Abstract: Aspects of the disclosure provide for controlling an autonomous vehicle. For instance, a first probability distribution may be generated for the vehicle at a first future point in time using a generative model for predicting expected behaviors of objects and a set of characteristics for the vehicle at an initial time expected to be perceived by an observer. Planning system software of the vehicle may be used to generate a trajectory for the vehicle to follow. A second probability distribution may be generated for a second future point in time using the generative model based on the trajectory and a set of characteristics for the vehicle at the first future point expected to be perceived by the observer. A surprise assessment may be generated by comparing the first probability distribution to the second probability distribution. The vehicle may be controlled based on the surprise assessment.

Abstract: A display console comprises a housing comprising a front panel, a light source disposed within the housing, a port positioned within an aperture of the front panel, and a diffuser. The diffuser comprises a first portion proximate the port and a second portion proximate the light source such that the diffuser diffuses light from the light source out the aperture of the front panel, wherein the second portion includes a flange.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data representing a sensor measurement of a scene captured by one or more sensors to generate an object detection output that identifies locations of one or more objects in the scene. When deployed within an on-board system of a vehicle, the object detection output that is generated can be used to make autonomous driving decisions for the vehicle with enhanced accuracy.

Abstract: The disclosure relates to smart signs or physical markers for facilitating passenger trips for autonomous vehicles. For instance, a physical marker remote from the autonomous vehicles may receive a first notification indicating a request for a trip has been made via a client computing device. The physical marker may determine when the client computing device has reached a physical marker, and in response to the determination, the physical marker may send a second notification to a dispatching server computing device indicating that the client computing device has reached a physical marker. Other aspects of the disclosure relate to various features and uses for the physical marker.

Abstract: A vehicle may receive one or more images of an environment of the vehicle. The vehicle may also receive a map of the environment. The vehicle may also match at least one feature in the one or more images with corresponding one or more features in the map. The vehicle may also identify a given area in the one or more images that corresponds to a portion of the map that is within a threshold distance to the one or more features. The vehicle may also compress the one or more images to include a lower amount of details in areas of the one or more images other than the given area. The vehicle may also provide the compressed images to a remote system, and responsively receive operation instructions from the remote system.

Abstract: A composition that is easily applied, clear, well-bonded, and superhydrophobic is disclosed. In one aspect, the composition includes a hydrophobic fluorinated solvent, a binder comprising a hydrophobic fluorinated polymer, and hydrophobic fumed silica nanoparticles. Also disclosed is a structure including a substrate coated with the composition, as well as a method for making the composition and a method of coating a substrate with the composition.

Abstract: A method is provided that includes a method is provided that includes transmitting a radar signal by a radar system. The method also includes receiving reflections of the radar signal from an environment by the radar system. Additionally, the method includes receiving a location of a plurality of objects in the environment by a radar processing system. The method further includes tracking a plurality of reflecting objects in the environment based on the received reflections by the radar processing system. Yet further, the method includes determining, by the radar processing system, that a received radar reflection corresponds to one of the plurality objects in the environment having an incorrect location. Moreover, the method includes revising a tracking for the one of the plurality objects in the environment having an incorrect location.

Abstract: An example method includes making a first determination that a load of a cooling system of a vehicle is expected to increase and become greater than a capacity of the cooling system; operating, in response to making the first determination, the vehicle in a first mode where a combustion engine and an electric motor operate such that a charge level of a power supply of the vehicle increases or is maintained above a threshold charge level; making, after operating the vehicle in the first mode, a second determination that the load of the cooling system has become greater than the capacity of the cooling system; and operating, in response to making the second determination, the vehicle in a second mode where the combustion engine and the electric motor operate such that the charge level of the power supply decreases or is maintained below the threshold charge level.

Abstract: A method is provided that includes receiving reflections of a plurality of radar signals from an environment by a radar system. The method also includes determining, by a radar processing system, that two received radar reflections correspond to an object in the environment based on a location of the object, where at least one of the two received radar reflections had a reflection in the environment off of a secondary reflecting object. The method further includes revising a tracking for the object.

Abstract: An autonomous vehicle configured for active sensing may also be configured to weigh expected information gains from active-sensing actions against risk costs associated with the active-sensing actions. An example method involves: (a) receiving information from one or more sensors of an autonomous vehicle, (b) determining a risk-cost framework that indicates risk costs across a range of degrees to which an active-sensing action can be performed, wherein the active-sensing action comprises an action that is performable by the autonomous vehicle to potentially improve the information upon which at least one of the control processes for the autonomous vehicle is based, (c) determining an information-improvement expectation framework across the range of degrees to which the active-sensing action can be performed, and (d) applying the risk-cost framework and the information-improvement expectation framework to determine a degree to which the active-sensing action should be performed.

