Abstract: Disclosed herein are methods and systems to avoid collisions with animals. In an example, a method comprises receiving, by a processor, an indication that a current trajectory of an autonomous vehicle is associated with a likelihood of a collision that satisfies a collision threshold indicating a potential collision with an animal having an attribute that satisfies a threshold; disabling, by the processor, at least one lighting apparatus associated with the autonomous vehicle; and enabling, by the processor, a sound-generating device associated with the autonomous vehicle.

Abstract: In some examples, an autonomous robotic welding system comprises a workspace including a part having a seam, a sensor configured to capture multiple images within the workspace, a robot configured to lay weld along the seam, and a controller. The controller is configured to identify the seam on the part in the workspace based on the multiple images, plan a path for the robot to follow when welding the seam, the path including multiple different configurations of the robot, and instruct the robot to weld the seam according to the planned path.

Abstract: A lightweight portable microprocessor-assisted remote control camera system provides precise repeatable camera movement through the improved stability of a 3-axis gimbal design, which allows a lightweight large sensor camera to be placed almost anywhere and smoothly controlled remotely via a simple touchscreen interface. The computer control module provides a wide range of control options including remote adjustment of all camera, lens and gimbal parameters, which can be programmed, set and recalled, including stabilization and motion smoothing, via the touchscreen interface.

Abstract: Systems and methods are provided for identifying a vehicle subject to an emergency alert. The method includes receiving an emergency alert, wherein the emergency alert includes a geographic region associated with the emergency alert and one or more identifiable markers of a wanted vehicle, determining whether the autonomous vehicle is within the geographic region associated with the emergency alert, and detecting, using one or more detection mechanisms coupled to the autonomous vehicle, a detected vehicle within an environment of the autonomous vehicle. The method further includes, when the autonomous vehicle is within the geographic region associated with the emergency alert, determining, for each identifiable marker, whether the detected vehicle matches the identifiable marker, and when the detected vehicle matches the one or more identifiable markers, generating, using a processor coupled to the autonomous vehicle, a signal indicating that the detected vehicle is the wanted vehicle.

Abstract: One variation of a method for tracking promotional states of slots in inventory structures within a store includes: accessing an image of an inventory structure within a store; detecting a shelf tag on the inventory structure in the image; extracting a set of features from the shelf tag detected in the image; detecting a promotional tag on the inventory structure in the image; extracting a set of features from the promotional tag detected in the image; detecting a deviation between the shelf tag and the promotional tag based on a difference between the sets of features; and, in response to detecting the deviation between the shelf tag and the promotional tag, identifying the first promotional tag as erroneous, and notifying a store associate to replace the first promotional tag with a second promotional tag at the first slot, the second promotional tag correcting the difference.

Abstract: A system includes an article supply location, wherein the article supply location includes a plurality of articles to be sorted, first and second transport vehicles, each having a first position in which an article is stowed about the vehicle and a second position in which the article is deposited into a proximal container. And a control system. The control system is configured to receive an order for a plurality of disparate articles, determine one destination container of a plurality of destination containers to direct the transport vehicle to deposit a selected article, direct the first transport vehicle to transport a selected article to the destination container and deposit the article by manipulation of the first transport vehicle from the first position to the second position for deposit of the selected article in the destination container.

Abstract: Systems for assessment of weld adjacent heat affected zones are described. An example system may include an inspection robot having a first payload comprising a first plurality of ultrasonic (UT) phased arrays, and a second payload comprising a second plurality of ultrasonic (UT) phased arrays. The inspection robot is configured to move in a direction of travel corresponding to a weld of an inspection surface, and the first payload is structured to measure characteristics of a first region of the inspection surface on a first side of the weld while the second payload is structured to measure characteristics of a second region of the inspection surface on a second side of the weld.

Abstract: Systems and methods for surface fitting of a surface of an object, for path planning, and for processing a surface of a part are disclosed. The method includes receiving, at a processor, a point cloud or a mesh of the surface; dividing, by the processor, the point cloud to a plurality of overlapping sub-patches; determining by the processor, a first Root Mean Squared Error (RMSE) of the overall surface; and in response to the first RMSE being smaller or equal to the user set RMSE, generating, by the processor, coefficients for characterizing the surface.

Abstract: Embodiments described herein include a system of fluid-delivery hardware, including tubes, valves, and pumps that deliver samples of fluid gathered from various exposed locations of a vehicle to commonly located gas analysis sensors. A durable sensor housing contains the gas sensors and is situated in a confined location of the vehicle, which is environmentally isolated and physically partitioned from the sample locations exposed to potentially deleterious environments. For a given sample location, a tube and valves gather and channel fluid samples from the sample location towards the sensor housing at the confined location. A pump forces air outwards to purge debris in the tube or tube inlet, and draws air inward through the tube towards the sensor housing for delivery to the sensors.

