Abstract: Techniques include generating a driving scenario representation based on another driving scenario representation and a modification representation. In examples, a method includes receiving a first driving scenario; receiving a second driving scenario; providing the first driving scenario and the second driving scenario to a first model; receiving, from the first model, a first representation associated with the first driving scenario and a second representation associated with the second driving scenario; determining a modification representation representing a difference measure associated with the first representation and the second representation; training the first model based at least in part on the modification representation; and providing the first model to a second system. The second system may be configured to modify a third driving scenario based at least in part on the first model to determine a fourth driving scenario, and control a vehicle based at least in part the fourth driving scenario.

Abstract: A method comprises (i) obtaining, by a first sensor of a plurality of sensors, first sensor data associated with one or objects in an environment in which one or more vehicles are located, (ii) obtaining, by a second sensor, second sensor data associated with one or more objects, (iii) determining contact metrics associated with the one or more objects associated with the first sensor data and the one or more objects associated with the second sensor data, (iv) determining one or more properties of one or more network connections to a remote system, (v) determining, based at least in part on the contact metrics and the one or more properties, a subset of sensor data to send to the system comprising at least some of the first sensor data and/or at least some of the second sensor data, and (vi) sending the subset of the sensor data to the system.

Abstract: Techniques are discussed for generating, maintaining, and accessing maps to be used for vehicle localization and navigation. A map of a region may include map data representing discrete tiles of the region, and be associated with a map manifest listing pointers to content of the map. In some cases, the map manifest may have a recursive structure which references other map manifests. The map files may be stored on a storage system that avoids duplication and allows efficient determination of changes to content. For example, the stored map files may each be associated with a content-based hash value, which may be incorporated into a filename or URI of the map file. Computing systems on a vehicle may use comparison of the content-based hash values to determine files that have changed and need to be downloaded. The computing systems may also use hash values to determine accuracy of downloaded files.

Abstract: A system and method for selecting a trajectory to traverse comprises receiving a primary trajectory, determining, based at least in part on the primary trajectory, a primary area traversed by the sensor platform in accordance with the primary trajectory and a secondary area traversed by the sensor platform in accordance with a contingent trajectory, and determining, based at least in part on a sensor associated with the sensor platform, that an object is located at least partly within a combined area comprising the primary and secondary area. Upon determining that an object is in the combined area, determining, based at least in part on the object being located at least partly within the combined area, a probability of a collision with the object; and controlling, based at least in part on the determined probability of collision, the sensor platform.

Abstract: Techniques for determining objective map quality and evaluating updated maps against existing maps to determine an operational map for use in controlling a vehicle in an environment are disclosed. A map and map data for an environment may be determined based on collected sensor data. A variety of map quality indicators may be determined based on such data and used to determine an overall quality of the map. The overall quantity for the map may be compared to a current operational map for the environment. The operational map may be replaced with the newer map if the newer map has a higher map quality. Otherwise, the current operational map may be retained. The map quality measurements described herein may also be used to determine whether changes in map generation processes and operations result in improved quality maps.

Abstract: Techniques for enabling a vehicle to navigate around a blocking object, such as double-parked vehicle (“DPV”), are discussed herein. In some examples, a vehicle may receive sensor data representative of an environment. The vehicle may analyze such sensor data to determine that a DPV is located proximate the vehicle. When determining whether to follow the trajectory, the vehicle may determine one or more cost values corresponding to the trajectory. Further, the vehicle may receive weighted heatmap(s) that cover the region proximate the DPV. The vehicle may modify some or all cost values of the trajectory based on the weighted values of the heatmap(s). In some examples, the vehicle may follow the trajectory based at least in part on the cost values.

Abstract: Techniques are discussed herein for training and executing movement and navigation models for controlling autonomous vehicles in simulations and/or in real-world physical environments. In some examples, a model training component may receive object movement data, such as velocities and/or steering angles, from vehicle logs or other ground truth data sources. The movement data may be discretized into labeled bins, and a smoothing function (e.g., a Gaussian quadrature or other weight sum function) centered on the ground truth data may be applied to the labeled bins. During model training, the model outputs can be compared to the smoothed object movement data using a loss function (e.g., a cross-entropy loss function), to reduce the magnitude of the loss penalties for incorrect predictions that are closer to the ground truth data. As a result, models trained using the techniques described herein may provide improved object movement predictions and/or navigation performance for controlling autonomous vehicles.

Abstract: Techniques for enabling operation of a vehicle in one or more different operational states after detecting a fault associated with a component of the vehicle are described herein. A vehicle computing system can monitor components of the vehicle and identify a fault associated with a component. Based on the fault, the vehicle computing system can identify a degraded operational state for the vehicle including one or more limitations or constraints on operation of the vehicle, such as limited speed, acceleration, direction of travel, and/or the like. The vehicle computing system can additionally determine a threshold time period, distance, or range for operating the vehicle in the degraded operational state. The vehicle computing system can cause the vehicle to be controlled according to the limitation(s) or constraint(s) for a time period, distance, or range that is equal to or less than the associated threshold.

Abstract: A method is provided comprising receiving log data associated with a vehicle traversing a real-world environment, and inputting the log data into a search algorithm. A first modified value of a first parameter associated with the log data is received from the search algorithm. The search algorithm determines the first modified value based on a first simulation score associated with occurrence of a first event in a first run of a driving simulation. The first run of the driving simulation includes an autonomous vehicle and is based at least in part on the first modified value of the first parameter. The first modified value of the first parameter is output, and may be used for validating or testing a machine learning model such as a machine learning model for controlling an autonomous vehicle.

