Abstract: An image capture device includes a mechanical stabilization system is used in image signal processing. The mechanical image stabilization system has an operating bandwidth and includes a motor to control an orientation of an image sensor. A processing apparatus of the image capture device determines a temperature of the motor and adjusts a cutoff frequency of the operating bandwidth based on the temperature of the motor.

Abstract: For one embodiment of the present disclosure, a computer implemented method provides deterministic multi-objective constrained optimization for a planning system of an autonomous vehicle (AV). The computer implemented method comprises initializing a planning solver with a plurality of candidate trajectories for an autonomous vehicle, selecting two or more optimal candidate trajectories that potentially satisfy all constraints and evaluating these two or more optimal candidate trajectories in parallel asynchronously using cost functions, determining whether a cost threshold is violated for a node in a temporarily ordered sequence of nodes for a branch of each of the two or more optimal candidate trajectories, and intentionally stopping branch evaluation early for a branch having a cost threshold violation.

Abstract: Disclosed are systems and methods for specifying goals and behavioral parameters for planning systems of autonomous vehicles. In some aspects, a method includes receiving, by a mission manager in an autonomous vehicle (AV), a mission from an input source of the AV, the mission comprising a request for a task that the AV is to fulfill; deconflicting the mission with one or more other missions of the AV to generate a ranked list of missions; selecting a target mission from the ranked list of missions in accordance with priorities corresponding to each mission in the ranked list of missions; generating one or more scenarios based on the target mission, the one or more scenarios comprising encoded representations of local and geometric terms to cause the target mission to be fulfilled by the AV; and dispatching the one or more scenarios to a planner layer of the AV.

Abstract: Approaches to utilizing contextual right-of-way decision making for autonomous vehicles are disclosed. An autonomous vehicle is operated in a road setting within an operating environment having other road users. The operation of the autonomous vehicle is based on safety constraints providing limits on operation of the autonomous vehicle. The presence of a selected other road user within the operating environment is detected. Potential trajectories for the autonomous vehicle within the operating environment are evaluated with respect to the other road user. The autonomous vehicle interacts with the other road user by generating vehicle control signals based on a machine learned model and within the one or more safety constraints. The machine learned model is based on a hierarchy of costs corresponding to characteristics of maneuvers by the autonomous vehicle.

Abstract: An image capture device includes a mechanical stabilization system is used in image signal processing. The mechanical image stabilization system has an operating bandwidth and includes a motor to control an orientation of an image sensor. A processing apparatus of the image capture device determines a temperature of the motor and adjusts a cutoff frequency of the operating bandwidth based on the temperature of the motor.

Abstract: Disclosed herein are systems and method including a method for managing an autonomous vehicle. The method includes obtaining labels associated with various aspects of right-of-way interactions between an autonomous vehicle and an agent, wherein the right-of-way interactions occur when a human driver takes over for the autonomous vehicle and performs the right-of-way interactions, running an autonomous vehicle stack that is untrained for processing right-of-way interactions between the autonomous vehicle and the agent, injecting the labels into the autonomous vehicle stack and determining, based on the injecting of the labels into the autonomous vehicle stack, a performance of the autonomous vehicle stack.

Abstract: Disclosed herein are systems and method including a method for managing an autonomous vehicle. The method include providing as first input to a machine learning model a raster image and a vector associated with a context of a scene comprising an autonomous vehicle and a plurality of agents, providing as second input to the machine learning model a planned travel path for the autonomous vehicle, based the first input and the second input, outputting from the machine learning model a plurality of yield/assert predictions, wherein the plurality of yield/assert predictions comprises a respective yield/assert prediction related to whether to yield or to assert in relation to each respective agent of the plurality of agents and causing the autonomous vehicle to travel along the planned travel path while yielding or asserting against the plurality of agents according to the plurality of yield/assert predictions.

Abstract: Systems and methods are disclosed for image signal processing. For example, method may include determining a sequence of orientation estimates based on sensor data from one or more motion sensors. The method may include receiving an image from the image sensor. The method may include filtering the sensor data with a pass band matching an operation bandwidth to the sequence of orientation estimates to obtain filtered data. The method may include invoking an electronic image stabilization module to correct the image based on the filtered data to obtain a stabilized image. The method may include storing, displaying, or transmitting an output image based on the stabilized image.

Abstract: A processor coupled to memory is configured to receive an identification of a geographical location associated with a target specified by a user remote from a vehicle. A machine learning model is utilized to generate a representation of at least a portion of an environment surrounding the vehicle using sensor data from one or more sensors of the vehicle. At least a portion of a path to a target location corresponding to the received geographical location is calculated using the generated representation of the at least portion of the environment surrounding the vehicle. At least one command is provided to automatically navigate the vehicle based on the determined path and updated sensor data from at least a portion of the one or more sensors of the vehicle.

Abstract: Disclosed is an electronic gimbal with camera and mounting configuration. The gimbal can include an inertial measurement unit which can sense the orientation of the camera and three electronic motors which can manipulate the orientation of the camera. The gimbal can be removably coupled to a variety of mount platforms, such as an aerial vehicle, a handheld grip, or a rotating platform. Moreover, a camera can be removably coupled to the gimbal and can be held in a removable camera frame. Also disclosed is a system for allowing the platform, to which the gimbal is mounted, to control settings of the camera or to trigger actions on the camera, such as taking a picture, or initiating the recording of a video. The gimbal can also provide a connection between the camera and the mount platform, such that the mount platform receives images and video content from the camera.

Abstract: A processor coupled to memory is configured to receive an identification of a geographical location associated with a target specified by a user remote from a vehicle. A machine learning model is utilized to generate a representation of at least a portion of an environment surrounding the vehicle using sensor data from one or more sensors of the vehicle. At least a portion of a path to a target location corresponding to the received geographical location is calculated using the generated representation of the at least portion of the environment surrounding the vehicle. At least one command is provided to automatically navigate the vehicle based on the determined path and updated sensor data from at least a portion of the one or more sensors of the vehicle.