Abstract: Systems, apparatus, and methods are described for robotic learning and execution of skills. A robotic apparatus can include a memory, a processor, sensors, and one or more movable components (e.g., a manipulating element and/or a transport element). The processor can be operatively coupled to the memory, the movable elements, and the sensors, and configured to obtain information of an environment, including one or more objects located within the environment. In some embodiments, the processor can be configured to learn skills through demonstration, exploration, user inputs, etc. In some embodiments, the processor can be configured to execute skills and/or arbitrate between different behaviors and/or actions. In some embodiments, the processor can be configured to learn an environmental constraint. In some embodiments, the processor can be configured to learn using a general model of a skill.

Abstract: Systems and methods for training artificial intelligence models based on sequences of image data are disclosed. The techniques described herein include generating, using an artificial intelligence model, a respective classification and a respective bounding box for an object depicted in each image of a sequence of images captured during operation of an autonomous vehicle; tracking the object in the sequence of images based on the respective bounding box of each image of the sequence of images and a tracking identifier corresponding to the object; determining a correction to the respective classification of an image of the sequence of images responsive to tracking the object in the sequence of images; and training the artificial intelligence model based on the correction.

Abstract: Embodiments described herein include an automated vehicle having a pitot tube mounted to a side-view mirror of the automated vehicle. The pitot gathers samples of wind speed information for calculating three-dimensional wind measurements using the information gathered by the pitot tube. The pitot tube is installed at an area that offers the pitot tube access to outside “clean air,” undisturbed by the vehicle's movement. A controller and/or driving software ingest the three-dimensional wind measurements and generate driving tasks of the automated vehicle based upon the three-dimensional wind measurements.

Abstract: Systems and methods for continuously monitoring a workcell during operation of industrial machinery are disclosed. The system may comprise a safety system that includes at least one sensor and supporting software and/or hardware for acquiring image data associated with the workcell; a monitoring system for detecting a parameter value associated with the safety system; and a controller configured to determine a status of the safety system based at least in part on the detected parameter value and cause an alert to be issued if the status of the safety system does not satisfy a target objective.

Abstract: Systems, methods, computing platforms, and storage media for controlling an autonomous inventory management system are disclosed. Exemplary implementations may: direct a first transport system to a first location; determine a respective drop off location for each of the one or more autonomous storage units; determine a boarding order for the one or more autonomous storage units based at least in part on the respective drop off location for each of the one or more autonomous storage units; direct the one or more autonomous storage units to board the first transport system at the first location; and transport the one or more autonomous storage units from the first location to the one or more respective drop off locations.

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 patient cart for a robot surgical system can include a mobile base having a frame adapted and configured to support a medical robot, one or more motive devices operatively connected to the frame, and one or more motors connected to the motive devices to drive the motive devices to move the frame. The patient cart can include a drive control interface connected to the frame and configured to sense a user input and to operate the one or more motors to move the one or more motive devices as a function of the user input.

Abstract: An autonomous earth moving system can determine a desired state for a portion of the EMV including at least one control surface. Then the EMV selects a set of control signals for moving the portion of the EMV from the current state to the desired state using a machine learning model trained to generate control signals for moving the portion of the EMV to the desired state based on the current state. After the EMV executes the selected set of control signals, the system measures an updated state of the portion of the EMV. In some cases, this updated state of the EMV is used to iteratively update the machine learning model using an online learning process.

Abstract: There are disclosed systems and methods for managing object configurations within a structure. For one embodiment, a fixed object profile including dimensions and locations of ventilation of a building space and a non-fixed object profile including dimensions and a location of a non-fixed object are identified. One or more contaminant risk locations of the building space are determined in response to determining the air flow within the building space associated with an HVAC unit. The air flow is determined based on incoming air flow streams to the building space and outgoing air flow streams away from the building space. One or more object positions are provided at an output device based on the contaminant risk location(s). For another embodiment, the contaminant risk location(s) are selected from possible people locations. A person position is displayed at an output device, in proximity to the building space, based on the contaminant risk location(s).

Abstract: A steerable overtube assembly for a robotic surgical system can include a steerable shaft having one or more instrument channel and a control hub configured to mount to the steerable shaft. The assembly can also include a manual actuator extending from the control hub and configured to allow the steerable shaft to be manually steered by a user's hand, and a robotic actuator housed by and/or extending from the control hub configured to connect to a robotic driver to allow robotic steering of the steerable shaft.

Abstract: The disclosure includes embodiments for an analysis system. A method according to some embodiments is executed by a graphics processing unit. The method includes generating input data including image data captured with a monocular camera operating in a field environment wherein the image data describes a two-dimensional image of the field environment. The method includes analyzing the input data to generate output data describing a three-dimensional graphic of the field environment depicted in the two-dimensional image. In some embodiments, the output data localizes objects, such as a mobile field device upon which the monocular camera is mounted, within the field environment. In some embodiments, the output data localizes any tangible object located within the field environment with an accuracy that satisfies a threshold for accuracy. The method includes modifying an operation of an autonomous control system of a mobile field device based on the output data.