Abstract: Porous solid members are provided that include, disposed on at least a portion of the internal surfaces of a plurality of channels thereof, a plurality of superhydrophobic particles. These particles inhibit ingress of water or other aqueous fluids into the internal spaces of the porous solid member, reducing the occurrence of corrosion, biological growth, or other unwanted effects of fluids present in the internal spaces. The porous solid member could be fabricated using 3D printing methods, e.g., the member could be a 3D printed aluminum or other metal(s). The plurality of superhydrophobic particles can be disposed on the internal surfaces of the channels within the porous solid member via a number of processes, e.g., by delivering the particles into the channels while disposed in a payload fluid that later evaporates.

Abstract: A vehicle configured to operate in an autonomous mode may operate a sensor to determine an environment of the vehicle. The sensor may be configured to obtain sensor data of a sensed portion of the environment. The sensed portion may be defined by a sensor parameter. Based on the environment of the vehicle, the vehicle may select at least one parameter value for the at least one sensor parameter such that the sensed portion of the environment corresponds to a region of interest. The vehicle may operate the sensor, using the selected at least one parameter value for the at least one sensor parameter, to obtain sensor data of the region of interest, and control the vehicle in the autonomous mode based on the sensor data of the region of interest.

Abstract: The technology involves communicating the reachability status associated with an autonomous vehicle to a user such as a rider within the vehicle, a person awaiting pickup, or a customer that scheduled a package deliver. Reachability information about pickup and/or drop off locations is presentable via an app on a user device, which helps set expectations with customers about where the vehicle is most likely to be able to perform a pickup and/or drop off. This may include indicating how much variance there may be based on current congestion, parking or idling regulations, or weather conditions. The reachability information may be presented via one or more visualization tools to indicate the uncertainty and/or likely final location. Presenting such contextual information may be done based on real time information, and the presentation may be updated as needed. Historical information about the location may also be used to lower the level of uncertainty.

Abstract: Aspects of the disclosure relate to a method of controlling a vehicle having an autonomous driving mode at a multi-way stop intersection. For instance, that the vehicle has come to a stop at a multi-stop intersection may be determined. At least one road user at the intersection may be identified. Based on the determination that the vehicle has come to the stop, a period of time to wait for the at least one road user to proceed through the intersection may be determined. After waiting the determined period of time, that the at least one road user has not begun to proceed through the intersection may be determined. Based on the determination that the at least one user has not begun to proceed through the intersection, the vehicle may be controlled in the autonomous driving mode in order to proceed through the intersection.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium that generates path prediction data for agents in the vicinity of an autonomous vehicle using machine learning models. One method includes identifying an agent in a vicinity of an autonomous vehicle navigating an environment and determining that the agent is within a vicinity of a crossing zone, which can be marked or unmarked. In response to determining that the agent is within a vicinity of a crossing zone: (i) features of the agent and of the crossing zone can be obtained; (ii) a first input that includes the features can be processed using a first machine learning model that is configured to generate a first crossing prediction that characterizes future crossing behavior of the agent, and (iii) a predicted path for the agent for crossing the roadway can be determined from at least the first crossing prediction.

Abstract: This technology relates to a system for clearing a sensor cover. The system may be comprised of a first sensor that rotates within a sensor cover, a plurality of second sensors that are fixed relative to the sensor cover, a first wiper that is configured to clear the sensor cover of debris, and a motor. The motor may rotate the first wiper in a first direction at a first predetermined rotation rate defined at least in part by a second predetermined rotation rate of the first sensor.

Abstract: An autonomous vehicle includes sensor subsystem(s) that output a sensor signal. A perception subsystem (i) detects an agent in a vicinity of the autonomous vehicle and (ii) generates a motion signal that describes at least one of a past motion or a present motion of the agent. An intention prediction subsystem processes the sensor signal to generate an intention signal that describes at least one intended action of the agent. A behavior prediction subsystem processes the motion signal and the intention signal to generate a behavior prediction signal that describes at least one predicted behavior of the agent. A planner subsystem processes the behavior prediction signal to plan a driving decision for the autonomous vehicle.

Abstract: The disclosure relates to detecting and clearing debris from a sensor window. For instance, a system may include the sensor window and one or more processors. The sensor window may include a transparent thin film conductor. The one or more processors may be configured to identify a change in capacitance using the transparent thin film conductor, detect debris on the sensor window using the change in capacitance, and activate a cleaning system in order to clear the detected debris from the sensor window.

Abstract: Aspects of the present disclosure relate to a vehicle for maneuvering a passenger to a destination autonomously. The vehicle includes one or more computing devices that receive a request for a vehicle from a client computing device. The request identifies a first location. The one or more computing devices also determine whether the first location is within a threshold outside of a service area of the vehicle. When the location is within the threshold distance outside of the service area of the vehicle, the one or more computing devices identify a second location within the service area of the vehicle where the vehicle is able to stop for a passenger and based on the first location. The one or more computing devices then provide a map and a marker identifying the position of the second location on the map for display on the client computing device.

