Abstract: Aspects of the disclosure relate to conducting pullover maneuvers for autonomous vehicles. For instance, a pullover location may be identified. A pullover start location may be determined for the pullover location. A first distance for the vehicle to come to a complete stop within a pullover deceleration limit may be determined based on a current speed of the vehicle. A second distance between a current location of the vehicle and the pullover start location may be determined. The first distance may be compared to the second distance to assess feasibility of the pullover location. The vehicle may be controlled in order to conduct a pullover maneuver in an autonomous driving mode.

Abstract: The technology relates to autonomous vehicles suffering a breakdown along a roadway. Onboard systems may utilize various proactive operations to alert specific vehicles or other objects on or near the roadway about the breakdown. This can be done alternatively or in addition to turning on the hazard lights or calling for remote assistance. The disabled vehicle is able to detect nearby and approaching objects. The detection may be performed in combination with a determination of the type of object or predicted behavior for that object, enables the vehicle to generate a targeted alert that can be transmitted or otherwise presented to that particular object. This approach provides the other object, such as a vehicle, bicyclist or pedestrian, sufficient time and information about the breakdown to take appropriate corrective action. Different communication options are available and may be selected based on the particular object, environmental conditions and other factors.

Abstract: The disclosure relates to assessing impact of blockages on an autonomous vehicle transportation service. An example method may include identifying a plurality of starting and destination location pairs within a service area; running a first plurality of simulations by determining a first route for each of the plurality of pairs without including a first blockage in the service area; determining a first summary for each determined first route identifying a length of time to complete that determined route; running a second plurality of simulations by determining a second route for each of the plurality of pairs and including the first blockage in the service area; determining a second summary for each determined second route identifying a length of time to complete that determined route; and comparing the determined first summaries with the determined second summaries in order to assess an impact of the first blockage on the service.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating rare pose data. One of the methods includes obtaining a three-dimensional model of a dynamic object, wherein the dynamic object has multiple movable elements that define a plurality of poses of the dynamic object. A plurality of template poses of the dynamic object are used to generate additional poses for the dynamic object including varying angles of one or more key joints of the dynamic object according to the three-dimensional model. Point cloud data is generated for the additional poses generated for the dynamic object.

Abstract: The disclosure relates to testing software for operating an autonomous vehicle. In one instance, a simulation may be run using log data collected by a vehicle operating in an autonomous driving mode. The simulation may be run using the software to control a simulated vehicle and by modifying a characteristic of an agent identified in the log data. During the running of the simulation, that a first type of interaction between the first simulated vehicle and the modified agent will occur may be determined. In response to determining that the particular type of interaction will occur, the modified agent may be replaced by a interactive agent that simulates a road user corresponding to the modified agent that is capable of responding to actions performed by simulated vehicles. That the particular type of interaction between the simulated vehicle and the interactive agent has occurred in the simulation may be determined.

Abstract: The present disclosure is directed to an autonomous vehicle having a vehicle control system. The vehicle control system includes an image processing system. The image processing system receives an image that includes a plurality of image portions. The image processing system also calculates a score for each image portion. The score indicates a level of confidence that a given image portion represents an illuminated component of a traffic light. The image processing system further identifies one or more candidate portions from among the plurality of image portions. Additionally, the image processing system determines that a particular candidate portion represents an illuminated component of a traffic light using a classifier. Further, the image processing system provides instructions to control the autonomous vehicle based on the particular candidate portion representing an illuminated component of a traffic light.

Abstract: Example embodiments relate to beam homogenization for occlusion avoidance. One embodiment includes a light detection and ranging (LIDAR) device. The LIDAR device includes a transmitter and a receiver. The transmitter includes a light emitter. The light emitter emits light that diverges along a fast-axis and a slow-axis. The transmitter also includes a fast-axis collimation (FAC) lens optically coupled to the light emitter. The FAC lens is configured to receive light emitted by the light emitter and reduce a divergence of the received light along the fast-axis of the light emitter to provide reduced-divergence light. The transmitter further includes a transmit lens optically coupled to the FAC lens. The transmit lens is configured to receive the reduced-divergence light from the FAC lens and provide transmit light. The FAC lens is positioned relative to the light emitter such that the reduced-divergence light is expanded at the transmit lens.

Abstract: The present disclosure relates to optical systems, vehicles, and methods that are configured to illuminate and image a wide field of view of an environment. An example optical system includes a camera having an optical axis and an outer lens element disposed along the optical axis. The optical system also includes a plurality of illumination modules, each of which includes at least one light-emitter device configured to emit light along a respective emission axis and a secondary optical element optically coupled to the at least one light-emitter device. The secondary optical element is configured to provide a light emission pattern having an azimuthal angle extent of at least 170 degrees so as to illuminate a portion of an environment of the optical system.

Abstract: Aspects of the disclosure provide systems and methods for providing suggested locations for pick up and destination locations. Pick up locations may include locations where an autonomous vehicle can pick up a passenger, while destination locations may include locations where the vehicle can wait for an additional passenger, stop and wait for a passenger to perform some task and return to the vehicle, or for the vehicle to drop off a passenger. As such, a request for a vehicle may be received from a client computing device. The request may identify a first location. A set of one or more suggested locations may be selected by comparing the predetermined locations to the first location. The set may be provided to the client computing device.