Abstract: Techniques for braking an autonomous vehicle include providing a pressurized fluid stream from a plurality of pressurized fluid sources to a plurality of pressure-controlled electronic braking assemblies; providing the pressurized fluid stream from a pressurized fluid control output of a first pressure-controlled electronic braking assembly directly to a pressurized fluid control input of a second pressure-controlled electronic braking assembly; providing the pressurized fluid stream from the second pressure-controlled electronic braking assembly to at least one vehicle brake set; providing sensor output data from one or more vehicle sensors to a plurality of electronic control units; and based at least in part on the sensor output data, controlling at least one of the first or second pressure-controlled electronic braking assemblies to adjust a pressure of the pressurized fluid stream from at least one of the first or second pressure-controlled electronic braking assemblies to the vehicle brake set.

Abstract: The technology involves determining a minimum lateral gap distance between a vehicle configured for autonomous driving and one or more other objects in the vehicle's environment. The minimum lateral gap is used when determining whether to have a driver take over control of certain driving operations. This provides a measure of safety during disengagements or other change of control events. Determining the minimum lateral gap includes calculating a budgeted distance based on a cross-track error for a lateral position of the vehicle, an allowed actual gap distance to an object in the vehicle's environment, and a perception error associated with a location of the object in the vehicle's environment. This determination can be done for a set of possible operating speeds and steering rate limit combinations. The vehicle's control system may notify the driver to take control, for instance with audible, visual and/or haptic notifications.

Abstract: A system may include a first sensor of a first type and a second sensor of a second different type and having a detector. A field of view of the second sensor may be formed by a plurality of regions of interest (ROIs) defined by the detector. Control circuitry of the system may be configured to perform operations including obtaining, from the first sensor, first sensor data representing an environment, and determining, based on the first sensor data, information associated with a feature of interest within the environment. The operations may also include determining, based on the information, a particular ROI that corresponds to an expected position of the feature at a later time, obtaining a plurality of ROI sensor data from the particular ROI instead of obtaining full-resolution sensor data, and analyzing the plurality of ROI sensor data to determine one or more attributes of the feature.

Abstract: Aspects of the present disclosure relate to context aware stopping of a vehicle without a driver. As an example, after a passenger has entered the vehicle, the vehicle is maneuvered by one or more processors in an autonomous driving mode towards a destination location along a route. The route is divided into two or more stages. A signal is received by the one or more processors. The signal indicates that the passenger is requesting that the vehicle stop or pull over. In response to the signal, the one or more processors determine a current stage of the route based on a current distance of the vehicle from a pickup location where the passenger entered the vehicle or a current distance of the vehicle from the destination location. The one or more processors then stop the vehicle in accordance with the determined current stage.

Abstract: Systems and methods described herein relate to the manufacture of optical elements and optical systems. An example method includes overlaying a first mask on a photoresist material and a substrate, and causing a light source to illuminate the photoresist material through the first mask during a first exposure so as to define a first feature. During the first exposure, the light source is positioned at a non-normal angle with respect to a plane parallel to the substrate. The method includes developing the photoresist material so as to retain an elongate portion of the photoresist material on the substrate. A first end of the elongate portion includes an angled portion that is sloped at an angle with respect to a long axis of the elongate portion. The method also includes depositing a reflective material through a second mask onto the angled portion.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for the generation and use of a surfel map with semantic labels. One of the methods includes receiving a surfel map that includes a plurality of surfels, wherein each surfel has associated data that includes one or more semantic labels; obtaining sensor data for one or more locations in the environment, the sensor data having been captured by one or more sensors of a first vehicle; determining one or more surfels corresponding to the one or more locations of the obtained sensor data; identifying one or more semantic labels for the one or more surfels corresponding to the one or more locations of the obtained sensor data; and performing, for each surfel corresponding to the one or more locations of the obtained sensor data, a label-specific detection process for the surfel.

Abstract: A computing system may operate a LIDAR device to emit and detect light pulses in accordance with a time sequence including standard detection period(s) that establish a nominal detection range for the LIDAR device and extended detection period(s) having durations longer than those of the standard detection period(s). The system may then make a determination that the LIDAR detected return light pulse(s) during extended detection period(s) that correspond to particular emitted light pulse(s). Responsively, the computing system may determine that the detected return light pulse(s) have detection times relative to corresponding emission times of particular emitted light pulse(s) that are indicative of one or more ranges. Given this, the computing system may make a further determination of whether or not the one or more ranges indicate that an object is positioned outside of the nominal detection range, and may then engage in object detection in accordance with the further determination.