Abstract: A system includes an image sensor having a plurality of pixels that form a plurality of regions of interest (ROIs), and configured to operate at a frame rate higher than a threshold rate. The system also includes an image processing resource. The system further includes control circuitry configured to perform operations that include obtaining, from the image sensor, a full-resolution image of an environment. The full-resolution image contains each respective ROI of the plurality of ROIs. The operations also include selecting a particular ROI based on the full-resolution image, and detecting an object of interest in the particular ROI. The operations include determining a mode of operation by which subsequent image data generated by the particular ROI is to be processed. The operations further include processing, based on the mode of operation and the frame rate, the image data comprising a plurality of ROI images of the object of interest.

Abstract: Aspects and implementations of the present disclosure relate to modeling of positional uncertainty of moving objects using precomputed polygons, for example, for the purposes of computing autonomous vehicle (AV) trajectories. An example method includes: receiving, by a data processing system of an AV, data descriptive of an agent state of an object; generating a polygon representative of the agent state; identifying extreme vertices of the polygon along a longitudinal axis parallel to a heading direction of the object or along a lateral axis orthogonal to the heading direction; and applying, based on the extreme vertices, at least one expansion transformation to the polygon along the longitudinal axis or the lateral axis to generate a precomputed polygon.

Abstract: Examples described may enable provision of remote assistance for an autonomous vehicle. An example method includes a computing system operating in a rewind mode. In the rewind mode, the system may be configured to provide information to a remote assistance operated based on a remote-assistance triggering criteria being met, such as a detected object having a low detection confidence. When the triggering criteria is met, the remote assistance system may provide data from the time leading up to when the remote-assistance triggering criteria was met that was capture of the environment of autonomous vehicle to the remote assistance operator. Based on viewing the data, the remote assistance operator may provide and input to the system that causes a command to be issued to the autonomous vehicle.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a depth map of a scene from a camera image using a neural network. One of the methods includes obtaining an image captured by a first sensor. A neural network processes the image to generate a respective score for each of a plurality of locations in the image. Known depth data specifying respective known depth values for some of the locations in the image is obtained. A depth output is generated that assigns a depth value to some of the locations in the image, including determining whether the score for a location exceeds a threshold; and when the score exceeds the threshold and the known depth value is available for the location, assigning the known depth value for the location to the location in the depth output.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network using contrastive learning. One of the methods includes obtaining a network input representing an environment; processing the network input using a first subnetwork of the neural network to generate a respective embedding for each location in the environment; processing the embeddings for each location in the environment using a second subnetwork of the neural network to generate a respective object prediction for each location; determining, for each of a plurality of pairs of the plurality of locations in the environment, whether the respective object predictions of the pair of locations characterize the same possible object or different possible objects; computing a respective contrastive loss value for each of the plurality of pairs of locations; and updating values for a plurality of parameters of the first subnetwork using the computed contrastive loss values.

Abstract: Aspects of the disclosure relate to generating a speed plan for an autonomous vehicle. As an example, the vehicle is maneuvered in an autonomous driving mode along a route using pre-stored map information. This information identifies a plurality of keep clear regions where the vehicle should not stop but can drive through in the autonomous driving mode. Each keep clear region of the plurality of keep clear regions is associated with a priority value. A subset of the plurality of keep clear regions is identified based on the route. A speed plan for stopping the vehicle is generated based on the priority values associated with the keep clear regions of the subset. The speed plan identifies a location for stopping the vehicle. The speed plan is used to stop the vehicle in the location.

Abstract: Aspects of the disclosure relate to generating map data. For instance, data generated by a perception system of a vehicle may be received. This data corresponds to a plurality of observations including observed positions of a passenger of the vehicle as the passenger approached the vehicle at a first location. The data may be used to determine an observed distance traveled by a passenger to reach a vehicle. A road edge distance between an observed position of an observation of the plurality of observations and a nearest road edge to the observed position may be determined. An inconvenience value for the first location may be determined using the observed distance and the road edge distance. The map data is then generated using the inconvenience value.

Abstract: Example embodiments relate to calibration systems for light detection and ranging (lidar) devices. An example calibration system includes a calibration target that includes a surface having at least one characterized reflectivity. The surface is configured to receive one or more calibration signals emitted by a lidar device along one or more optical axes when the lidar device is separated from the calibration target by an adjustable distance. The calibration system also includes at least one lens that modifies the one or more calibration signals. In addition, the system includes an adjustable attenuator configured to attenuate each of the one or more calibration signals to simulate, in combination with the at least one lens, a distance that is greater than the adjustable distance. Further, the system includes a calibration controller configured to analyze data associated with detected reflections of the one or more calibration signals.

Abstract: Aspects of the disclosure relate generally to detecting discrete actions by traveling vehicles. The features described improve the safety, use, driver experience, and performance of autonomously controlled vehicles by performing a behavior analysis on mobile objects in the vicinity of an autonomous vehicle. Specifically, an autonomous vehicle is capable of detecting and tracking nearby vehicles and is able to determine when these nearby vehicles have performed actions of interest by comparing their tracked movements with map data.

Abstract: Aspects of the disclosure relate generally to detecting discrete actions by traveling vehicles. The features described improve the safety, use, driver experience, and performance of autonomously controlled vehicles by performing a behavior analysis on mobile objects in the vicinity of an autonomous vehicle. Specifically, an autonomous vehicle is capable of detecting and tracking nearby vehicles and is able to determine when these nearby vehicles have performed actions of interest by comparing their tracked movements with map data.