Abstract: Systems and methods for training an adapter network that adapts a model pre-trained on synthetic images to real-world data are disclosed herein. A system may include a processor and a memory in communication with the processor and having machine-readable that cause the processor to output, using a neural network, a predicted scene that includes a three-dimensional bounding box having pose information of an object, generate a rendered map of the object that includes a rendered shape of the object and a rendered surface normal of the object, and train the adapter network, which adapts the predicted scene to adjust for a deformation of the input image by comparing the rendered map to the output map acting as a ground truth.

Abstract: Systems, methods, and non-transitory computer-readable media can determine contextual information associated with an environment including a vehicle and at least one agent for generating a computer simulation based on the environment. One or more behavior constraints for the at least one agent can be determined based on the contextual information. A set of trajectories can be generated based on the one or more behavior constraints. A trajectory can be selected from the set of trajectories based on determining that the trajectory satisfies one or more predetermined criteria. The computer simulation can be generated, wherein the computer simulation includes monitoring driving behavior of the vehicle in response to the vehicle interacting with the at least one agent based on the selected trajectory.

Abstract: The present invention relates to a method of generating an overhead view image of an area. More particularly, the present invention relates to a method of generating a contextual multi-image based overhead view image of an area using ground map data and field of view image data. Various embodiments of the present technology can include methods, systems and non-transitory computer readable media and computer programs configured to receive a plurality of images of the geographical area, determine a ground map of the geographical area, divide the ground map into a plurality of sampling points of the geographical area; and determine a color for each of the plurality of sampling points, wherein the color of each of the sampling points is determined by determining a correlation between the sampling points of the geographical area and color of the sampling points captured in at least one of the plurality of images.

Abstract: Systems, methods, and non-transitory computer-readable media can receive a geometric map and a semantic map associated with a geographic area, the semantic map comprising semantic data associated with vehicle navigation. A first semantic position estimate associated with a first piece of semantic data contained in the semantic map is generated based on semantic data location information associated with the first piece of semantic data. A final position for the first semantic position estimate is received. One or more three-dimensional semantic labels are applied to the geometric map based on the final position of the first semantic position estimate. A warped semantic map is generated. Generating the warped semantic map comprises warping the semantic map based on the one or more three-dimensional semantic labels.

Abstract: In one embodiment, a method includes identifying, for each of one or more environmental radars, one or more parameter values associated with a radar signal of the environmental radar, determining one or more transmission parameter values for the radar, wherein a combination of the one or more transmission parameter values is different from a combination of the one or more parameter values of each of the one or more environmental radars, and configuring the radar with the determined one or more transmission parameter values.

Abstract: A system and method that enables resource analysis within an intelligent content absorption network with autonomous mobility implementations includes generating a prioritization model, training the prioritization model on a data corpus to generate a prioritization schedule, deploying the prioritization schedule to one or more autonomous vehicles, offloading data at a local content absorption node, processing data at the local content absorption node, and optionally transmitting data results from the processed data.

Abstract: In one embodiment, a method includes generating a simulated sensor based on performance features associated with a sensor. The method includes determining a placement indicator specifying a location and orientation of the simulated sensor on a vehicle in a virtual environment associated with the vehicle. The method includes simulating, based on the performance features associated with the sensor, behavior of one or more emissions originating from the simulated sensor in the virtual environment. For each emission, the simulating includes determining an interaction of the emission with one or more simulated objects in the virtual environment. The method includes providing a representation of a capability of the sensor based on the simulated behavior of the emissions.

Abstract: In one embodiment, a computing system may transmit, using one or more light emitters, light beams of different wavelengths simultaneously into a surrounding environment. The system may determine a characteristic of the surrounding environment based on reflections of the light beams. In response to a determinization that the characteristic of the surrounding environment satisfies a criterion, the system may configure the one or more light emitters to transmit light beams of different wavelengths sequentially into the surrounding environment for measuring distances to one or more objects in the surrounding environment.

Abstract: In one embodiment, a method includes determining an initial cost volume associated with a plurality of potential trajectories of a vehicle in an environment based on a set of movement restrictions of the vehicle, generating a delta cost volume using the initial cost volume and environment data associated with the environment, wherein the delta cost volume is generated by determining adjustments to the initial cost volume that incorporate observed driving behavior, and scoring a trajectory of the plurality of potential trajectories for the vehicle based on the initial cost volume and the delta cost volume.

Abstract: Examples disclosed herein may involve (i) based on an analysis of 2D data captured by a vehicle while operating in a real-world environment during a window of time, generating a 2D track for at least one object detected in the environment comprising one or more 2D labels representative of the object, (ii) for the object detected in the environment: (a) using the 2D track to identify, within a 3D point cloud representative of the environment, 3D data points associated with the object, and (b) based on the 3D data points, generating a 3D track for the object that comprises one or more 3D labels representative of the object, and (iii) based on the 3D point cloud and the 3D track, generating a time-aggregated, 3D visualization of the environment in which the vehicle was operating during the window of time that includes at least one 3D label for the object.

Abstract: Disclosed herein is technology for deriving a planned path for a vehicle that is operating in a geographic area. In an example embodiment, a computing system associated with the vehicle may function to (i) identify a set of path priors to use as a basis for deriving the planned path for the vehicle in the geographic area, (ii) sample path priors in the identified set of path priors and thereby producing a set of points that is representative of the identified set of path priors, (iii) fit a curve to the set of points produced by the sampling, and (iv) derive the planned path for the vehicle based on the fitted curve.

