A robot including: a robot body that includes an arm having a longitudinal axis, and at least one joint; and a proximity sensor unit that detects an object approaching the arm of the robot body. The proximity sensor unit includes: a support member that is fixed to the arm of the robot body and that is disposed, at such a position as to extend across the joint of the robot body, so as to be away from a surface of the arm in a direction perpendicular to the longitudinal axis of the arm; and a plurality of proximity sensors that are attached to the support member.

A robot includes a sensor including an electrode portion of a sensor for detecting approach of or contact with another object is formed on an outer surface or an inner surface of an exterior member, and in which a drive unit of the robot main body is controlled so as to avoid approach between the robot body and the other object based on an output signal of the sensor.

A robot including: a robot body that includes an arm having a longitudinal axis, and at least one joint; and a proximity sensor unit that detects an object approaching the arm of the robot body. The proximity sensor unit includes: a support member that is fixed to the arm of the robot body and that is disposed, at such a position as to extend across the joint of the robot body, so as to be away from a surface of the arm in a direction perpendicular to the longitudinal axis of the arm; and a plurality of proximity sensors that are attached to the support member.

An anti-collision method for robot is provided. The method controls a robot to sense a variation of electric field over continuous time via electric field sensor, determine a relative moving direction of an obstacle when detecting the obstacle by the variation of electric field, generate motor control data according to the relative moving direction of the obstacle, and control a motor to rotate according to the motor control data for making a robotic limb move along a dodge vector to dodge the obstacle. The anti-collision method can effectively make the robot dodge automatically before a collision, and prevent the robot or the obstacle from crash and damage.

A robot includes a sensor including an electrode portion of a sensor for detecting approach of or contact with another object is formed on an outer surface or an inner surface of an exterior member, and in which a drive unit of the robot main body is controlled so as to avoid approach between the robot body and the other object based on an output signal of the sensor.

An apparatus for collision avoidance by surface proximity detection includes a plurality of piezoelectric elements disposed adjacent to a surface of an object, a memory storing instructions, and at least one processor configured to execute the instructions to control a first one among the piezoelectric elements to generate an acoustic wave along the surface of the object, and receive, via a second one among the piezoelectric elements, an acoustic wave signal corresponding to the generated acoustic wave. The at least one processor is further configured to execute the instructions to filter the received acoustic wave signal, using a band-pass filter for reducing noise of the received acoustic wave signal, obtain a proximity signal for proximity detection, from the filtered acoustic wave signal, using a linear time-invariant filter, and detect whether an obstacle is proximate to the surface of the object by inputting the obtained proximity signal into a neural network.

An apparatus for collision avoidance by surface proximity detection includes a plurality of piezoelectric elements disposed adjacent to a surface of an object, a memory storing instructions, and at least one processor configured to execute the instructions to control a first one among the piezoelectric elements to generate an acoustic wave along the surface of the object, and receive, via a second one among the piezoelectric elements, an acoustic wave signal corresponding to the generated acoustic wave. The at least one processor is further configured to execute the instructions to filter the received acoustic wave signal, using a band-pass filter for reducing noise of the received acoustic wave signal, obtain a proximity signal for proximity detection, from the filtered acoustic wave signal, using a linear time-invariant filter, and detect whether an obstacle is proximate to the surface of the object by inputting the obtained proximity signal into a neural network.

A robot system for human-robot collaboration is disclosed that includes one or more proximity sensing elements disposed on the movable parts of the robot, joint position sensing sensors, and a safety control module connects the proximity sensing element and joint position sensing sensors and monitors the speed of the robot and the proximity distance to the objects and stop the robot safely when speed exceed the set limit. The safety control module switches the safety status of the robot when a set proximity distance threshold is triggered. Then, multiple embodiments of the safety status triggered by proximity sensing are introduced for different processes of the human-robot collaboration, includes separation monitoring, force limiting for bumping, and manipulation of the robot. Furthermore, embodiments of utilizing different types of sensors to implement the proximity sensing elements are also disclosed.