Abstract: A system includes multiple microphone arrays positioned at different locations on a roof of an autonomous vehicle. Each microphone array includes two or more microphones. Internal clocks of each microphone array are synchronized by a processor and used to generate timestamps indicating when microphones capture a sound. Based on the timestamps, the processor is configured to localize a source of the sound.

Abstract: Disclosed herein are neural networks for generating target classifications for an object from a set of input sequences. Each input sequence includes a respective input at each of multiple time steps, and each input sequence corresponds to a different sensing subsystem of multiple sensing subsystems. For each time step in the multiple time steps and for each input sequence in the set of input sequences, a respective feature representation is generated for the input sequence by processing the respective input from the input sequence at the time step using a respective encoder recurrent neural network (RNN) subsystem for the sensing subsystem that corresponds to the input sequence. For each time step in at least a subset of the multiple time steps, the respective feature representations are processed using a classification neural network subsystem to select a respective target classification for the object at the time step.

Abstract: Described examples relate to an apparatus comprising a memory for storing a sequence of image frames and at least one processor. The at least one processor may be configured to receive a first image frame of a sequence of image frames from an image capture device and select a first portion of a first image frame. The at least one processor may also be configured to obtain alignment information and determine a first portion and a second portion of a second image frame based on the alignment information. Further, the at least one processor may be configured to determine a bounding region within the second image frame and fetch image data corresponding to the bounding region of the second image frame from memory. In some examples, the first image frame may comprise a base image and the second image frame may comprise an alternative image frame. Further, the first image frame may comprise any one of the image frames of the sequence of image frames.

Abstract: The present disclosure relates to devices, light detection and ranging (lidar) systems, and vehicles involving solid-state, single photon detectors. An example device includes a substrate defining a primary plane and a plurality of photodetector cells disposed along the primary plane. The plurality of photodetector cells includes at least one large-area cell and at least one small-area cell. The large-area cell has a first area and the small-area cell has a second area and the first area is greater than the second area. The device also includes read out circuitry coupled to the plurality of photodetector cells. The read out circuitry is configured to provide an output signal based on incident light detected by the plurality of photodetector cells.

Abstract: Methods and systems are disclosed for cross-validating a second sensor with a first sensor. Cross-validating the second sensor may include obtaining sensor readings from the first sensor and comparing the sensor readings from the first sensor with sensor readings obtained from the second sensor. In particular, the comparison of the sensor readings may include comparing state information about a vehicle detected by the first sensor and the second sensor. In addition, comparing the sensor readings may include obtaining a first image from the first sensor, obtaining a second image from the second sensor, and then comparing various characteristics of the images. One characteristic that may be compared are object labels applied to the vehicle detected by the first and second sensor. The first and second sensors may be different types of sensors.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating candidate future trajectories for agents. One of the methods includes obtaining scene data characterizing a scene in an environment at a current time point; for each of a plurality of lane segments, processing a model input comprising (i) features of the lane segment and (ii) features of the target agent using a machine learning model that is configured to process the model input to generate a respective score for the lane segment that represents a likelihood that the lane segment will be a first lane segment traversed by the target agent after the current time point; selecting, as a set of seed lane segments, a proper subset of the plurality of lane segments based on the respective scores; and generating a plurality of candidate future trajectories for the target agent.

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: Aspects of the disclosure relate generally to detecting and avoiding blind spots of other vehicles when maneuvering an autonomous vehicle. Blind spots may include both areas adjacent to another vehicle in which the driver of that vehicle would be unable to identify another object as well as areas that a second driver in a second vehicle may be uncomfortable driving. In one example, a computer of the autonomous vehicle may identify objects that may be relevant for blind spot detecting and may determine the blind spots for these other vehicles. The computer may predict the future locations of the autonomous vehicle and the identified vehicles to determine whether the autonomous vehicle would drive in any of the determined blind spots. If so, the autonomous driving system may adjust its speed to avoid or limit the autonomous vehicle's time in any of the blind spots.

Abstract: Aspects of the disclosure relate to detecting and responding to malfunctioning traffic signals for a vehicle having an autonomous driving mode. For instance, information identifying a detected state of a traffic signal for an intersection. An anomaly for the traffic signal may be detected based on the detected state and prestored information about expected states of the traffic signal. The vehicle may be controlled in the autonomous driving mode based on the detected anomaly.

Abstract: One example method of testing an electrical device comprises transmitting a data pattern to a memory device of the electrical device by a controller of the electrical device to provide a written data pattern to the memory device, wherein the data pattern replicates a resonant frequency of at least a portion of the electrical device, reading the written data pattern from the memory device with the controller, and comparing the written data pattern to the data pattern.

Abstract: One example device comprises a plurality of emitters including at least a first emitter and a second emitter. The first emitter emits light that illuminates a first portion of a field-of-view (FOV) of the device. The second emitter emits light that illuminates a second portion of the FOV. The device also comprises a controller that obtains a scan of the FOV. The controller causes each emitter of the plurality of emitters to emit a respective light pulse during an emission time period associated with the scan. The controller causes the first emitter to emit a first-emitter light pulse at a first-emitter time offset from a start time of the emission time period. The controller causes the second emitter to emit a second-emitter light pulse at a second-emitter time offset from the start time of the emission time period.

