A method for teaching and controlling a robot to perform an operation based on human demonstration with images from a camera. The method includes a demonstration phase where a camera detects a human hand grasping and moving a workpiece to define a rough trajectory of the robotic movement of the workpiece. Line features or other geometric features on the workpiece collected during the demonstration phase are used in an image-based visual servoing (IBVS) approach which refines a final placement position of the workpiece, where the IBVS control takes over the workpiece placement during the final approach by the robot. Moving object detection is used for automatically localizing both object and hand position in 2D image space, and then identifying line features on the workpiece by removing line features belonging to the hand using hand keypoint detection.

The disclosure provides a communication system and a gripping system. When two or more nodes transmit the frames at the same time, a communication system performs, among the nodes starting transmission at the same time, communication arbitration by stopping transmission except for the node transmitting the frame having a highest priority. The frame ID includes a type ID indicating a type of the node that is a transmission source, a change ID changeable by the node that is the transmission source, and a fixed ID specific to the node that is the transmission source. The type includes a master and slaves. When the type ID is the master, a priority of the frame is set higher than when the type ID is the slave. The master node is capable of transmitting to the bus an instruction signal instructing the slave node to change the change ID.

Example implementations may relate to methods and systems for determining a safe trajectory for movement of an object by a robotic system. According to these various implementations, the robotic system may determine at least first and second candidate trajectories for moving the object. For at least a first point along the first candidate trajectory, the robotic system may determine a predicted cost of dropping the object at the first point along the first candidate trajectory. And for at least a second point along the second candidate trajectory, the robotic system may determine a predicted cost of dropping the object at the second point along the second candidate trajectory. Then, based on these various determined predicted costs, the robotic system may select between the first and second candidates trajectories and may then move the object along the selected trajectory.

A position and an orientation of an object are measured with high accuracy. An approximate position-orientation of a target object is obtained, positional information of the target object is obtained by measuring the target object using a noncontact sensor, positional information of contact positions touched by a contact sensor is obtained by bringing the contact sensor into contact with the target object, and a position-orientation of the target object is obtained by associating shape information of the target object with the positional information of the target object and the positional information of the contact positions in accordance with the approximate position-orientation.

A liquid transport method is disclosed for efficiently producing cell cultures. The liquid transport method of the present disclosure, which is in processing of cells, includes: a) a step in which a container holding a liquid is gripped by a gripping tool of a robot; and b) a step in which the liquid in the container is transported to a collection container by rotating the gripped container. In steps a) and b) the robot operates such as not to pass over a vertical line of an opening of the collection container.

A method and apparatus for dispensing and retrieving products is provided. A system may include: a grasping head; first and second grasping members, each grasping member comprising: a top member; a post member; and first and second grasping fingers, where the first and second grasping fingers extend from the post member and are spaced apart from the top member by a predetermined distance, where the first and second grasping members are connected to the grasping head, where at least one of the first and second grasping members is movably connected to the grasping head, where the at least one of the first and second grasping members is movable relative to the other of the first and second grasping members.

A robotic grasp generation technique for part picking applications. Part and gripper geometry are provided as inputs, typically from CAD files. Gripper kinematics are also defined as an input. A set of candidate grasps is provided using any known preliminary grasp generation tool. A point model of the part and a model of the gripper contact surfaces with a clearance margin are used in an optimization computation applied to each of the candidate grasps, resulting in an adjusted grasp database. The adjusted grasps optimize grasp quality using a virtual gripper surface, which positions the actual gripper surface a small distance away from the part. A signed distance field calculation is then performed on each of the adjusted grasps, and those with any collision between the gripper and the part are discarded. The resulting grasp database includes high quality collision-free grasps for use in a robotic part pick-and-place operation.

An industrial robot continuously and automatically executes a teaching step of learning a hand position that is the position of a hand when mounting a transported object to be placed in a predetermined position on a placing section, and a calibration step of correcting the hand position learned in the teaching step. In the calibration step, the hand is moved to the hand position identified in the teaching step, and a transported object for teaching placed in the predetermined position is mounted and taken out onto the hand. Thereafter, the hand is moved again to the hand position identified in the teaching step and the transported object for teaching is placed on the placing section. Afterward, the position of the transported object for teaching is detected by second sensors attached to the hand and the hand position is corrected based on the detection result by the second sensors.

A method for palletizing by a robot includes positioning an object at an initial position adjacent to a target object location, tilting the object at an angle relative to a ground plane, shifting the object in a first direction from the initial position toward a first alignment position, shifting the object in a second direction from the first alignment position toward a second alignment position, and releasing the object from the robot to pivot the object toward the target object location.

A self-contained truck-mounted brick laying machine can include a frame that can support packs or pallets of bricks placed on a platform. A transfer robot can pick up and move the brick(s). A carousel can be coaxial with a tower. The carousel can transfer the brick(s) via the tower to an articulated and/or telescoping boom. The bricks can be moved along the boom by, e.g., linearly moving shuttles, to reach a brick laying and adhesive applying head. The brick laying and adhesive applying head can mount to an element of the stick, about an axis which is disposed horizontally. The poise of the brick laying and adhesive applying head about the axis can be adjusted and can be set in use so that the base of a clevis of the robotic arm mounts about a horizontal axis, and the tracker component is disposed uppermost on the brick laying and adhesive applying head. The brick laying and adhesive applying head can apply adhesive to the brick and can have a robot that lays the brick. Vision and laser scanning and tracking systems can be provided to allow the measurement of as-built slabs, bricks, the monitoring and adjustment of the process and the monitoring of safety zones. The first, or any course of bricks can have the bricks pre machined by the router module so that the top of the course is level once laid.