In one embodiment, a method includes, by a computing system associated with a vehicle, determining a current location of the vehicle in a first region, identifying one or more first sets of model parameters associated with the first region and one or more second sets of model parameters associated with a second region, generating, using one or more machine-learning models based on the first sets of model parameters, one or more first inferences based on first sensor data captured by the vehicle, switching the configurations of the models from the first sets of model parameters to the second sets of model parameters, generating, using the models having configurations based on the second sets of model parameters, one or more second inferences based on second sensor data generated by the sensors of the vehicle in the second region, and causing the vehicle to perform one or more operations based on the second inferences.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for unmanned aerial vehicle modular command priority determination and filtering system. One of the methods includes enabling control of the UAV by a first control source that provides modular commands to the UAV, each modular command being a command associated with performance of one or more actions by the UAV. Modular commands from a second control source requesting control of the UAV are received. The second control source is determined to be in control of the UAV based on priority information associated with each control source. Control of the UAV is enabled by the second control source, and modular commands are implemented.

A vehicle adapted to be remotely driven via a wireless communication network comprises a capturing unit for capturing live video data of the vehicle's environment, a video encoding unit for video encoding the captured live video data, a transmission unit for transmitting the encoded live video data via the wireless communication network, and a control unit for controlling the video encoding unit and/or the transmission unit. The control unit controls the video encoding unit to optimize the video encoding of the captured live video data and/or to control the transmission unit to optimize the transmission of the encoded live video data. The controlling is based on one, two or all of: (i) pre-determined location information associated with a current location of the vehicle; (ii) real-time driving information associated with current driving parameters of the vehicle, and; (iii) real-time environment information associated with a current environment of the vehicle.

A pool cleaning system for cleaning debris from a submerged surface of a swimming pool includes a self-propelled pool cleaner having rotatably-mounted supports for supporting and guiding the cleaner on the pool surface; an electric motor for enabling the rotation of the rotatably-mounted supports on the pool surface; at least one camera to capture imagery of the pool surface; a controller, in electronic communication with the at least one camera, to determine a cleanliness characteristic of the pool surface on which the cleaner has passed based on the camera imagery and generate a control signal to direct movement of the cleaner based on the cleanliness characteristic of the pool surface, and a portable electronic device configured to present a graphic on a display, the graphic depicting the submerged surface of the pool and those portions of the surface that remain uncleaned as the cleaner traverses the pool surface.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting locations in an environment of a vehicle where objects are likely centered and determining properties of those objects. One of the methods includes receiving an input characterizing an environment external to a vehicle. For each of a plurality of locations in the environment, a respective first object score that represents a likelihood that a center of an object is located at the location is determined. Based on the first object scores, one or more locations from the plurality of locations are selected as locations in the environment at which respective objects are likely centered. Object properties of the objects that are likely centered at the selected locations are also determined.

In one embodiment, a computing system of a vehicle may access sensor data associated with a surrounding environment of a vehicle. The system may generate, based on the sensor data, a first trajectory having one or more first driving characteristics for navigating the vehicle in the surrounding environment. The system may generate a second trajectory having one or more second driving characteristics by modifying the one or more first driving characteristics of the first trajectory. The modifying may use adjustment parameters based on one or more human-driving characteristics of observed human-driven trajectories such that the one or more second driving characteristics satisfy a similarity threshold relative to the one or more human-driving characteristics. The system may determine, based on the second trajectory, vehicle operations to navigate the vehicle in the surrounding environment.

Systems, methods, and non-transitory computer-readable media can be configured to determine a targeted scenario and a mission associated with the targeted scenario. A route to a location associated with the mission can be determined based at least in part on a likelihood of encountering the targeted scenario, wherein the likelihood of encountering the targeted scenario is based at least in part on a frequency with which scenarios similar to the targeted scenario were encountered at the location. Whether the targeted scenario was encountered can be determined based on an evaluation of captured sensor data associated with the mission upon passing the location.

Described is a system for training a neural network for estimating surface normals for use in operating an autonomous platform. The system uses a parallelizable k-nearest neighbor sorting algorithm to provide a patch of points, sampled from the point cloud data, as input to the neural network model. The points are transformed from Euclidean coordinates in a Euclidean space to spherical coordinates. A polar angle of a surface normal of the point cloud data is estimated in the spherical coordinates. The trained neural network model is utilized on the autonomous platform, and the estimate of the polar angle of the surface normal is used to guide operation of the autonomous platform within the environment.

The present disclosure relates to a system and a method for addressing an error in a localization system that includes monitoring a plurality of sensors of a driver assistance system in real-time, with each sensor generating a data stream. The method further includes identifying a sensor having an anomalous data stream and calculating a primary localization and a backup localization. The primary localization calculation includes the anomalous data stream and the backup localization calculation does not include the anomalous data stream. Further, the method includes executing an action when the backup localization error estimate exceeds a threshold.

Among other things, techniques are described for predicting how an agent (e.g., a vehicle, bicycle, pedestrian, etc.) will move in an environment based on prior movement, the road network, the surrounding objects and/or other relevant environmental factors. One trajectory prediction technique involves generating a probability map for an agent's movement. Another trajectory prediction technique involves generating a trajectory lattice, for an agent's movement. In addition, a different trajectory prediction technique involves multi-modal regression where a classifier (e.g., a neural network) is trained to classify the probability of a number of (learned) modes such that each model produces a trajectory based on the current input.