Abstract: A method of generating robot trajectories for a robot device includes generating surface parameters and/or measurements for the surface of the object; receiving one or more parameters to maximize or minimize robot objectives; receiving one or more motion parameters for the robot to perform the task on the surface of the object and/or receiving one or more workspace parameters; receiving a plurality of constraint parameters; and generating an initial parametric representation of a trajectory for the robot in performing the task. The method further includes generating an initial trajectory based on the initial parametric representation of the trajectory, one or more workspace parameters, the one or more motion parameters, and/or the one or more parameters to maximize or minimize robot objectives; selecting a first set of constraint parameters; and performing trajectory generation by applying the selected first set of constraint parameters to create one or more first robot trajectories.

Abstract: A computing device generates a graphical user interface displaying a three-dimensional representation of the site comprising a position of a vehicle capable of moving material within the site and a target location within the site for the vehicle to move material. The computing device transmits a set of instructions for the vehicle to move a volume of material from the target location. The computing device receives sensor data describing a depth of the target location, a current volume of material moved from the target location, and a position of the vehicle. The graphical user interface displayed on the computing device is modified to display the current depth of the target location, and the position of the vehicle relative to the target location. The computing device modifies the set of instructions based on the received sensor data and provides the modified set of instructions to the vehicle.

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: Provided are systems and methods by which robots predictively detect objects that may obstruct robotic tasks prior to the robots performing those tasks. For instance, a robot may receive a task, and may obtain dimensions of a task object based on a first identifier obtained with the task or with a sensor of the robot. The robot may determine a first boundary for moving the task object based on the task object dimensions and an added buffer of space that accounts for imprecise robotic operation. The robot may detect a second identifier of a neighboring object, and may obtain dimensions of the neighboring object using the second identifier. The robot may compute a second boundary of the neighboring object based on the dimensions of the neighboring object and a position of the second identifier, and may detect an obstruction based on the second boundary crossing into the first boundary.

Abstract: One aspect provides a modular inspection robot for inspecting vertical shafts, chambers or tunnels. An embodiment provides related methods and products. One method includes: capturing, using a plurality of video cameras associated with an infrastructure inspection unit, two or more videos of infrastructure; accessing, using one or more processors, image metadata indicating a mesh of connected vertices based on the two or more videos; selecting, using the one or more processors, image data of frames of the two or more videos for inclusion in an output based on the mesh; and outputting, using the one or more processors, a photo-realistic image of the infrastructure comprising the image data selected. Other examples are described and claimed.

Abstract: Data is received that includes a feed of images of a plurality of objects passing in front of an inspection camera module forming part of a quality assurance inspection system. Within each image, it is detected whether an object is present within the image. Instance identifiers are assigned to each object. A single image is identified in which the object is optimally represented for each object using the corresponding instance identifier. These identified images are provided to a consuming application or process for quality assurance analysis.

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: Airway management methods, devices, assemblies and systems. Methods, devices, assemblies and systems may include robotic movement and control of an intubation tube introducer or guide, and may include utilizing image data from one or more image sensors. The methods, devices, assemblies and systems may optionally be used in endotracheal intubation procedures.

Abstract: An automated robotic depalletizing system includes at least one robot for transferring inventory that arrives on a pallet to different storage locations within a warehouse. The robot may perform the automated depalletizing by moving to the pallet having a stacked arrangement of a plurality of objects, identifying, via a sensor, a topmost object of the plurality of objects, aligning a retriever with the topmost object, engaging the topmost object with the retriever, and transferring the topmost object from the pallet to the robot by actuating the retriever. The automated depalletizing may also be performed via coordinated operations of two or more robots. For instance, a first robot may retrieve objects from the pallet, and a second set of one or more robots may be used to transfer the retrieved objects into storage.

