A robot includes a body on which is mounted a functional head also including a capacitive detector, including: at least one electrical insulator in order to electrically insulate the functional head; at least one apparatus for electrically polarizing the functional head at a first alternating electrical potential (V.sub.g), different from a ground potential; at least one guard polarized at an alternating guard potential (V.sub.G) identical to the first alternating electrical potential; and at least one electronics, called detection electronics, for measuring a signal relating to a coupling capacitance, called electrode-object capacitance, between the sensitive part and a surrounding object.

Accuracy in interference determination between a hand gripping a workpiece and nearby objects is increased. An information processing apparatus includes a measuring unit configured to decide an object to be gripped among a plurality of objects on the basis of a first image of the imaged objects, a specifying unit configured to specify an attention area for determining, when a gripping device grips the object to be gripped, whether the gripping device interferes with objects near the object to be gripped, a controller configured to change an imaging range of an imaging device on the basis of the attention area, and a determination unit configured to determine, when the gripping device grips the object to be gripped, whether the gripping device interferes with the objects near the object to be gripped on the basis of a second image of an object imaged in a changed imaging range.

The partitioning method for a working space of a robot includes defining the working space of the robot; setting a plurality of partitioning planes based on at least three non-collinear points in the working space; if the setting of the plurality of partitioning planes is completed, defining partitioning lines by intersecting the plurality of partitioning planes; dividing the plurality of partitioning planes into a plurality of designated sections and a plurality of extended sections based on the partitioning lines; combining the plurality of designated sections for constructing a full partitioning plane; partitioning the working space into two working regions based on the full partitioning plane; and setting the working region containing an origin of the robot as an operation region. Therefore, the partitioning process can be simplified.

To provide a robot system capable of ensuring safety while giving consideration to the occurrence of a trouble in image capture means. A robot system with a camera for monitoring a robot comprises: current position model generation means that generates a current position model for the robot based on current position data about the robot and robot model data about the robot; simulation image generation means that generates a simulation image of the robot viewed from the direction of the camera based on set position data about the camera, set position data about the robot, and the current position model; detection means that compares the simulation image and a monitoring image acquired from the camera to detect the robot in the monitoring image; and safety ensuring means that ensures the safety of the robot system if the detection means does not detect the robot in the monitoring image.

A machine learning method includes: a first learning step which is performed in a phase before a neural network is installed in a mobile robot and in which a stationary first obstacle is placed in a set space and the first obstacle is placed at different positions using simulation so that the neural network repeatedly learns a path from a starting point to the destination which avoids the first obstacle; and a second learning step which is performed in a phase after the neural network is installed in the mobile robot and in which, when the mobile robot recognizes a second obstacle that operates around the mobile robot in a space where the mobile robot moves, the neural network repeatedly learns a path to the destination which avoids the second obstacle every time the mobile robot recognizes the second obstacle.

A robot system includes a robot and a motion control unit. The robot includes a bottom, a swiveling base, first to third arms. A bottom side of the first arm is supported on the swiveling base swivelably around a horizontal-direction second axis. A bottom side of the redundant arm is supported on a leading side of the first arm swivelably around an axis parallel to the second axis. A bottom side of the second arm is supported on a leading side of the redundant arm swivelably around a third axis parallel to the second axis. A bottom side of the third arm is supported on a leading side of the second arm rotatably around a fourth axis perpendicular to the third axis. The motion control unit activates the redundant arm so that a control point provided on the fourth axis linearly moves while maintaining a direction of the fourth axis.

A system includes a robotic vehicle having a propulsion and a manipulator configured to perform designated tasks. The system also including a local controller disposed onboard the robotic vehicle and configured to receive input signals from an off-board controller. Responsive to receiving an input signal for moving in an autonomous mode, the local controller is configured to move the robotic vehicle toward one of the different final destinations by autonomously and iteratively determining a series of waypoints until the robotic vehicle has reached the one final destination. For each iteration, the local controller is configured to determine a next waypoint between a current location of the robotic vehicle and the final destination, determine movement limitations of the robotic vehicle, and generate control signals in accordance with the movement limitations.

A sensorless collision detection method of robotic arm based on motor current includes acquiring an output current of a robotic arm joint motor; building a neural network, and using a backpropagation algorithm to update the weights and the deviations of the neural network to obtain an estimated current value; judging whether collision occurs by comparing the collision detection threshold with the error value between the output current of the robotic arm joint motor and the estimated output current of the neural network. The detection method is easy to operate and has higher universality.

A flexible manipulator apparatus includes an elongate flexible manipulator having a sensor, a user output device configured to provide sensory outputs to the user, and processing circuitry. The flexible manipulator may be movable to form a curve in the flexible manipulator. The processing circuitry may be configured to receive captured sensor data from the sensor during movement of the flexible manipulator, and determine a collision likelihood score based on application of the captured sensor data to a collision detection model used for position estimation. The collision detection model may be based on an empirical data training for the flexible manipulator that includes training sensor data from the sensor and training image data of positions of the flexible manipulator. The processing circuitry may be configured to control the user output device based on the collision likelihood score to provide a collision alert sensory output to the user.

A robot system includes a robot, a teach pendant having an operator interface, and a robot controller with a computer and associated hardware and software containing a virtual representation of the robot and the environment. The system employs a method for avoiding collisions including moving a manipulator arm along an actual path in an environment containing objects constituting collision geometry. Operator input is entered into the teach pendant, whereby the operator is able to directly control motion of the robot along the actual path. A recent history of the motion of the robot is recorded, and a predicted path of the robot is developed based on the input entered into the teach pendant and the recent history of the motion of the robot. Real-time collision checking between the predicted path and the collision geometry is performed while the operator manually controls the robot using the teach pendant.