Abstract: A method performed by one or more computers, the method comprising: obtaining scene context data characterizing a scene in an environment at a current time point, wherein the scene context data includes features of the scene in a scene-centric coordinate system; generating a scene-centric encoded representation of the scene in the environment by processing the scene context data using an encoder neural network; for each target agent: obtaining agent-specific features for the target agent, processing the agent-specific features for the target agent and the scene-centric encoded representation of the scene using a fusion neural network to generate a fused scene representation for the target agent, and processing the fused scene representation for the target agent using a decoder neural network to generate a trajectory prediction output for the target agent in an agent-centric coordinate system for the target agent.

Abstract: 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.

Abstract: 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.

Abstract: Techniques for determining a prediction probability associated with a disengagement event are discussed herein. A first prediction probability can include a probability that a safety driver associated with a vehicle (such as an autonomous vehicle) may assume control over the vehicle. A second prediction probability can include a probability that an object in an environment is associated the disengagement event. Sensor data can be captured and represented as a top-down representation of the environment. The top-down representation can be input to a machine learned model trained to output prediction probabilities associated with a disengagement event. The vehicle can be controlled based the prediction probability and/or the interacting object probability.

Abstract: A LIDAR system includes a laser emitter configured to emit a laser pulse in a sample direction of a sample area of a scene. A sensor element of the LIDAR system is configured to sense a return pulse, which is a reflection from the sample area corresponding to the emitted laser pulse. The LIDAR system may compare a width of the emitted laser pulse to a width of the return pulse in the time-domain. The comparison of the width of the emitted pulse to the width of the return pulse may be used to determine an orientation or surface normal of the sample area relative to the sample direction. Such a comparison leads to a measurement of the change of pulse width, referred to as pulse broadening or pulse stretching, from the emitted pulse to the return pulse.

Abstract: Systems, methods, and apparatuses described herein are directed to performing segmentation on voxels representing three-dimensional data to identify static and dynamic objects. LIDAR data may be captured by a perception system for an autonomous vehicle and represented in a voxel space. Operations may include determining a drivable surface by parsing individual voxels to determine an orientation of a surface normal of a planar approximation of the voxelized data relative to a reference direction. Clustering techniques can be used to grow a ground plane including a plurality of locally flat voxels. Ground plane data can be set aside from the voxel space, and the remaining voxels can be clustered to determine objects. Voxel data can be analyzed over time to determine dynamic objects. Segmentation information associated with ground voxels, static object, and dynamic objects can be provided to a tracker and/or planner in conjunction with operating the autonomous vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training trajectory prediction neural networks using distillation.

Abstract: Multi-dimensional data can be mapped to a projection shape and converted for image analysis. In some examples, the multi-dimensional data may include data captured by a LIDAR system for use in conjunction with a perception system for an autonomous vehicle. Converting operations can include converting three-dimensional LIDAR data to multi-channel two-dimensional data. Data points of the multi-dimensional data can be mapped to a projection shape, such as a sphere. Characteristics of the projection shape may include a shape, a field of view, a resolution, and a projection type. After data is mapped to the projection shape, the projection shape can be converted to a multi-channel, two-dimensional image. Image segmentation and classification may be performed on the two-dimensional data. Further, segmentation information may be used to segment the three-dimensional LIDAR data, while a rendering plane may be positioned relative to the segmented data to perform classification on a per-object basis.

Abstract: 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.

Abstract: 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 including 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.

Abstract: Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. In particular, a method may include receiving an indication of a sensor anomaly, determining one or more sensor recovery strategies based on the sensor anomaly, and executing a course of action that ensures the autonomous vehicle system operates within accepted parameters. Alternative sensors may be relied upon to cover for the sensor anomaly, which may include a failed sensor while the autonomous vehicle is in operation.

Abstract: 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.

Abstract: Various embodiments relate generally to autonomous vehicles and associated mechanical, electrical and electronic hardware, computer software and systems, and wired and wireless network communications to provide an autonomous vehicle fleet as a service. In particular, a method may include receiving data associated with a sensor measurement of a perceived object, determining a label associated with the perceived object based on an initial calibration, retrieving log file data associated with the label, determining a calibration parameter associated with the sensor measurement based on the retrieved log file data, and storing the calibration parameter in association with a sensor associated with the sensor measurement. Sensors may be calibrated on the fly while the autonomous vehicle is in operation using one or more other sensors and/or fused data from multiple types of sensors.

