A method and system for calculating a minimum distance from a robot to dynamic objects in a robot workspace. The method uses images from one or more three-dimensional cameras, where edges of objects are detected in each image, and the robot and the background are subtracted from the resultant image, leaving only object edge pixels. Depth values are then overlaid on the object edge pixels, and distance calculations are performed only between the edge pixels and control points on the robot arms. Two or more cameras may be used to resolve object occlusion, where each camera's minimum distance is computed independently and the maximum of the cameras' minimum distances is used as the actual result. The use of multiple cameras does not significantly increase computational load, and does require calibration of the cameras with respect to each other.

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.

A method includes receiving position information and force information, providing control commands to a steering mechanism of a continuum manipulator based on the position information and the force information, updating a control matrix based on the position information and the provided control commands, and providing updated control commands to the steering mechanism based on the updated control matrix. A continuum manipulator includes a body, a steering mechanism configured to steer the body, sensors, and a controller. The sensors include a position sensor to detect a position of the body and a force sensor to detect a force against the body. The controller is configured to receive position information from the position sensor and force information from the force sensor, provide control commands to the steering mechanism based on the position information and the force information, and update a control matrix based on the position information and the provided control commands.

A method for modeling a robot simplified for stable walking control of a bipedal robot provides a robot model that is simplified as a virtual pendulum model including a virtual body, two virtual legs connected to the body at a virtual pivot point (VPP) that is set at a position higher than the center of mass (CoM) of the body, and virtual feet connected to the two legs, respectively, to step on the ground. A ground reaction force, which acts on the two legs, acts towards the VPP, thereby providing a restoring moment with respect to the CoM such that stabilization of the posture of the body naturally occurs.

Devices, systems, and methods for providing commanded movement of an end effector of a manipulator while providing a desired movement of one or more joints of the manipulator. Methods include augmenting a Jacobian so that joint movements calculated from the Jacobian perform one or more auxiliary tasks and/or desired joint movements concurrent with commanded end effector movement, the one or more auxiliary tasks and/or desired joint movements extending into a null-space. The auxiliary tasks and desired joint movements include inhibiting movement of one or more joints, inhibiting collisions between adjacent manipulators or between a manipulator and a patient surface, commanded reconfiguration of one or more joints, or various other tasks or combinations thereof. Such joint movements may be provided using joint velocities calculated from the pseudo-inverse solution of the augmented Jacobian. Various configurations for systems utilizing such methods are provided herein.

Systems and methods for calibrating the location of an end effector-carrying apparatus relative to successive workpieces before the start of a production manufacturing operation. The location calibration is performed using a positioning system. These disclosed methodologies allow an operator to program (or teach) the robot motion path once and reuse that path for subsequent structures by using relative location feedback from a measurement system to adjust the position and orientation offset of the robot relative to the workpiece. When each subsequent workpiece comes into the robotic workcell, its location (i.e., position and orientation) relative to the robot may be different than the first workpiece that was used when developing the initial program. The disclosed systems and methods can also be used to compensate for structural differences between workpieces intended to have identical structures.

A medical system includes a manipulator arm including a movable distal portion, a proximal portion coupled to a base, and joints between the distal portion and the base. A processor coupled to the manipulator arm performs operations including calculating a first movement of the joints in a null-space of a Jacobian of the manipulator arm, the first movement being calculated in accordance with a first objective for arm-to-patient collision avoidance. The operations further include calculating a second movement of the joints in the null-space, the second movement being calculated in accordance with a second objective for arm-to-arm collision avoidance, and combining at least the first and second movements into a combined movement in a manner allowing the first objective to overpower the second objective, and driving the joints to effect the combined movement.

A robot control device includes: a first acquisition unit to acquire path information relating to a path of a robot and speed information relating to a speed the robot moves on the path; a second acquisition unit to acquire specification information relating to a specification of the robot; a determination unit to determine a segment where an action time of the robot is shortened even when a waypoint is added on the path; a correction unit to correct the path of the robot so as to make inertia of the robot smaller in a segment where an action time of the robot is shortened; a computation unit to compute a load acting on a joint of the robot; and an adjustment unit to adjust a control amount for controlling an acceleration of the robot joint such that the load computed by the computation unit satisfies a target load.

A method is provided for the alignment of a multiaxial manipulator with an input device, which serves to control the manipulator, which method includes the steps of execution of one or more reference movements with the input device, execution of one or more reference movements with the manipulator, recording of the executed reference movements, calculation of a transformation matrix based on the recorded reference movements, and use of the calculated transformation matrix for the alignment of the movements of the input device with the manipulator.

A robot controller (2) configured to control a robot (1) including a plurality of joints (J.sub.1-J.sub.6) each rotatable around a rotation axis, the robot controller (2) including: an acquisition unit (21) configured to acquire a rotation angle of each of the plurality of joints (J.sub.1-J.sub.6); a determination unit (22) configured to determine whether or not the robot (1) has been in proximity to a singular configuration, based on the rotation angle of each of the plurality of joints (J.sub.1-J.sub.6); and a control unit (23) configured to control the plurality of joints (J.sub.1-J.sub.6) to be rotated not to rotate simultaneously, when the determination unit (22) determines that the robot (1) has been in proximity to the singular configuration.