Abstract: Aspects of the disclosure provide for generation of trajectories for a vehicle driving in an autonomous driving mode. In one instance, a default number of trajectories to be generated may be identified. A set of maneuvering options may be selected from a set of predetermined maneuvering options based on the number of trajectories. The set of maneuvering options may be filtered based on the default number of trajectories. A set of trajectories may be generated based on the filtered set of maneuvering option such that each trajectory of the set corresponds to a different maneuvering behavior. A cost for each trajectory of the set of trajectories may be determined, and one of the trajectories of the set of trajectories may be selected based on the determined costs. The vehicle may be maneuvered in the autonomous driving mode according to the selected one of the trajectories.

Abstract: Systems, methods, devices, and other techniques for training a trajectory planning neural network system to determine waypoints for trajectories of vehicles. A neural network training system can train the trajectory planning neural network system on the multiple training data sets. Each training data set can include: (i) a first training input that characterizes a set of waypoints that represent respective locations of a vehicle at each of a series of first time steps, (ii) a second training input that characterizes at least one of (a) environmental data that represents a current state of an environment of the vehicle or (b) navigation data that represents a planned navigation route for the vehicle, and (iii) a target output characterizing a waypoint that represents a target location of the vehicle at a second time step that follows the series of first time steps.

Abstract: The technology relates to controlling a vehicle based on a railroad light's activation status. In one example, one or more processors receive images of a railroad light. The one or more processors determine, based on the images of the railroad light, the illumination status of a pair of lights of the railroad light over a period of time as the vehicle approaches the railroad light. The one or more processors determine based on the illumination status of the pair of lights, a confidence level, wherein the confidence level indicates the likelihood the railroad light is active. The vehicle is controlled as it approaches the railroad light based on the confidence level.

Abstract: This disclosure describes devices, systems, and methods that relate to obtaining image frames with variable resolutions in synchronization with a clock source. An example device may include an image sensor, a clock input, and a controller. The controller includes at least one processor and a memory. The at least one processor is operable to execute program instructions stored in the memory so as to carry out operations. The operations include receiving, by the clock input, a clock signal. The clock signal is a periodic signal defining at least one scan interval. The operations also include during the scan interval, causing the image sensor to capture a full resolution image frame. The operations yet further include during the scan interval, causing the image sensor to capture at least one reduced resolution image frame.

Abstract: A method is provided that involves identifying a target region of an environment of an autonomous vehicle to be monitored for presence of moving objects. The method also involves operating a first sensor to obtain a scan of a portion of the environment that includes at least a portion of the target region and an intermediate region between the autonomous vehicle and the target region. The method also involves determining whether a second sensor has a sufficiently clear view of the target region based on at least the scan obtained by the first sensor. The method also involves operating the second sensor to monitor the target region for presence of moving objects based on at least a determination that the second sensor has a sufficiently clear view of the target region. Also provided is an autonomous vehicle configured to perform the method.

Abstract: The technology relates to enhancing the operation of autonomous vehicles. Extendible sensors are deployed based on detected or predicted conditions around a vehicle while operating in a self-driving mode. When not needed, the sensors are fully retracted into the vehicle to reduce drag and increase fuel economy. When the onboard system determines that there is a need for a deployable sensor, such as to enhance the field of view of the perception system, the sensor is extended in a predetermined manner. The deployment may depend on one or more operating conditions and/or particular driving scenarios. These and other sensors of the vehicle may be protected with a rugged housing, for instance to protect against damage from the elements. And in other situations, deployable foils may extend from the vehicle's chassis to increase drag and enhance braking. This may be helpful for large trucks in steep descent situations.

Abstract: Aspects of the disclosure relate to controlling a vehicle in an autonomous driving mode. For instance, a first location corresponding to a location where the vehicle is to pick up or drop off a passenger is received. A first cost for the vehicle to reach the first location is determined. A second location based on the first location is identified, and a second cost is determined based on a cost for the vehicle to reach the second location and a cost for the passenger to reach the second location. The first cost is compared to the second cost, and a notification is sent based on the notification. In response to sending the notification, instructions to proceed to the second location are received, and in response to receiving the instructions, the vehicle is controlled in the autonomous driving mode to the second location to pick up or drop off the passenger.

Abstract: Aspects of the disclosure provide for generation of trajectories for a vehicle driving in an autonomous driving mode. For instance, information identifying a plurality of objects in the vehicle's environment and a confidence value for each of the objects is received. A set of constraints may be generated. That one or more processors are unable to solve for a trajectory given the set of constraints and an acceptable braking limit may be determined. A first constraint is identified as a constraint for which could not be solved and a first confidence value. That the vehicle should apply a maximum braking level is determined based on the identified first confidence value, a threshold, and the determination that the one or more processors are unable to solve for a trajectory. Based on the determination that the vehicle should apply the maximum braking level, the maximum braking level is applied.

