Abstract: Aspects of this technical solution can include a method of calibration of a inertial navigation system of a vehicle. The method can include obtaining, from a first vehicle at a second vehicle by a communication interface coupled with the first vehicle and the second vehicle, with first data indicating a direction of gravity relative to a physical orientation of the first vehicle. The method can include obtaining, from the first vehicle at the second vehicle by the communication interface, with second data of the first vehicle indicating the physical orientation of the first vehicle, during movement of the first vehicle caused by the second vehicle. And the method can include generating, at the second vehicle during the movement of the first vehicle and based on the first data and the second data, third data corresponding to a calibration of the physical orientation of the first vehicle.

Abstract: Aspects of this technical solution can include a method of calibration of a positioning system of a vehicle. The method can include transmitting, from a first vehicle at a second vehicle by a communication interface coupled with the first vehicle and the second vehicle, first data indicating a direction of gravity relative to a physical orientation of the first vehicle. The method can include transmitting, from the first vehicle at the second vehicle by the communication interface, second data of the first vehicle indicating the physical orientation of the first vehicle, during movement of the first vehicle caused by the second vehicle. And the method can include receiving, at the first vehicle from the second vehicle during the movement of the first vehicle and based on the first data and the second data, third data corresponding to a calibration of the physical orientation of the first vehicle.

Abstract: An autonomous vehicle can include a sensor and one or more processors. The processors can be configured to automatically control the autonomous vehicle to an energy supply station responsive to determining to resupply energy to the autonomous vehicle; detect, via the sensor, an object corresponding to the energy supply station, the object indicating to initiate energy supply to the autonomous vehicle; responsive to detecting the object, control the autonomous vehicle to stop at a defined position relative to the energy supply station; and open an energy input receptacle of the autonomous vehicle to receive energy from the energy supply station.

Abstract: Systems and methods for real time feedback and for updating welding instructions for a welding robot in real time is described herein. The data of a workspace that includes a part to be welded can be received via at least one sensor. This data can be transformed into a point cloud data representing a three-dimensional surface of the part. A desired state indicative of a desired position of at least a portion of the welding robot with respect to the part can be identified. An estimated state indicative of an estimated position of at least the portion of the welding robot with respect to the part can be compared to the desired state. The welding instructions can be updated based on the comparison.

Abstract: An autonomous vehicle can include first one or more sensors located on a first side of the autonomous vehicle; second one or more sensors located on a second side of the autonomous vehicle; and one or more processors. The can processors be configured to automatically control, using images generated by the first one or more sensors, the autonomous vehicle to an energy supply station responsive to determining to resupply energy to the autonomous vehicle; detect, using the images generated by the first one or more sensors, an arrival of the autonomous vehicle at the energy supply station; and responsive to detecting the arrival of the autonomous vehicle at the energy supply station, switch from processing images generated by the first one or more sensors to processing images generated by the second one or more sensors.

Abstract: Embodiments herein include an automated vehicle performing localization functions using particle scoring and particle filters. The automated vehicle performs a phase correlation operation that transforms image data of a sensed map and pre-stored base map from a spatial to frequency domain and combines the transformed maps to generate image data of a correlation map. Estimated location information of particles are compared against sensed data or other data in sensed sub-maps or the correlation map. The automated vehicle may apply an image-convolution scoring map by combining image data of the sensed and base maps in the spatial domain. The autonomy system may calculate entropies for the correlation map and image-convolution scoring map and combines these maps based upon the respective entropies.

Abstract: An energy supply station can include a mechanical arm, an energy delivery receptacle, and one or more processors. The processors can be configured to detect an arrival of a vehicle at the energy supply station; transmit an indication of the arrival to a remote computer, causing activation of a virtual interface; and move the mechanical arm, based on input at the virtual interface, to cause the energy delivery receptacle to contact or couple with an energy input receptacle of the vehicle.

Abstract: Aspects of this technical solution can include transmitting, from a first vehicle to a second vehicle by a communication interface coupled with the first vehicle and the second vehicle, first data indicating a positioning of an antenna of a location sensor of the first vehicle, transmitting, from the first vehicle to the second vehicle by the communication interface, second data of the first vehicle indicating a physical location of the first vehicle, during movement of the first vehicle caused by the second vehicle, and receiving, at the first vehicle from the second vehicle by the communication interface in response to the movement of the first vehicle, third data generated at the second vehicle based on the first data and the second data, the third data corresponding to a calibration of the physical location of the first vehicle.

Abstract: Aspects of this technical solution can include obtaining, from a first vehicle at a second vehicle by a communication interface coupled with the first vehicle and the second vehicle, first data indicating a positioning of an antenna of a location sensor of the first vehicle, obtaining, from the first vehicle at the second vehicle by the communication interface, second data of the first vehicle indicating a physical location of the first vehicle, during movement of the first vehicle caused by the second vehicle, and generating, at the second vehicle during the movement of the first vehicle and based on the first data and the second data, third data corresponding to a calibration of the physical location of the first vehicle.

Abstract: Embodiments described herein implement an improved autonomy system with a beneficial approach to implementation a localization loop. When the automated vehicle loses access to geolocation data updates, the autonomy system invokes a geo-denied localization loop that performs map localization and motion estimation functions without geolocation data. The localization loop feeds map localizer outputs into a motion estimator of the INS and/or the IMU, and feeds motion estimation outputs from the motion estimator back into the map localizer. When executing the localization loop, the autonomy system detects outlier measurements as errors in the map localizer and mitigates the errors in the map localizer or the motion estimator. The autonomy system executes programming in an error detection phase for monitoring and detecting errors in the localization loop, and an error mitigation phase for mitigating or resolving errors, such as applying a covariance boosting value on outputted data values.