Abstract: Multi-dimensional data can be mapped to a projection shape and converted for image analysis. In some examples, the multi-dimensional data may include data captured by a LIDAR system for use in conjunction with a perception system for an autonomous vehicle. Converting operations can include converting three-dimensional LIDAR data to multi-channel two-dimensional data. Data points of the multi-dimensional data can be mapped to a projection shape, such as a sphere. Characteristics of the projection shape may include a shape, a field of view, a resolution, and a projection type. After data is mapped to the projection shape, the projection shape can be converted to a multi-channel, two-dimensional image. Image segmentation and classification may be performed on the two-dimensional data. Further, segmentation information may be used to segment the three-dimensional LIDAR data, while a rendering plane may be positioned relative to the segmented data to perform classification on a per-object basis.

Abstract: A LIDAR system includes a laser emitter configured to emit a laser pulse in a sample direction of a sample area of a scene. A sensor element of the LIDAR system is configured to sense a return pulse, which is a reflection from the sample area corresponding to the emitted laser pulse. The LIDAR system may compare a width of the emitted laser pulse to a width of the return pulse in the time-domain. The comparison of the width of the emitted pulse to the width of the return pulse may be used to determine an orientation or surface normal of the sample area relative to the sample direction. Such a comparison leads to a measurement of the change of pulse width, referred to as pulse broadening or pulse stretching, from the emitted pulse to the return pulse.

Abstract: Multi-dimensional data can be mapped to a projection shape and converted for image analysis. In some examples, the multi-dimensional data may include data captured by a LIDAR system for use in conjunction with a perception system for an autonomous vehicle. Converting operations can include converting three-dimensional LIDAR data to multi-channel two-dimensional data. Data points of the multi-dimensional data can be mapped to a projection shape, such as a sphere. Characteristics of the projection shape may include a shape, a field of view, a resolution, and a projection type. After data is mapped to the projection shape, the projection shape can be converted to a multi-channel, two-dimensional image. Image segmentation and classification may be performed on the two-dimensional data. Further, segmentation information may be used to segment the three-dimensional LIDAR data, while a rendering plane may be positioned relative to the segmented data to perform classification on a per-object basis.

Abstract: A LIDAR system includes a laser emitter configured to emit a laser pulse in a sample direction of a sample area of a scene. A sensor element of the LIDAR system is configured to sense a return pulse, which is a reflection from the sample area corresponding to the emitted laser pulse. The LIDAR system may compare a width of the emitted laser pulse to a width of the return pulse in the time-domain. The comparison of the width of the emitted pulse to the width of the return pulse may be used to determine an orientation or surface normal of the sample area relative to the sample direction. Such a comparison leads to a measurement of the change of pulse width, referred to as pulse broadening or pulse stretching, from the emitted pulse to the return pulse.

Abstract: Systems, methods, and apparatuses described herein are directed to performing segmentation on voxels representing three-dimensional data to identify static and dynamic objects. LIDAR data may be captured by a perception system for an autonomous vehicle and represented in a voxel space. Operations may include determining a drivable surface by parsing individual voxels to determine an orientation of a surface normal of a planar approximation of the voxelized data relative to a reference direction. Clustering techniques can be used to grow a ground plane including a plurality of locally flat voxels. Ground plane data can be set aside from the voxel space, and the remaining voxels can be clustered to determine objects. Voxel data can be analyzed over time to determine dynamic objects. Segmentation information associated with ground voxels, static object, and dynamic objects can be provided to a tracker and/or planner in conjunction with operating the autonomous vehicle.

Abstract: Multi-dimensional data can be mapped to a projection shape and converted for image analysis. In some examples, the multi-dimensional data may include data captured by a LIDAR system for use in conjunction with a perception system for an autonomous vehicle. Converting operations can include converting three-dimensional LIDAR data to multi-channel two-dimensional data. Data points of the multi-dimensional data can be mapped to a projection shape, such as a sphere. Characteristics of the projection shape may include a shape, a field of view, a resolution, and a projection type. After data is mapped to the projection shape, the projection shape can be converted to a multi-channel, two-dimensional image. Image segmentation and classification may be performed on the two-dimensional data. Further, segmentation information may be used to segment the three-dimensional LIDAR data, while a rendering plane may be positioned relative to the segmented data to perform classification on a per-object basis.

Abstract: Systems, methods, and apparatuses described herein are directed to performing segmentation on voxels representing three-dimensional data to identify static and dynamic objects. LIDAR data may be captured by a perception system for an autonomous vehicle and represented in a voxel space. Operations may include determining a drivable surface by parsing individual voxels to determine an orientation of a surface normal of a planar approximation of the voxelized data relative to a reference direction. Clustering techniques can be used to grow a ground plane including a plurality of locally flat voxels. Ground plane data can be set aside from the voxel space, and the remaining voxels can be clustered to determine objects. Voxel data can be analyzed over time to determine dynamic objects. Segmentation information associated with ground voxels, static object, and dynamic objects can be provided to a tracker and/or planner in conjunction with operating the autonomous vehicle.