Abstract: A method includes obtaining multiple images captured by pixel sensors of an image sensor, analyzing, using neural network circuitry integrated in the image sensor, the multiple images for object detection, generating, for each of the multiple images using the neural network circuitry integrated in the image sensor, neural network output data related to results of the analysis of the multiple images for object detection, and transmitting, from the image sensor, the neural network output data for each of the multiple images and image data for a subset of the multiple images instead of image data of each of the multiple images.

Abstract: Aspects of the disclosure relate to reducing the likelihood of injury to a passenger in a collision. In one example, a system for reducing the likelihood of a passenger submarining, may include a restraining device for restraining the passenger. A second restraining device for further restraining the passenger may also be included in the system. A locking mechanism may be configured to prevent a seat back from reclining when the second restraining device is not activated.

Abstract: Aspects of the disclosure relate to arranging a pickup between a driverless vehicle and a passenger. For instance, dispatch instructions dispatching the vehicle to a predetermined pickup area in order to pick up the passenger are received by the vehicle which begins maneuvering to the predetermined pickup area. While doing so, the vehicle receives from the passenger's client computing device the device's location. An indication that the passenger is interested in a fly-by pickup is identified. The fly-by pickup allows the passenger to safely enter the vehicle at a location outside of the predetermined pickup area and prior to the one or more processors have maneuvered the vehicle to the predetermined pickup area. The vehicle determines that the fly-by pickup is appropriate based on at least the location of the client computing device and the indication, and based on the determination, maneuvers itself in order to attempt the fly-by pickup.

Abstract: Example embodiments relate to identifying defects in optical detector systems based on extent of stray light. An example embodiment includes a method. The method includes capturing, using an optical detector system, an image of a scene that includes a bright object. The method also includes determining a location of the bright object within the image. Further, the method includes determining, based on the location of the bright object within the image, an extent of stray light from the bright object that is represented in the image. In addition, the method includes determining, by comparing the extent of stray light from the bright object that is represented in the image to a predetermined threshold extent of stray light, whether one or more defects are present within the optical detector system. The predetermined threshold extent of stray light corresponds to an expected extent of stray light.

Abstract: Aspects of the disclosure relate to determining a next vehicle task for a vehicle of a fleet. Vehicle data from the vehicle, charger data about at least one charger, and demand data may be received and used to determine the next vehicle task. The vehicle may be directed to the next vehicle task. Determining a next vehicle task may further be based on predictions made using the vehicle data, the charger data, and the demand data. Heuristics may also be used in determining a next vehicle task.

Abstract: In an example method, a vehicle configured to operate in an autonomous mode could have a radar system used to aid in vehicle guidance. The method could include transmitting at least two signal pulses. The method further includes, for each transmitted signal pulse, receiving a reflection signal associated with reflection of the respective transmitted signal pulse. Each reflection signal may be received when the apparatus is in a different respective location. Additionally, the method includes processing the received reflection signals to determine target information relating to one or more targets in an environment of the vehicle. Also, the method includes correlating the target information with at least one object of a predetermined map of the environment of the vehicle to provide correlated target information. Yet further, the method includes storing the correlated target information for the at least one object in an electronic database.

Abstract: The technology relates to detecting and responding to emergency vehicles. This may include using a plurality of microphones to detect a siren noise corresponding to an emergency vehicle and to estimate a bearing of the emergency vehicle. This estimated bearing is compared to map information to identify a portion of roadway on which the emergency vehicle is traveling. In addition, information identifying a set of objects in the vehicle's environment as well as characteristics of those objects is received from a perception system is used to determine whether one of the set of objects corresponds to the emergency vehicle. How to respond to the emergency vehicle is determined based on the estimated bearing and identified road segments and the determination of whether one of the set of objects corresponds to the emergency vehicle. This determined response is then used to control the vehicle in an autonomous driving mode.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing point cloud data using dynamic voxelization. When deployed within an on-board system of a vehicle, processing the point cloud data using dynamic voxelization can be used to make autonomous driving decisions for the vehicle with enhanced accuracy, for example by combining representations of point cloud data characterizing a scene from multiple views of the scene.

Abstract: Example implementations relate to vehicle occupancy confirmation. An example implementation involves receiving, at a computing system from a camera positioned inside a vehicle, an image representing an occupancy within the vehicle. The implementation further involves, responsive to receiving the image, displaying the image on a display interface, and receiving an operator input confirming the occupancy meets a desired occupancy. The implementation additionally includes transmitting an occupancy confirmation from the computing system to the vehicle. In some instances, in response to receiving the occupancy confirmation, the vehicle executes an autonomous driving operation.

Abstract: Aspects of the disclosure relate to assigning a fleet of driverless vehicles to a plurality of parking locations for parking vehicles of the fleet. For instance, locations of the vehicles of the fleet as well as a number of available spaces at each of the plurality of parking location locations may be tracked. A subset of the fleet not already located at one of the plurality of parking locations is identified. At least one assignment assigning each vehicle of the subset to a respective parking location of the plurality of parking locations is determined according to the numbers of available spaces and the identified locations of the subset. For the at least one assignment, a total cost is determined by determining a cost value for each of a plurality of factors. The given assignment is sent to the fleet based on the total cost and the cost value.

