters that define the rigid relationship between sensors are in set checker bounds.

Abstract: The subject technology is related to autonomous vehicles (AV) and, in particular, to calibration of an sensors of an AV on open roads after calibrating the sensors in an undefined training area. An example method includes calibrating a plurality of sensors of the AV based on performing a plurality of training steps of increasing complexity within the undefined environment, wherein the plurality of sensors of the AV are uncalibrated with respect to each other, determining that the AV satisfies an open road requirement to navigate an open road based on completing the plurality of training steps in the undefined environment, and operating the AV on open roads subject to at least one constraint. The method of claim 1, wherein the at least one constraint comprises a list of prohibited maneuvers that limit operation of the AV on open roads. The constraints are configured to dynamically change.

Abstract: The subject technology is related to autonomous vehicles (AV) and, in particular, to calibrating multiple sensors of an AV in an undefined training area. An example method includes instructing the AV to pilot itself in an undefined training area subject to at least one constraint, wherein the AV is instructed to pilot itself along a path until the AV has overlapped at least a portion of the path, and at a location at which the AV has overlapped at least the portion of the path, determining that first returns from a previous LIDAR scan overlaps with second returns from a subsequent LIDAR scan taken when the AV has overlapped at least the portion of the path. Initially, the AV does not include a location reference to identify locations of objects in the undefined training area and a plurality of sensors of the AV are uncalibrated with respect to each other.

Abstract: The subject disclosure relates to estimating a chassis frame of an autonomous vehicle. A process of the disclosed technology can include receiving a position for each of a plurality of sensors on an autonomous vehicle, determining an ideal chassis point in relation to a constellation of model sensors in a CAD model associated with the autonomous vehicle, generating a constellation of the plurality of sensors based on the positions of the plurality of sensors in relation to the ideal chassis point, minimizing distortion between measured values associated with the constellation of the plurality of sensors and ideal values associated with the constellation of model sensors, determining an estimated real chassis point based on the minimized distortion between the measured values and the ideal values, and calibrating at least one of the plurality of sensors based on the estimated real chassis point.

Abstract: Various aspects of the subject technology relate to a lidar validation system. The lidar validation system is configured to acquire one or more lidar point clouds from a lidar unit, wherein the lidar unit comprises one or more lasers, and wherein each point cloud is a representation of a scene according to a laser in the lidar unit, the scene comprising a fiducial target. The lidar validation system is configured to generate, based on points in the one or more point clouds, a target cloud that correspond to the fiducial target, perform a rigid body processing to minimize a sum of distances from each point in the target cloud to the fiducial target, and generate lidar validation measurements based on the distances from each point in the target cloud to the fiducial target.

Abstract: Methods and systems are provided for performing radar-to-lidar calibration. In some aspects, a process can include steps for receiving, at an autonomous vehicle system, radar data from a radar of an object, receiving, at the autonomous vehicle system, lidar data from a lidar of the object, generating, by the autonomous vehicle system, a plurality of cost functions based on the radar data and the lidar data of the object, and adjusting, by the autonomous vehicle system, at least one setting based on the plurality of cost functions of the radar data and the lidar data of the object.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations. The motorized turntable may confirm that rotation has stopped to the vehicle to trigger sensor capture, and the vehicle may communicate completion of sensor capture at an orientation to the motorized turntable to trigger further rotation.

Abstract: Various aspects of the subject technology relate to a lidar validation system. The lidar validation system is configured to acquire one or more lidar point clouds from a lidar unit, wherein the lidar unit comprises one or more lasers, and wherein each point cloud is a representation of a scene according to a laser in the lidar unit, the scene comprising a fiducial target. The lidar validation system is configured to generate, based on points in the one or more point clouds, a target cloud that correspond to the fiducial target, perform a rigid body processing to minimize a sum of distances from each point in the target cloud to the fiducial target, and generate lidar validation measurements based on the distances from each point in the target cloud to the fiducial target.

Abstract: A sensor calibration target includes dark markings on a light substrate. The dark markings absorb more heat from a heat source than the light substrate, and are visually distinguishable from the light substrate. Thus, the dark markings are discernable by the both a camera and an infrared sensor of a vehicle during vehicle sensor calibration. The sensor calibration target may otherwise non-metallic but include a metallic feature for calibrating a radio detection and ranging (RADAR) sensor. The sensor calibration target may also include one or more apertures in the substrate for calibrating a light detection and ranging (LIDAR) sensor.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations. The motorized turntable may confirm that rotation has stopped to the vehicle to trigger sensor capture, and the vehicle may communicate completion of sensor capture at an orientation to the motorized turntable to trigger further rotation.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations. The motorized turntable may confirm that rotation has stopped to the vehicle to trigger sensor capture, and the vehicle may communicate completion of sensor capture at an orientation to the motorized turntable to trigger further rotation.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each vehicle orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations, for example by comparing these representations to previously stored information about the sensor targets and generating a correction based on differences, the correction applied to post-calibration sensor data.

Abstract: A sensor calibration target includes dark markings on a light substrate. The dark markings absorb more heat from a heat source than the light substrate, and are visually distinguishable from the light substrate. Thus, the dark markings are discernable by the both a camera and an infrared sensor of a vehicle during vehicle sensor calibration. The sensor calibration target may otherwise non-metallic but include a metallic feature for calibrating a radio detection and ranging (RADAR) sensor. The sensor calibration target may also include one or more apertures in the substrate for calibrating a light detection and ranging (LIDAR) sensor.

Abstract: Various aspects of the subject technology relate to a lidar validation system. The lidar validation system is configured to acquire one or more lidar point clouds from a lidar unit, wherein the lidar unit comprises one or more lasers, and wherein each point cloud is a representation of a scene according to a laser in the lidar unit, the scene comprising a fiducial target. The lidar validation system is configured to generate, based on points in the one or more point clouds, a target cloud that correspond to the fiducial target, perform a rigid body processing to minimize a sum of distances from each point in the target cloud to the fiducial target, and generate lidar validation measurements based on the distances from each point in the target cloud to the fiducial target.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each vehicle orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations, for example by comparing these representations to previously stored information about the sensor targets and generating a correction based on differences, the correction applied to post-calibration sensor data.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations. The motorized turntable may confirm that rotation has stopped to the vehicle to trigger sensor capture, and the vehicle may communicate completion of sensor capture at an orientation to the motorized turntable to trigger further rotation.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each vehicle orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations, for example by comparing these representations to previously stored information about the sensor targets and generating a correction based on differences, the correction applied to post-calibration sensor data.

Abstract: Sensors coupled to a vehicle are calibrated using a dynamic scene with sensor targets around a motorized turntable that rotates the vehicle to different orientations. The sensors capture data at each orientation along the rotation. The vehicle's computer identifies representations of the sensor targets within the data captured by the sensors, and calibrates the sensor based on these representations. The motorized turntable may confirm that rotation has stopped to the vehicle to trigger sensor capture, and the vehicle may communicate completion of sensor capture at an orientation to the motorized turntable to trigger further rotation.