Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating object interaction predictions using a neural network. One of the methods includes obtaining a sensor input derived from data generated by one or more sensors that characterizes a scene. The sensor input is provided to an object interaction neural network. The object interaction neural network is configured to process the sensor input to generate a plurality of object interaction outputs. Each respective object interaction output includes main object information and interacting object information. The respective object interaction outputs corresponding to the plurality of regions in the sensor input are received as output of the object interaction neural network.

Abstract: Systems and methods can align of one or more optical beams with respect to one another, an optical axis, a far-field location, and/or a near-field location. An example method includes coupling, with an index-matched epoxy, a plurality of adjustable optical surfaces and an optical element. Each adjustable optical surface of the plurality of adjustable optical surfaces is associated with a respective light-emitter device of a plurality of light-emitter devices. Additionally, the method includes causing at least one light-emitter device to emit light that interacts with at least one adjustable optical surface and an optical element to provide a transmitted light beam. The method also includes receiving information about a beam profile of the transmitted light beam, comparing the beam profile to a desired beam profile, and adjusting a position of the at least one adjustable optical surface with respect to the optical element based on the comparison.

Abstract: A image sensor includes a first integrated circuit layer including pixel sensors that are grouped based on position into pixel sensor groups, a second integrated circuit layer in electrical communication with the first integrated circuit layer, the second integrated circuit layer including image processing circuitry groups that are configured to each receive pixel information from a corresponding pixel sensor group, the image processing circuitry groups further configured to perform image processing operations on the pixel information to provide processed pixel information during operation of the image sensor, a third integrated circuit layer in electrical communication with the second integrated circuit layer, and the third integrated circuit layer including neural network circuitry groups that are configured to each receive the processed pixel information from a corresponding image processing circuitry group and perform analysis for object detection on the processed pixel information during operation of the

Abstract: A method and system are provided for controlling braking a vehicle in an autonomous driving mode. For instance, the vehicle is controlled in the autonomous driving mode according to a first braking control mode using a first model to adjust the position of a vehicle relative to an expected position of a current trajectory of the vehicle. Using a second model how close to a maximum deviation threshold the vehicle would come if a maximum braking strength for the vehicle was applied is predicted. The maximum deviation threshold provides an allowed forward deviation from the current trajectory. Based on the prediction, the vehicle is controlled in the autonomous driving mode according to a second braking control mode by automatically applying the maximum braking strength.

Abstract: Because of the nature of autonomous vehicles, and in particular that they do not require manual inputs from a driver or passenger to control braking and steering, autonomous vehicle can include features that may not necessarily be useful or practical in a typical non-autonomous (or semi-autonomous vehicle) that would require such manual input.

Abstract: One example method involves obtaining a plurality of images using a camera located at a given position relative to a light detection and ranging device (LIDAR). A first image of the plurality may be indicative of a view, via one or more optical elements of the LIDAR, of a receiver of the LIDAR. The method also involves determining simulated detector positions for intercepting reflections of simulated light beams associated with a plurality of light sources in a transmitter of the LIDAR. The method also involves determining one or more alignment offsets between the transmitter and the receiver based on at least the simulated detector positions and the plurality of images.

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: 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: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying high-priority agents in the vicinity of a vehicle. In one aspect, a method comprises processing an input that characterizes a trajectory of the vehicle in an environment using an importance scoring model to generate an output that defines a respective importance score for each of a plurality of agents in the environment in the vicinity of the vehicle. The importance score for an agent characterizes an estimated impact of the agent on planning decisions generated by a planning system of the vehicle which plans a future trajectory of the vehicle. The high-priority agents are identified as a proper subset of the plurality of agents with the highest importance scores.

Abstract: A light detection and ranging (LIDAR) system can emit light toward an environment and detect responsively reflected light to determine a distance to one or more points in the environment. The reflected light can be detected by a plurality of plurality of photodiodes that are reverse-biased using a high voltage. Signals from the plurality of reverse-biased photodiodes can be amplified by respective transistors and applied to an analog-to-digital converter (ADC). The signal from a particular photodiode can be applied to the ADC by biasing a respective transistor corresponding to the particular photodiode while not biasing transistors corresponding to other photodiodes. The gain of each photodiode/transistor pair can be controlled by adjusting the bias voltage applied to each photodiode using a digital-to-analog converter. The gain of each photodiode/transistor pair can be controlled based on the detected temperature of each photodiode.

Abstract: An autonomous vehicle may include a stuck condition detection component and a communications component. The stuck-detection component may be configured to detect a condition in which the autonomous vehicle is impeded from navigating according to a first trajectory. The communications component may send an assistance signal to an assistance center and receive a response to the assistance signal. The assistance signal may include sensor information from the autonomous vehicle. The assistance center may include a communications component and a trajectory specification component. The communications component may receive the assistance signal and send a corresponding response. The trajectory specification component may specify a second trajectory for the autonomous vehicle and generate the corresponding response that includes a representation of the second trajectory. The second trajectory may be based on the first trajectory and may ignore an object that obstructs the first trajectory.