Abstract: Techniques for improving scenario determinations for generate testing scenarios for vehicle control system testing are disclosed. A model generates scenario embeddings based on a natural language scenario description. Similar scenarios are identified and/or generated based on similarities between the embeddings for such scenarios and the embeddings determined for the scenario description. The similar scenarios are evaluated for similarity quality and the results of this evaluation are used to adjust the embeddings, embedding determination process, and/or the similarity determination process. This process may be iteratively performed until the system consistently generates and/or identifies sufficiently similar scenarios.

Abstract: A collision avoidance system may validate, reject, or replace a trajectory generated to control a vehicle. The collision avoidance system may comprise a secondary perception component that may receive sensor data, receive and/or determine a corridor associated with operation of a vehicle, classify a portion of the sensor data associated with the corridor as either ground or an object, determine a position and/or velocity of at least the nearest object, determine a threshold distance associated with the vehicle, and control the vehicle based at least in part on the position and/or velocity of the nearest object and the threshold distance.

Abstract: Techniques for reducing latency associated with temporal sensor data processing. The techniques may include determining a region of interest within a field of view of a temporal sensor (e.g., rotating lidar sensor, rolling shutter camera, etc.). Based at least in part on determining the region of interest, an azimuth angle associated with a partial scan of the temporal sensor may be determined such that the region of interest is disposed within the azimuth angle. The techniques may also include receiving sensor data from the temporal sensor and determining whether the sensor data corresponds with the azimuth angle/region of interest. Based at least in part on a determination that the sensor data corresponding with the azimuth angle/region of interest has been received, the sensor data may be processed prior to at least one of receiving additional sensor data or a completion of a full scan by the temporal sensor.

Abstract: Techniques for generating (e.g., creating and/or updating) map data associated with an environment based on sensor data. An example system may determine (e.g., based on the sensor data) and/or receive an indication of a lane boundary associated with a path. The system may determine, based on a set of drivable areas associated with the path, a polygon. The system may determine a representative line associated with the polygon and determine a set of points along the representative line. The system may determine a set of intersections of a set of lines that originate at the set of points and extend laterally from the representative line. The system may determine, based on the set of intersections, a representation of the lane boundary and associate the representation with the map data.

Abstract: Techniques for reducing stray light or glare in sensor data are discussed herein. The sensor data can be captured by a sensor, and the sensor data can be based on laser pulses emitted from emitters associated with a first polarization and received by the sensor associated with a second polarization. A difference between the first polarization and the second polarization can be used to filter out or reduce stray light from the sensor and sensor data. The sensor data can be utilized to determine distance data associated with an object. The sensor data and the first polarization and second polarization can also be utilized to determine characteristics of the object.

Abstract: Techniques are described herein for determining whether multipath reflections are present in a sensed signal associated with a time-of-flight sensor. In various examples, multiple signals may be generated associated with differing wavelengths and exposure times. Such signals may be used to reference a map of values generated from, in some examples, simulations of environments in which multipath reflections are likely. The map, in turn, may provide one or more values associated with one or more distances associated with an object and a multipath reflection. Additionally, an emitted waveform may form the basis of a reference signal for demodulation of the plurality of signals to account for manufacturing, thermal, and other defects. The resultant distances may be used to filter data and remove “bad” pixels to form a resultant depth-image which may be used, for example, to control a vehicle.

Abstract: In order to operate reliably and effectively, an autonomous vehicle may at least partially rely on accurately determining an initial position and orientation of the vehicle within the environment. Without an accurate localization of the vehicle's location, position, and orientation in an environment, the vehicle's perception and/or planning components may be hindered, thereby reducing the effectiveness and/or safety of the vehicle. Techniques of the disclosure herein are related to initializing a localization component of a vehicle.

Abstract: Techniques are disclosed in which sensor data may be received from a sensor associated with a vehicle in an environment. Based at least in part on the sensor data, a set of reachable positions of a first object in the environment in a future time window may be determined. Based at least in part on the set of reachable positions, a first metric may be determined. The first metric may be associated with likelihood of the first object interacting with the vehicle in the future time window. It may be determined, based at least in part on the first metric, to predict a future position of the first object based on a first or a second prediction method. Techniques may determine a trajectory for controlling the vehicle based at least in part on the future position of the first object.

Abstract: Lidar sensor alignment validation may ensure that a relative position and/or orientation of two or more lidar sensors is accurate by determining a sensor alignment error associated with lidar data received from two or more lidar sensors. In some examples, the sensor alignment error may be determined based at least in part on a median angular error and/or median angle determined based at least in part on the lidar data. The median angular error and/or median angle may be determined based at least in part on a first distance from a first lidar point of a first lidar device to a first geometric approximation of a second lidar device's lidar data within a voxel and/or a second distance from a second lidar point of the second lidar device to a second geometric approximation of the first lidar device's lidar data within the voxel.

Abstract: Techniques for engaging and disengaging a vehicle from an autonomous operation mode are described. The techniques include receiving a request to engage or disengage the autonomous mode at a teleoperations system. The request is validated at the teleoperations system using a first set of conditions describing trust in the request and validity of the request. The request is then sent, if valid, to the vehicle where a second validation is performed using a second set of conditions describing the conditions or states of the vehicle. If the second conditions are valid then the request is performed and the vehicle engages or disengages from autonomous mode.