Abstract: This technology relates to a cooling system for reducing the amount of heat within a sensor housing. The system comprising a cold plate containing an interior liquid cooling channel containing a cooling fluid, a heat exchanger attached to the cold plate, and at least one fan configured to generate an air flow loop. The heat exchanger is configured to draw heat from the air flow loop and pass the drawn heat to the cold plate, which in turn, passes the drawn heat to the cooling liquid.

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: A method is provided that includes a vehicle receiving data from an external computing device indicative of at least one other vehicle in an environment of the vehicle. The vehicle may include a sensor configured to detect the environment of the vehicle. The at least one other vehicle may include at least one sensor. The method also includes determining a likelihood of interference between the at least one sensor of the at least one other vehicle the sensor of the vehicle. The method also includes initiating an adjustment of the sensor to reduce the likelihood of interference between the sensor of the vehicle and the at least one sensor of the at least one other vehicle responsive to the determination.

Abstract: The present disclosure relates to systems and methods for attenuating vibrations. An example system includes a camera device with an optical lens. The optical lens defines an optical axis. The example system further includes mechanical fasteners, each mechanical fastener having a first end, a second end coupled to a mounting surface of the vehicle, and a shaft. The shaft has a primary axis parallel to the optical axis and extends through the camera device such that the camera device is able to move through a primary range of motion in a direction along the primary axis and a restricted range of motion in directions perpendicular to the primary axis. The example system additionally includes compliant structures coupled to the camera device, each compliant structure associated with a respective mechanical fastener and configured to change shape in response to motion of the camera device along the primary axis.

Abstract: Aspects of the disclosure relate generally to generating and providing route options for an autonomous vehicle. For example, a user may identify a destination, and in response the vehicle's computer may provide routing options to the user. The routing options may be based on typical navigating considerations such as the total travel time, travel distance, fuel economy, etc. Each routing option may include not only an estimated total time, but also information regarding whether and which portions of the route may be maneuvered under the control of the vehicle alone (fully autonomous), a combination of the vehicle and the driver (semiautonomous), or the driver alone. The time of the longest stretch of driving associated with the autonomous mode as well as map information indicating portions of the routes associated with the type of maneuvering control may also be provided.

Abstract: Example embodiments relate to slanted radomes for protecting radar units. An example radar system may include a radar unit that includes at least one antenna having a radiation pattern. The radar unit is configured to transmit a radar signal based on the radiation pattern and receive radar signals. In addition, the radar system further includes a radome located in a direction of transmission of the radiation pattern. Particularly, the radome is aligned at an angle relative to a plane of the at least one antenna such that reflections of the transmitted radar signal caused by the radome are directed towards at least one of a null of the radiation pattern and an absorption component.

Abstract: The technology relates to determining whether a vehicle operating in an autonomous driving mode is experiencing an anomalous condition, for instance due to a loss of tire pressure, a mechanical failure, or a shift or loss of cargo. The actual current pose of the vehicle is compared to an expected pose of the vehicle, where the expected pose is based on a model of the vehicle. If a pose discrepancy is identified, the anomalous condition is determined from information associated with the pose discrepancy. The vehicle is then able to take corrective action based on the nature of the anomalous condition. The corrective action may include making a real-time driving change, modifying a planned route, alerting a remote operations center, or communicating with one or more other vehicles.

Abstract: The technology relates to detecting a person directing traffic. For instance, a first vehicle may be controlled in an autonomous driving mode. Sensor data is received from a perception system of the first vehicle, the sensor data identifying a person. Behavior of the person is observed using the sensor data. The observed behavior of the person and the observed behavior of a second vehicle are used to determine a likelihood value indicative of whether the person is directing traffic. The first vehicle is maneuvered in the autonomous driving mode based on the determined likelihood value.

Abstract: The disclosure relates to assessing operation of a camera. In one instance, a volume of space corresponding to a first vehicle in an environment of a second vehicle may be identified using sensor data generated by a LIDAR system of the second vehicle. An image captured by a camera of the second vehicle may be identified. The camera may have an overlapping field of view of the LIDAR system at a time when the sensor data was generated. An area of the image corresponding to the volume of space may be identified and processed in order to identify a vehicle light. The operation of the camera may be assessed based on the processing.