Abstract: This disclosure provides systems and methods for routing and topology management of computer networks with steerable beam antennas. A network controller can generate an input graph for a first time period. The input graph can have a plurality of vertices each representing a respective moving node and a plurality of edges each representing a possible link between a pair of moving nodes. The input graph also can include corresponding location information for each of the moving nodes during the first time period. A solver module can receive information corresponding to the input graph, a maximum degree for each vertex in the input graph, and a set of provisioned network flows. The solver module can determine a subgraph representing a network topology based on the input graph, the maximum degree for each vertex in the input graph, and the set of provisioned network flows, such that a number of edges associated with each vertex in the subgraph does not exceed the maximum degree for each vertex.

Abstract: One example system comprises a plurality of substrates disposed in an overlapping arrangement. The plurality of substrates includes at least a first substrate and a second substrate. The system also comprises a first waveguide disposed on the first substrate to define a first optical path on the first substrate. The first waveguide is configured to guide light along the first optical path and to transmit, at an output section of the first waveguide, the light out of the first waveguide toward the second substrate. The system also comprises a second waveguide disposed on the second substrate to define a second optical path on the second substrate. An input section of the second waveguide is aligned with the output section of the first waveguide to receive the light transmitted by the first waveguide. The second waveguide is configured to guide the light along the second optical path.

Abstract: Aspects of the disclosure provide a method of facilitating communications from an autonomous vehicle to a user. For instance, a method may include, while attempting to pick up the user and prior to the user entering an vehicle, inputting a current location of the vehicle and map information into a model in order to identify a type of communication action for communicating a location of the vehicle to the user; enabling a first communication based on the type of the communication action; determining whether the user has responded to the first communication from received sensor data; and enabling a second communication based on the determination of whether the user has responded to the communication.

Abstract: An article including an optically transparent, superomniphobic coating that is durable and relatively easy to keep clean, is disclosed. In one aspect, the present disclosure provides an article comprising a substrate and a graded layer, the graded layer having a first side disposed adjacent the substrate, the first side comprising 45-85 wt. % silicon oxide in a first glass phase and 10-40 wt. % boron oxide in a second glass phase, and opposed the first side, a second side comprising at least 45 wt. % silicon oxide, no more than 5 wt. % boron oxide, and 10-50 wt. % aerogel, the aerogel present in the graded layer as a plurality of distinct domains.

Abstract: Aspects of the disclosure provide systems and methods for confirming the identity of a passenger and changing destination of a vehicle. This may include receiving dispatching instructions to pick up a first passenger at a pickup location and to drop off the first passenger at a first destination as well as authentication information for authenticating a first client computing device of the first passenger. Once the client device is authenticated and a second passenger enters the vehicle, the vehicle is maneuvered towards the first destination. While doing so, a location of the vehicle is compared to location information received from the client computing devices. A notification is sent to a dispatching server based on the comparison and a second destination location is received in response. The vehicle is then maneuvered towards the second destination instead of the first destination.

Abstract: A vehicle having a communication system is disclosed. The system includes two electrical couplings, coupled by way of a rotary joint having a bearing waveguide. Each electrical coupling includes an interface waveguide configured to couple to external signals. Each electrical coupling also includes a waveguide section configured to propagate electromagnetic signals between the interface waveguide and the bearing waveguide of the rotary joint. Additionally, the rotary joint is configured to allow one electrical coupling to rotate with respect to the other electrical coupling. An axis of rotation of the rotary joint is defined by a center of a portion of the waveguides. Yet further, the rotary joint allows electromagnetic energy to propagate between the waveguides of the electrical couplings.

Abstract: Systems and methods for performing operations based on LIDAR communications are described. An example device may include one or more processors and a memory coupled to the one or more processors. The memory includes instructions that, when executed by the one or more processors, cause the device to receive data associated with a modulated optical signal emitted by a transmitter of a first LIDAR device and received by a receiver of a second LIDAR device coupled to a vehicle and the device, generate a rendering of an environment of the vehicle based on information from one or more LIDAR devices coupled to the vehicle, and update the rendering based on the received data. Updating the rendering includes updating an object rendering of an object in the environment of the vehicle. The instructions further cause the device to provide the updated rendering for display on a display coupled to the vehicle.

Abstract: An optical system may include a substrate and a plurality of silicon photomultipliers (SiPMs) monolithically integrated with the substrate. Each SiPM may include a plurality of single photon avalanche diodes (SPADs). The optical system also includes an aperture array having a plurality of apertures. The plurality of SiPMs and the aperture array are aligned so as to define a plurality of receiver channels. Each receiver channel includes a respective SiPM of the plurality of SiPMs optically coupled to a respective aperture of the plurality of apertures.

Abstract: Aspects of the disclosure relate to controlling a vehicle having an autonomous driving mode or an autonomous vehicle. For instance, a polygon representative of the shape and location of a first object may be received. A polyline contour representation of a portion of a polygon representative of the shape and location of a second object may be received. The polyline contour representation may be in half-plane coordinates and including a plurality of vertices and line segments. Coordinates of the polygon representative of the first object may be converted to the half-plane coordinate system. A collision location between the polyline contour representation and the polygon representative of the first object may be determined using the converted coordinates. The autonomous vehicle may be controlled in the autonomous driving mode to avoid a collision based on the collision location.

Abstract: The present disclosure relates to optical systems and methods of their operation. An example optical system includes an optical component and one or more light sources configured to emit a light signal. The light signal interacts with the optical component so as to provide an interaction light signal. The optical system also includes a detector configured to detect at least a portion of the interaction light signal as a detected light signal. The optical system additionally includes a controller configured to carry out operations including causing the one or more light sources to emit the light signal and receiving the detected light signal from the detector. The operations also include determining, based on the detected light signal, that one or more defects are associated with the optical component.