Abstract: Disclosed are a method and an apparatus for predicting vehicle trajectory, and a method and an apparatus for training a neural network prediction model, relating to the field of intelligent driving technology. The method for predicting vehicle trajectory including: determining raster image data of a vehicle at a current time point based on ego-vehicle travelling data of the vehicle during travelling and environmental data of the vehicle; processing the raster image data based on a neural network prediction model, and predicting a trajectory of the vehicle in a future predetermined time period based on the multidimensional feature map, ego-vehicle size data and the environmental data.

Abstract: Autonomous vehicles including sensors and electronic control units (ECUs) that communicate via ring networks are disclosed. A system includes an ECU of an autonomous vehicle that includes an ECU network interface. The system includes a plurality of sensors disposed on the autonomous vehicle, and each of the plurality of sensors includes a respective sensor network interface. The system includes a plurality of network links communicatively coupling the plurality of sensors to the ECU network interface of the ECU via the respective sensor network interface in a ring configuration.

Abstract: A system can include one or more processors. The processors can be configured to receive, from a vehicle via first one or more sensors of the vehicle, first images or video of a physical environment surrounding the vehicle; receive, from an energy supply station via second one or more sensors of the energy supply station, second images or video of the physical environment surrounding the vehicle; and responsive to receiving the first images or video and the second images or video, generate a virtual interface depicting the physical environment based on the first images or video and the second images or video, the virtual interface enabling a user to provide input to control a mechanical arm of the energy supply station to supply energy to the vehicle.

Abstract: Systems and methods for automated cooking are described. In one embodiment, an automated kitchen system includes a robotic device and a computing device having a memory storing instructions and a processor. The instructions cause the processor to identify a recipe associated with an order for at least one food item. The instructions cause the processor to identify an ingredient based on the set of instructions of the recipe. The instructions cause the processor to determine a measurement associated with the ingredient based on the set of instructions of the recipe. The instructions cause the processor to cause the robotic device to retrieve a measured portion of the ingredient based on the measurement and deliver the measured portion of the ingredient to cookware. The instructions cause the processor to cause the robotic device to execute a task in response to the measured portion of the ingredient being delivered to the cookware.

Abstract: Systems, methods, and apparatuses for inspecting a tank containing a flammable fluid are provided. A vehicle configured to inspect the tank can include a propeller, a battery, a control unit, an inspection device, and a ranging device. The battery provides power to the propeller, the control unit, the inspection device, and the ranging device. The control unit generates a map of the tank and determines a first position of the vehicle on the map. The propeller moves the vehicle through the flammable fluid in the tank. The inspection device includes a pulsed eddy current array to obtain inspection data indicating a quality of a tank wall. The control unit causes the propeller to move the vehicle from the first position to a second position within the tank. The control unit obtains first inspection data indicating the quality of the tank wall, and stores the first inspection data.

Abstract: The foodstuff assembly system can include: a robot arm, a frame, a set of foodstuff bins, a sensor suite, a set of food utensils, and a computing system. The system can optionally include: a container management system, a human machine interface (HMI). However, the foodstuff assembly system 100 can additionally or alternatively include any other suitable set of components. The system functions to enable picking of foodstuff from a set of foodstuff bins and placement into a container (such as a bowl, tray, or other foodstuff receptacle). Additionally or alternatively, the system can function to facilitate transferal of bulk material (e.g., bulk foodstuff) into containers, such as containers moving along a conveyor line.

Abstract: A prism for reflecting a laser includes: a single mounting cap at a first end of the prism, and first to seventh trihedral corner (TC) reflectors, each including a reflective surface including: three side edges, and three corners at respective intercept points between the side edges, wherein the seventh TC reflector, among the first to seventh TC reflectors, is on a second end of the prism opposite to the first end of the prism.

Abstract: Methods and systems are described herein for hosting and arbitrating algorithms for the generation of structured frames of data from one or more sources of unstructured input frames. A plurality of frames may be received from a recording device and a plurality of object types to be recognized in the plurality of frames may be determined. A determination may be made of multiple machine learning models for recognizing the object types. The frames may be sequentially input into the machine learning models to obtain a plurality of sets of objects from the plurality of machine learning models and object indicators may be received from those machine learning models. A set of composite frames with the plurality of indicators corresponding to the plurality of objects may be generated, and an output stream may be generated including the set of composite frames to be played back in chronological order.

Abstract: A mobility platform is configured to execute one or more tasks in a worksite including a passive landmark. A mobility platform may include a first laser rangefinder and at least one processor configured to sweep the first passive landmark with the first laser rangefinder to collect a first plurality of distance measurements for a first plurality of yaw angles, fit a first shape to the first plurality of distance measurements based on a predetermined shape of the first passive landmark, and determine a position of a geometric center of the first passive landmark relative to the first location of the first laser rangefinder based on the fit first shape.

Abstract: Inspection robots with independent, swappable, drive modules are described. An example inspection robot may have a center body with a plurality of power interfaces, a plurality of communication interfaces, and a plurality of cooling interfaces. The example inspection robot may have a plurality of drive modules, where each drive module is structured to be coupled to a power interface, a communication interface, and a cooling interface.