Abstract: An antenna includes a plurality of waveguide antenna elements arranged in a first array configured to operate with a first polarization. The antenna also includes a plurality of waveguide output ports arranged in a second array configured to operate with a second polarization. The second polarization is different from the first polarization. The antenna further includes a polarization-modification layer with channels defined therein. The polarization-modification layer is disposed between the waveguide antenna elements and the waveguide output ports. The channels are oriented at a first angle with respect to the waveguide antenna elements and at a second angle with respect to the waveguide output ports. The channels are configured to receive input electromagnetic waves having the first polarization and transmit output electromagnetic waves having a first intermediate polarization.

Abstract: Aspects of the disclosure relate to vehicles capable of autonomous driving. These vehicles may include seats for accommodating different numbers of passengers. In some cases, the seats may be reconfigurable. For instance, a vehicle may include a first row of seating having a first, passenger use configuration. The first row may allow a passenger to sit in a seat of the first row of seating and access user input controls for the vehicle. The first row of seating may also have a second, folded configuration where the first row is in a folded configuration and no longer usable for passenger seating. The vehicle may also have a second row of seating. When the first row of seating is in the second, folded configuration, the second row of seating may still be usable for seating and may include additional legroom for the passenger as compared to when the first row of seating is in the first passenger use configuration.

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: The present disclosure relates to methods and systems that improve the dynamic range of LIDAR systems. An example system includes a plurality of single-photon photodetectors and at least one additional photodetector monolithically integrated on a shared substrate. The plurality of single-photon photodetectors and the at least one additional photodetector are configured to detect light from a shared field of view. The system also includes a controller configured to carry out operations. The operations include: receiving respective photodetector signals from the plurality of single-photon photodetectors and the at least one additional photodetector; selecting a photodetector signal from at least two of: the two received photodetector signals and a combined photodetector signal formed by combining the two received photodetector signals; and determining an intensity of light in the field of view based on the selected photodetector signal.

Abstract: Example systems and methods enable an autonomous vehicle to request assistance from a remote operator in certain predetermined situations. One example method includes determining a representation of an environment of an autonomous vehicle based on sensor data of the environment. Based on the representation, the method may also include identifying a situation from a predetermined set of situations for which the autonomous vehicle will request remote assistance. The method may further include sending a request for assistance to a remote assistor, the request including the representation of the environment and the identified situation. The method may additionally include receiving a response from the remote assistor indicating an autonomous operation. The method may also include causing the autonomous vehicle to perform the autonomous operation.

Abstract: A method is provided for managing and tracking scouting tasks to obtain map information using a fleet of autonomous vehicles. For instance, the method includes defining a scouting quest to obtain the map information. The scouting quest includes a plurality of objectives. Each objective is associated with a geographic location from which sensor data is to be captured. The method also includes receiving a first update message from an autonomous vehicle of the fleet. The update message identifies a location of the autonomous vehicle. The method also includes assigning at least one of the objectives to the autonomous vehicle based on the location of the autonomous vehicle. The method also includes, sending instructions to the autonomous vehicle in order to cause the autonomous vehicle to complete the at least one objective and after sending, tracking a status of the scouting quest.

Abstract: Aspects of the disclosure relate generally to speed control in an autonomous vehicle. For example, an autonomous vehicle may include a user interface which allows the driver to input speed preferences. These preferences may include the maximum speed above the speed limit the user would like the autonomous vehicle to drive when other vehicles are present and driving above or below certain speeds. The other vehicles may be in adjacent or the same lane the vehicle, and need not be in front of the vehicle.

Abstract: The technology provides an interior camera sensing system for self-driving vehicles. The sensor system includes image sensors and infrared illuminators to see the vehicle's cabin and storage areas in all ambient lighting conditions. The system can monitor the vehicle for safety purposes, to detect the cleanliness of the cabin and storage areas, as well as to detect whether packages or other objects have been inadvertently left in the vehicle. The cameras are arranged to focus on selected regions in the vehicle cabin and the system carries out certain actions in response to information evaluated for those regions. The interior space is divided into multiple zones assigned different coverage priorities. Regardless of vehicle size or configuration, certain actions are performed according to various ride checklists and the imagery detected by the interior cameras. The checklists include pre-ride, mid-ride, and post-ride checklists.

Abstract: The present application describes a method including transmitting at least two radar signals by a radar unit of a vehicle, where a first signal is transmitted from a first location and a second signal is transmitted from a second location. The method also includes receiving a respective reflection signal associated with each of the transmitted signals. Additionally, the method includes determining, by a processor, at least one stationary object that caused a reflection. Further, the method includes based on the determined stationary object, determining, by the processor, an offset for the radar unit. The method yet further includes operating the radar unit based on the determined offset. Furthermore, the method includes controlling an autonomous vehicle based on the radar unit being operated with the determined offset.