Abstract: Machine-learning models are described detecting the signaling state of a traffic signaling unit. A system can obtain an image of the traffic signaling unit, and select a model of the traffic signaling unit that identifies a position of each traffic lighting element on the unit. First and second neural network inputs are processed with a neural network to generate an estimated signaling state of the traffic signaling unit. The first neural network input can represent the image of the traffic signaling unit, and the second neural network input can represent the model of the traffic signaling unit. Using the estimated signaling state of the traffic signaling unit, the system can inform a driving decision of a vehicle.

Abstract: A rotatable LIDAR device including contactless electrical couplings is disclosed. An example rotatable LIDAR device includes a vehicle electrical coupling including (i) a first conductive ring, (ii) a second conductive ring, and (iii) a first coil. The example rotatable LIDAR device further includes a LIDAR electrical coupling including (i) a third conductive ring, (ii) a fourth conductive ring, and (iii) a second coil. The example rotatable LIDAR device still further includes a rotatable LIDAR electrically coupled to the LIDAR electrical coupling. The first conductive ring and the third conductive ring form a first capacitor configured to transmit communications to the rotatable LIDAR, the second conductive ring and the fourth conductive ring form a second capacitor configured to transmit communications from the rotatable LIDAR, and the first coil and the second coil form a transformer configured to provide power to the rotatable LIDAR.

Abstract: Systems, methods, devices, and techniques for generating object-heading estimations. In one example, methods include actions of receiving sensor data representing measurements of an object that was detected within a proximity of a vehicle; processing the sensor data with one or more preliminary heading estimation subsystems to respectively generate one or more preliminary heading estimations for the object; processing two or more inputs with a second heading estimation subsystem to generate a refined heading estimation for the object, the two or more inputs including the one or more preliminary heading estimations for the object; and providing the refined heading estimation for the object to an external processing system.

Abstract: Some aspects of the subject matter disclosed herein include a system implemented on one or more data processing apparatuses. The system can include an interface configured to obtain, from one or more sensor subsystems, sensor data describing an environment of a vehicle, and to generate, using the sensor data, (i) one or more first neural network inputs representing sensor measurements for a particular object in the environment and (ii) a second neural network input representing sensor measurements for at least a portion of the environment that encompasses the particular object and additional portions of the environment that are not represented by the one or more first neural network inputs; and a convolutional neural network configured to process the second neural network input to generate an output, the output including a plurality of feature vectors that each correspond to a different one a plurality of regions of the environment.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating object predictions using a neural network. One of the methods includes receiving respective projections of a plurality of channels of input sensor data, wherein each channel of input sensor data represents different respective characteristics of electromagnetic radiation reflected off of one or more objects. Each of the projections of the plurality of channels of input sensor data are provided to a neural network subsystem trained to receive projections of input sensor data as input and to provide an object prediction as an output. At the output of the neural network subsystem, an object prediction that predicts a region of space that is likely to be occupied by an object is received.

Abstract: A method and apparatus for controlling a first vehicle autonomously are disclosed. For instance, one or more processors may plan to maneuver the first vehicle to complete an action and predict that a second vehicle will take a particular responsive action. The first vehicle is then maneuvered towards completing the action in a way that would allow the first vehicle to cancel completing the action without causing a collision between the first vehicle and the second vehicle, and in order to indicate to the second vehicle or a driver of the second vehicle that the first vehicle is attempting to complete the action. Thereafter, when the first vehicle is determined to be able to take the action, the action is completed by controlling the first vehicle autonomously according to whether the second vehicle begins to take the particular responsive action.

Abstract: Example embodiments relate to an air cooling system for an electronic spinning assembly. An example embodiment includes a plurality of vanes coupled to a static base. A vane cover is rotatably coupled to the static base. The vane cover at least partially encloses the plurality of vanes. Additionally, the vane cover is coupled to an electronic spinning assembly and configured to rotate with the spinning assembly. The vane cover further includes at least one air inlet configured to act as an air intake for an airflow, at least one air duct extending from the vane cover and configured to direct the airflow, and at least one choke point disposed in the cover. The at least one choke point is configured to increase a pressure of the airflow.

Abstract: Aspects of the disclosure provide for enabling autonomous vehicles to pull over into driveways when picking up or dropping off passengers or goods. For instance, a request for a trip identifying a first location and a second location may be received. The first location may be a location of a client computing device, and the second location may be a starting location or a destination for the trip. A user preference for the trip indicating that a pickup for the trip be in a driveway may be identified. That the first location corresponds with the second location may be identified. Based on the determination that the first location corresponds with the second location, dispatch instructions may be to an autonomous vehicle. The dispatch instructions may identify a polygon for a driveway at the second location in order to cause the autonomous vehicle to pull over into the driveway.

Abstract: The technology relates to controlling a vehicle in an autonomous driving mode. For instance, sensor data identifying an object in an environment of the vehicle may be received. A grid including a plurality of cells may be projected around the object. For each given one of the plurality of cells, a likelihood that the object will enter the given one within a period of time into the future is predicted. A contour is generated based on the predicted likelihoods. The vehicle is then controlled in the autonomous driving mode in order to avoid an area within the contour.