Abstract: One aspect provides a method, including: obtaining sensor data from a ground penetrating radar (GPR) unit; analyzing, using a processor, the sensor data to detect a first object and a second object, the second object being associated with the first object based on location; identifying, with the processor, an underground pipe feature based on the analyzing; associating a position of the underground pipe feature with a location in a pipe network; selecting a subset of the pipe network including a pipe segment associated with the position of the underground pipe feature; and providing the subset of the pipe network as displayable data to a display device. Other aspects are described and claimed.

Abstract: Some embodiments described herein relate to optical systems and methods for determining the shape and/or size of objects that include projecting a pattern of light onto the object. The pattern of light can be configured such that first-order reflections can be distinguished from second- and/or higher-order reflections, which can be rejected. Thus, even in instances in which the pattern of light is reflected onto the object multiple times, the original, or first-order, reflection can be detected, distinguished, and/or used for laser triangulation. In some embodiments, a pattern of light that does not have reflection and/or rotational symmetry is projected onto the object, such that second-order and/or higher-order reflections can be distinguished from the first-order reflection.

Abstract: A dish cart includes a top with a slot for receiving a lift arm that may be lifted up through the slot to raise or lower dishes. Lobe openings emanating from the slot receive lobes of a lift paddle secured to the lift arm. The cart may define a gap below the top for permitting insertion of the lift paddle and the lift arm. The cart may be adjusted to receive differently sized dishes by means of rails of different sizes or adjustable vanes. A dish drop station includes the lift arm and lift paddle and a lift mechanism for raising and lower the lift arm. The dish drop station may include a cart present sensor and include a lock for retaining the cart. The controller may be programmed to the lower the lift arm to an unlock position that disengages the cart lock.

Abstract: Systems and methods for electronically mapping a facility are presented. The method comprises obtaining a CAD file that includes graphical representations of a facility. An occupancy-map image is generated based on the CAD file. A sensor, such as a sensor on a self-driving vehicle, is used to detect a sensed feature within the facility. Based on the sensed feature, the occupancy-map image can be updated, since the sensed feature was not one of the known features in the CAD file prior to the sensed feature being detected by the sensor.

Abstract: A mobile robot is configured for operation in a commercial or industrial setting, such as an office building or retail store. The robot can patrol one or more routes within a building, and can detect violations of security policies by objects, building infrastructure and security systems, or individuals. In response to the detected violations, the robot can perform one or more security operations. The robot can include a removable fabric panel, enabling sensors within the robot body to capture signals that propagate through the fabric. In addition, the robot can scan RFID tags of objects within an area, for instance coupled to store inventory. Likewise, the robot can generate or update one or more semantic maps for use by the robot in navigating an area and for measuring compliance with security policies.

Abstract: An intelligent robotic nursing system includes a robotic medical platform vehicle that autonomously or manually moves within a structure to perform a healthcare task and information system containing data of symptomatic patients from all over the world to assist doctors in early detection of disease and providing effective treatments to patient.

Abstract: An order fulfillment and delivery system for autonomously fulfilling orders while en route to a delivery location. The system includes a delivery vehicle having a storage area, a robotic system at least partially disposed within the storage area and one or more processors. The one or more processors being configured to receive an order of one or more inventory items, generate container retrieval instructions for the robotic system to perform based on the received order and transmit to the robotic system the container retrieval instructions to perform. The robot system includes a container retrieval device movable in at least two dimensions to engage and move a container, based upon the container retrieval instructions, from a first location within the delivery vehicle to a second location within the delivery vehicle.

Abstract: System for guiding an instrument within a vascular network of a patient are disclosed. In some embodiments, the system receives a medical image from a medical imaging device and identifies a distal tip and a direction the instrument in the image. The system may then determine a waypoint for the distal tip of the instrument based at least in part on the position and direction of the distal tip of the instrument. The system may then generate a trajectory command for moving the instrument through the vascular network from the current position to the waypoint. The system may operate in a closed loop. The system may provide the trajectory command to a robotic medical system configured to move the instrument according to the command.