Abstract: In one embodiment, a method includes determining an operational status of a vehicle including a radar antenna. The operational status is related to autonomous-driving operations of the vehicle in an environment. The method includes determining an expected amount of signaling resources associated with the radar antenna to be utilized by the vehicle while the vehicle performs the autonomous-driving operations, based at least on the operational status of the vehicle and the environment. The method includes determining to switch one or more of the signaling resources associated with the radar antenna from a first mode to a second mode based on the expected amount of signaling resources to be utilized by the radar antenna while the vehicle performs the autonomous-driving operations. The method includes causing the one or more of the signaling resources associated with the radar antenna to switch from the first mode to the second mode.

Abstract: Examples disclosed herein may involve (i) obtaining data for one or more data variables related to autonomous operation of a vehicle in a test environment being facilitated by the vehicle's autonomy system, (ii) based on the obtained data, evaluating one or more predefined fault rules, each of which comprises (a) one or more predefined criteria related to the one or more data variables and (b) a predefined fault that is to be injected into the autonomy system when the one or more predefined criteria are determined to be satisfied, (iii) based on the evaluation, injecting a predefined fault into the autonomy system, and (iv) capturing data indicative of a response by a response mechanism of the vehicle to the vehicle autonomously operating in accordance with the injected fault.

Abstract: A system and method that includes collecting vehicle sensor data, wherein prioritizing vehicle sensor data includes identifying a level of importance for each of a plurality of vehicle sensor data types included in the vehicle sensor data; generating a vehicle sensor data schedule, wherein generating the vehicle data schedule includes one or more of (i) identifying a transmission order for each of the plurality of vehicle sensor data types and (ii) identifying a storage scheme selected from a hierarchy of data storage types for each of the plurality of vehicle sensor data types; transforming vehicle sensor data into message data, wherein the transforming includes selectively converting one or more of the vehicle sensor data types of the vehicle sensor data to a messaging format based on the prioritization; and transmitting, via one or more selected communication networks, the message data according to the vehicle sensor data schedule.

Abstract: Examples disclosed herein may involve a computing system that is operable to (i) present, via a visual interface, a virtual shape associated with a three-dimensional (3D) coordinate system, (ii) present, via the visual interface, a visual indicator positioned in proximity to the virtual shape and indicating that a specified spatial parameter of the virtual shape will be modified along a specified dimension of the 3D coordinate system in response to a given type of user input associated with the visual indicator, (iii) while presenting the visual indicator, detect an instance of the given type of user input associated with the visual indicator, and (iv) after detecting the instance of the given type of user input, update the virtual shape that is presented via the visual interface by modifying the specified spatial parameter of the virtual shape along the specified dimension.

Abstract: Systems, methods, and other embodiments relate to determining the speed of a vehicle. In one embodiment, a method includes receiving a first frame of data generated by a first sensor of a vehicle, the first frame of data including a first set of angular positions associated with a first set of objects in the environment. The method includes receiving a second frame of data generated by a second sensor of the vehicle, the second frame of data including a second set of angular positions associated with a second set of objects in the environment. The method includes generating a speed estimate for the vehicle in relation to the first set of objects and the second set of objects based at least in part on the first set of angular positions of the first frame of data and the second set of angular positions of the second frame of data.

Abstract: A method includes accessing a training sample including an image of a scene, depth measurements of the scene, and a predetermined 3D position of an object in the scene. The method includes training a 3D-detection model for detecting 3D positions of objects based the depth measurements and the predetermined 3D position, and training a 2D-detection model for detecting 2D positions of objects within images. Training the 2D-detection model includes generating an estimated 2D position of the object by processing the image using the 2D-detection model, determining a subset of the depth measurements that correspond to the object based on the estimated 2D position and a viewpoint from which the image is captured, generating an estimated 3D position of the object based on the subset of the depth measurements, and updating the 2D-detection model based on a comparison between the estimated 3D position and the predetermined 3D position.

Abstract: In one embodiment, a method includes accessing first image data generated by a first image sensor having a first filter array that has a first filter pattern. The first filter pattern includes a number of first filter types. The method also includes accessing second image data generated by a second image sensor having a second filter array that has a second filter pattern different from the first filter pattern. The second filter pattern includes a number of second filter types, the number of second filter types and the number of first filter types have at least one filter type in common. The method also includes determining a correspondence between one or more first pixels of the first image data and one or more second pixels of the second image data based on a portion of the first image data associated with the filter type in common.

Abstract: A method includes determining vehicle driving parameters associated with a driving behavior of a vehicle while in an autonomous driving mode. A plurality of electronic control units (ECUs) is interconnected to a vehicle bus for communicating instructions from electromechanical contacts to actuators to control the driving behavior. The computing unit may receive a control signal from one of the ECUs. The computing unit lacks knowledge of whether the control signal a valid. The method further includes analyzing vehicle driving parameters associated with the driving behavior to determine whether the vehicle driving parameters satisfy a driving behavior criteria. Subsequent to determining that the vehicle driving parameters fails to satisfy the driving behavior criteria, the method includes generating a signal that causes the electromechanical contacts to disconnect from the vehicle bus and disable communication of instructions between the ECUs and the vehicle bus.

Abstract: In one embodiment, a modular sensor assembly configured for mounting on a vehicle includes a first set of sensors and a second set of sensors. The modular sensor assembly includes a coordinate frame baseplate including a continuous surface, and sensor mounting elements coupled to the continuous surface for mounting the first set of sensors at a first height. The coordinate frame baseplate includes a sensor platform configured for mounting the second set of sensors at a second height. The first set of sensors and the second set of sensors are coupled to the coordinate frame baseplate so as to impart a common coordinate frame for the first set of sensors mounted at the first height and the second set of sensors mounted at the second height. The modular sensor assembly includes a bridging support structure coupled to the coordinate frame baseplate and capable of being mounted on a vehicle.