A position/force controller includes a function-dependent force/speed distribution conversion unit that, on the basis of speed, position and force information relating to a position based on an action of an actuator and control reference information, performs a conversion to distribute control energy to at least one of speed or position energy and force energy according to a function that is being realized. A control amount calculation unit calculates at least one of a speed or position control amount and a force energy on the basis of at least one of the speed or position energy and the force energy distributed by the force/speed distribution conversion unit. An integration unit integrates speed or position control amount with force control amount and, to return an output to the actuator, performs a reverse conversion on the speed or position control amount and the force control amount and determines an input to the actuator.

A system includes: a hand module to, based on a demonstration of a human hand grasping an object, determine first and second vectors that are normal to and parallel to a palm of the human hand, respectively, and a position of the human hand; a gripper module to determine third and fourth vectors that are normal to and parallel to a palm of a gripper of a robot, respectively, and a present position of the gripper; and an actuation module to: move the gripper when open such that the present position of the gripper is at the position of the human hand, the third and first vectors are aligned, and the fourth and second vectors are aligned; close fingers of the gripper based on minimizing a first loss; and actuate the fingers of the gripper to minimize a second loss determined based on the first loss and a third loss.

Apparatus, systems, methods, and articles of manufacture for automatic robot perception programming by imitation learning are disclosed. An example apparatus includes a percept mapper to identify a first percept and a second percept from data gathered from a demonstration of a task and an entropy encoder to calculate a first saliency of the first percept and a second saliency of the second percept. The example apparatus also includes a trajectory mapper to map a trajectory based on the first percept and the second percept, the first percept skewed based on the first saliency, the second percept skewed based on the second saliency. In addition, the example apparatus includes a probabilistic encoder to determine a plurality of variations of the trajectory and create a collection of trajectories including the trajectory and the variations of the trajectory. The example apparatus also includes an assemble network to imitate an action based on a first simulated signal from a first neural network of a first modality and a second simulated signal from a second neural network of a second modality, the action representative of a perceptual skill.

A position/force controller includes a function-dependent force/speed distribution conversion unit that, on the basis of speed, position and force information relating to a position based on an action of an actuator and control reference information, performs a conversion to distribute control energy to at least one of speed or position energy and force energy according to a function that is being realized. A control amount calculation unit calculates at least one of a speed or position control amount and a force energy on the basis of at least one of the speed or position energy and the force energy distributed by the force/speed distribution conversion unit. An integration unit integrates speed or position control amount with force control amount and, to return an output to the actuator, performs a reverse conversion on the speed or position control amount and the force control amount and determines an input to the actuator.

Robotic arms or manipulators can be utilized to grasp inventory items within an inventory system. Information can be obtained about constraints relative to relevant elements of a process of transferring the item from place to place. Examples of such elements may include a grasping location from which an item is to be grasped, a receiving location in which a grasped item is to be placed, or a space between the grasping location and the receiving location. The information about the constraints can be used to select from multiple possible grasping options, such as by eliminating options that conflict with the constraints or preferring options that outperform others given the constraints.

A position/force controller performs: detecting information relating to a position based on the effect of an actuator; converting by distributing control energy to speed or positional energy and force energy in response to functions realized on the basis of speed (position) and force information corresponding to the information relating to the position and on the basis of information serving as a reference for control; calculating the control amount for speed or position on the basis of the speed or positional energy; calculating the force control amount on the basis of the force energy; and integrating the speed or position control amount and the force control amount and performing a reverse conversion on the speed or position control amount and the force control amount to return the output to the actuator, to determine the input to the actuator.

Systems and methods for optimizing body and object interactions are provided. Based on obtained contact pressure maps and coefficient of friction (COF) maps at a contact interface where at least a portion of a body is in physical contact with a surface of an object, friction force maps can be determined, which can be used to optimize body and object interactions.

A device includes: an image data acquisition unit that acquires, when a robot is grasping a workpiece by a hand, image data of the workpiece imaged by a visual sensor disposed at a known position on a control coordinate system; a workpiece position acquisition unit that acquires workpiece position data indicating a position and a posture of the workpiece on the basis of the image data; a hand position acquisition position that acquires hand position data indicating a position and a posture of the hand obtained when the visual sensor has imaged the image data; and a teaching position acquisition unit that acquires, on the basis of the workpiece position data and the hand position data, teaching position data indicating a positional relationship between the hand and the workpiece obtained when the visual sensor has imaged the image data.

Robotic arms or manipulators can be utilized to grasp inventory items within an inventory system. Information can be obtained about constraints relative to relevant elements of a process of transferring the item from place to place. Examples of such elements may include a grasping location from which an item is to be grasped, a receiving location in which a grasped item is to be placed, or a space between the grasping location and the receiving location. The information about the constraints can be used to select from multiple possible grasping options, such as by eliminating options that conflict with the constraints or preferring options that outperform others given the constraints.

Robotic arms or manipulators can be utilized to grasp inventory items within an inventory system. Information can be obtained about constraints relative to relevant elements of a process of transferring the item from place to place. Examples of such elements may include a grasping location from which an item is to be grasped, a receiving location in which a grasped item is to be placed, or a space between the grasping location and the receiving location. The information about the constraints can be used to select from multiple possible grasping options, such as by eliminating options that conflict with the constraints or preferring options that outperform others given the constraints.