A monitoring method for a robot. The actual internal loads are measured with a sensor at a reference point of the robot and are compared with the expected internal loads. The expected internal loads are calculated using the movement of the robot and a dynamic model. It is possible to estimate which external forces act on the robot by comparing the actual and expected internal loads. The signal characteristics of different signal components in the signal of the estimated external forces are used to differentiate between said signal components.

The present invention is directed to a method for mitigation of the damages in case of accidental collisions in a machine tool comprising a computer numerical control (CNC) and a plurality of axes, wherein the occurrence of collisions is monitored, comprises: identifying a first axis being an axis at which a collision is first detected, identifying a second axis being an axis parallel to said first axis, and determining if both or one or none of the axes are resting. If both are resting unlocking the first axis or both axes. If the first axis or second axis is not resting, then the moving axis is defined as the collider, and said moving axis is braked, and simultaneously the resting axis is unlocked or stepped away or held in position. If both axes are moving, defining a collider axis based on said identified first axis at which a collision has been first detected, braking said collider axis and simultaneously unlocking or stepping away the axis parallel to said collider axis.

A robotic tube bending machine is disclosed. The machine includes a tube feeding tray to load tubes. The pneumatic feed separator comprising two jaws to move in a reciprocating motion to separate each tube for sequential operation. The machine includes a robotic arm assembly in communication with a controller and includes a robotic arm and a pneumatic gripper and two gripper fingers to pick each tube from the tray by simultaneous movement of multiple axis of the robotic arm to reach a three-dimensional coordinate. The collision detection module to detect presence of the robotic arm across a non-intended area by measuring force of the robotic arm and deactivate the robotic arm upon detecting a condition of collision. The machine includes a bending die to clamp each tube and a pressure die to apply pressure on the bending die to bend each tube in intricate three dimensional shapes by rotating the tubes at predefined angles by maneuvering the robotic arm.

A collision position estimation device allowing extraction of data related to a torque of a section related to collision of a cushion member includes a machine learning device. The machine learning device includes a state observation unit for observing axis movement data indicating information related to movement of the axis and motor torque data indicating data related to torque of a motor driving the axis as a state variable representing a current state of an environment, a label data acquisition unit for acquiring collision position data indicating the position of the axis during collision of the cushion member as label data, and a learning unit for associating and learning the information related to movement of the axis and the data related to the torque of the motor driving the axis with the position of the axis during collision of the cushion member using the state variable and the label data.

A computer-implemented method of determining a collision between an object and a robot, comprises monitoring one or more articular parts of the robot by measuring the parameters associated with the real displacements of the one or more articular parts; comparing the measured parameters with the expected parameters associated with the corresponding commanded displacements; and determining the probability of a collision with an object. Described developments comprise the exclusion of system failures, the identification of the collided object by computer vision or by communicating with the object, the execution of one or more actions such as a safety mode, the identification of systematic discrepancies in performed comparisons, the grouping of articular parts belonging to a same articular chain, and the mutual surveillance of robots. The use of capacitive sensors, bumper sensors and magnetic rotary encoders is disclosed.

Provided is a robot including: a robot body that is provided with at least one arm; a gas spring that functions as a balancer for the arm of the robot body; an internal-pressure detecting unit that detects a cylinder internal pressure of the gas spring; and a control device that controls the robot body. The control device calculates, as an estimated disturbance value, the difference between a torque command value for a servomotor that drives the arm and a torque of the servomotor that is required to actually operate the arm, determines that the robot body has had a collision when the estimated disturbance value exceeds a predetermined threshold, and corrects the estimated disturbance value or the threshold on the basis of the cylinder internal pressure detected by the internal-pressure detecting unit.

Method for collision monitoring for a periodically moving, electrically driven component of a container handling machine with another component, wherein a limit value for a measured variable that is indicative of a collision between the components is stipulated that, when exceeded, prompts the drive of the component to be shut down, characterized in that the limit value for the measured variable is determined dynamically for a current period of the movement of the component on the basis of the measured variable measured during a preceding period, and a container handling machine designed to perform the method.

A method for detecting a collision of a robot arm with an object and a correspondingly configured robot. The robot arm is a part of the robot and includes a plurality of serially arranged links mounted relative to respective axes, and position sensors allocated to the individual axes are provided for determining the poses of any two adjacent links relative to one another. The robot further includes an electronic control device connected to the positioning devices, and actuators controlled by the electronic control device for automatically moving the links. The method includes evaluating whether at least one invariant for a target movement of the robot arm is satisfied by an actual movement of the robot arm and, when the evaluation results in a non-satisfaction of the at least one invariant, then indicating a collision of the robot arm with the object and initiating a safety function of the robot.

A control system (10) according to the present invention includes a robot arm (11) provided in a manner capable of moving in a given space, a motor (14) for operating the robot arm (11), a torque adjustment device (16) for operating in a manner capable of adjusting a transmitted torque that is transmitted from the motor (14) to the robot arm (11), and a control device (19) for performing operation control of the robot arm (11). The robot arm (11) is provided with a gravity-compensating mechanism (12) for cancelling an effect of gravity due to the robot arm (11), and the control device (19) commands adjustment of the transmitted torque at the torque adjustment device (16), without taking into account the effect of the gravity of the robot arm (11).

A monitoring device of a robot system including: a current sensor detecting a value of a current flowing through the servo motor; a current/torque converting the value of the current flowing through the servo motor which is detected by the current sensor into a torque value; a driving torque estimating section estimating at least a part of driving torque required to drive the servo motor; a differential torque calculating differential torque between the torque value obtained by conversion in the current/torque converting section and an estimated value of the driving torque; an external force converting the differential torque calculated by the differential torque calculating section into an external force applied to the robot; and a stop signal generating section which generates to stop the robot based on a value of the external force obtained by conversion in the external force converting section, and supplies the stop signal to the controller.