Abstract: Disclosed is an electronic gimbal with camera and mounting configuration. The gimbal can include an inertial measurement unit which can sense the orientation of the camera and three electronic motors which can manipulate the orientation of the camera. The gimbal can be removably coupled to a variety of mount platforms, such as an aerial vehicle, a handheld grip, or a rotating platform. Moreover, a camera can be removably coupled to the gimbal and can be held in a removable camera frame. Also disclosed is a system for allowing the platform, to which the gimbal is mounted, to control settings of the camera or to trigger actions on the camera, such as taking a picture, or initiating the recording of a video. The gimbal can also provide a connection between the camera and the mount platform, such that the mount platform receives images and video content from the camera.

Abstract: Systems and methods are disclosed for image signal processing. For example, method may include determining a sequence of orientation estimates based on sensor data from one or more motion sensors. The method may include receiving an image from the image sensor. The method may include filtering the sensor data with a pass band matching an operation bandwidth to the sequence of orientation estimates to obtain filtered data. The method may include invoking an electronic image stabilization module to correct the image based on the filtered data to obtain a stabilized image. The method may include storing, displaying, or transmitting an output image based on the stabilized image.

Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include determining a sequence of orientation estimates based on sensor data from one or more motion sensors; based on the sequence of orientation estimates, invoking a mechanical stabilization system to reject motions of an image sensor occurring within a first operating bandwidth with an upper cutoff frequency; receiving an image from the image sensor; based on the sequence of orientation estimates, invoking an electronic image stabilization module to correct the image for rotations of the image sensor occurring within a second operating bandwidth with a lower cutoff frequency to obtain a stabilized image, wherein the lower cutoff frequency is greater than the upper cutoff frequency; and storing, displaying, or transmitting an output image based on the stabilized image.

Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include determining a sequence of orientation estimates based on sensor data from one or more motion sensors; based on the sequence of orientation estimates, invoking a mechanical stabilization system to reject motions of an image sensor occurring within a first operating bandwidth with an upper cutoff frequency; receiving an image from the image sensor; based on the sequence of orientation estimates, invoking an electronic image stabilization module to correct the image for rotations of the image sensor occurring within a second operating bandwidth with a lower cutoff frequency to obtain a stabilized image, wherein the lower cutoff frequency is greater than the upper cutoff frequency; and storing, displaying, or transmitting an output image based on the stabilized image.

Abstract: Disclosed is an electronic gimbal with camera and mounting configuration. The gimbal can include an inertial measurement unit which can sense the orientation of the camera and three electronic motors which can manipulate the orientation of the camera. The gimbal can be removably coupled to a variety of mount platforms, such as an aerial vehicle, a handheld grip, or a rotating platform. Moreover, a camera can be removably coupled to the gimbal and can be held in a removable camera frame. Also disclosed is a system for allowing the platform, to which the gimbal is mounted, to control settings of the camera or to trigger actions on the camera, such as taking a picture, or initiating the recording of a video. The gimbal can also provide a connection between the camera and the mount platform, such that the mount platform receives images and video content from the camera.

Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include determining a sequence of orientation estimates based on sensor data from one or more motion sensors; based on the sequence of orientation estimates, invoking a mechanical stabilization system to reject motions of an image sensor occurring within a first operating bandwidth with an upper cutoff frequency; receiving an image from the image sensor; based on the sequence of orientation estimates, invoking an electronic image stabilization module to correct the image for rotations of the image sensor occurring within a second operating bandwidth with a lower cutoff frequency to obtain a stabilized image, wherein the lower cutoff frequency is greater than the upper cutoff frequency; and storing, displaying, or transmitting an output image based on the stabilized image.

Abstract: Disclosed is an electronic gimbal with camera and mounting configuration. The gimbal can include an inertial measurement unit which can sense the orientation of the camera and three electronic motors which can manipulate the orientation of the camera. The gimbal can be removably coupled to a variety of mount platforms, such as an aerial vehicle, a handheld grip, or a rotating platform. Moreover, a camera can be removably coupled to the gimbal and can be held in a removable camera frame. Also disclosed is a system for allowing the platform, to which the gimbal is mounted, to control settings of the camera or to trigger actions on the camera, such as taking a picture, or initiating the recording of a video. The gimbal can also provide a connection between the camera and the mount platform, such that the mount platform receives images and video content from the camera.

Abstract: A processor coupled to memory is configured to receive an identification of a geographical location associated with a target specified by a user remote from a vehicle. A machine learning model is utilized to generate a representation of at least a portion of an environment surrounding the vehicle using sensor data from one or more sensors of the vehicle. At least a portion of a path to a target location corresponding to the received geographical location is calculated using the generated representation of the at least portion of the environment surrounding the vehicle. At least one command is provided to automatically navigate the vehicle based on the determined path and updated sensor data from at least a portion of the one or more sensors of the vehicle.

Abstract: Systems and methods are disclosed for image signal processing. For example, methods may include determining a sequence of orientation estimates based on sensor data from one or more motion sensors; based on the sequence of orientation estimates, invoking a mechanical stabilization system to reject motions of an image sensor occurring within a first operating bandwidth with an upper cutoff frequency; receiving an image from the image sensor; based on the sequence of orientation estimates, invoking an electronic image stabilization module to correct the image for rotations of the image sensor occurring within a second operating bandwidth with a lower cutoff frequency to obtain a stabilized image, wherein the lower cutoff frequency is greater than the upper cutoff frequency; and storing, displaying, or transmitting an output image based on the stabilized image.