Abstract: The present disclosure relates to systems and methods relating to the fabrication of light guide elements. An example system includes an optical component configured to direct light emitted by a light source to illuminate a photoresist material at one or more desired angles so as to expose an angled structure in the photoresist material. The photoresist material overlays at least a portion of a first surface of a substrate. The optical component includes a container containing a light-coupling material that is selected based in part on the one or more desired angles. The system also includes a reflective surface arranged to reflect at least a first portion of the emitted light to illuminate the photoresist material at the one or more desired angles.

Abstract: One example system comprises a light source configured to emit light. The system also comprises a waveguide configured to guide the emitted light from a first end of the waveguide toward a second end of the waveguide. The waveguide has an output surface between the first end and the second end. The system also comprises a plurality of mirrors including a first mirror and a second mirror. The first mirror reflects a first portion of the light toward the output surface. The second mirror reflects a second portion of the light toward the output surface. The first portion propagates out of the output surface toward a scene as a first transmitted light beam. The second portion propagates out of the output surface toward the scene as a second transmitted light beam.

Abstract: The technology relates to detection of aberrant driving situations during operation of a vehicle in an autonomous driving mode. Aberrant situations may include potential theft or unsafe conditions, which are determined according to one or more signals. The signals are derived from information detected about the environment around the vehicle, such as from one or more sensors disposed on the vehicle. In response to an aberrant situation, the vehicle may take various corrective action, such as rerouting, locking down the vehicle or communicating with remote assistance. The type of corrective action taken may depend on a type of cargo being transported or whether one or more passengers are in the vehicle. If there are passengers, the system may communicate with the passengers via the passenger's client computing devices or by presenting visual or audible information via a user interface system of the vehicle.

Abstract: The technology relates to detecting and responding to processions. For instance, sensor data identifying two or more objects in an environment of a vehicle may be received. The two or more objects may be determined to be disobeying a predetermined rule in a same way. Based on the determination that the two or more objects are disobeying a predetermined rule, that the two or more objects are involved in a procession may be determined. The vehicle may then be controlled autonomously in order to respond to the procession based on the determination that the two or more objects are involved in a procession.

Abstract: The technology provides a sign detection and classification methodology. A unified pipeline approach incorporates generic sign detection with a robust parallel classification strategy. Sensor information such as camera imagery and lidar depth, intensity and height (elevation) information are applied to a sign detector module. This enables the system to detect the presence of a sign in a vehicle's externa environment. A modular classification approach is applied to the detected sign. This includes selective application of one or more trained machine learning classifiers, as well as a text and symbol detector. Annotations help to tie the classification information together and to address any conflicts with different the outputs from different classifiers. Identification of where the sign is in the vehicle's surrounding environment can provide contextual details.

Abstract: Example embodiments relate to low-overhead, bidirectional error checking for a serial peripheral interface. An example device includes an integrated circuit. The device also includes a serial peripheral interface (SPI) with a Master In Slave Out (MISO) channel and a Master Out Slave In (MOSI) channel. The MOSI channel is configured to receive a write address, payload data, and a forward error-checking code usable to identify data corruption within the write address or the payload data. The integrated circuit is configured to calculate and provide a reverse error-checking code usable to identify data corruption within the write address or the payload data. Additionally, the integrated circuit is configured to compare the forward error-checking code to the reverse error-checking code. Further, the integrated circuit is configured to write, to the write address if the forward error-checking code matches the reverse error-checking code, the payload data.

Abstract: The technology involves pullover maneuvers for vehicles operating in an autonomous driving mode. A vehicle operating in an autonomous driving mode is able to identify parking locations that may be occluded or otherwise not readily visible. A best case estimation for any potential parking locations, including partially or fully occluded areas, is compared against predictions for identified visible parking locations. This can include calculating a cost for each potential parking location and comparing that cost to a baseline cost. Upon determining that an occluded location would provide a more viable option than any visible parking locations, the vehicle is able to initiate a driving adjustment (e.g., slow down) prior to arriving at the occluded location. This enables the vehicle to minimize passenger discomfort while also providing notice to other road users of an intent to pull over.

Abstract: An integrated hybrid rotary assembly is configured to provide power, torque and bi-directional communication to a rotatable sensor, such as a lidar, radar or optical sensor. A common ferrite core is shared by a motor, rotary transformer and radio frequency communication link. This hybrid configuration reduces cost, simplifies the manufacturing process, and can improve system reliability by employing a minimum number of parts. The assembly can be integrated with the sensor unit, which may be used in vehicles and other systems.

Abstract: Described herein is a LIDAR device that may include a transmitter, first and second receivers, and a rotating platform. The transmitter may be configured to emit light having a vertical beam width. The first receiver may be configured to detect light at a first resolution while scanning the environment with a first FOV and the second receiver may be configured to detect light at a second resolution while scanning the environment with a second FOV. In this arrangement, the first resolution may be higher than the second resolution, the first FOV may be at least partially different from the second FOV, and the vertical beam width may encompass at least a vertical extent of the first and second FOVs. Further, the rotating platform may be configured to rotate about an axis such that the transmitter and first and second receivers each move based on the rotation.