A tendon-driven robotic gripper is disclosed for performing fingertip and enveloping grasps. One embodiment comprises two fingers, each with two links, and is actuated using a single active tendon. During unobstructed closing, the distal links remain parallel, creating exact fingertip grasps. Conversely, if the proximal links are stopped by contact with an object, the distal links start flexing, creating a stable enveloping grasp. The route of the active tendon and the parameters of the springs providing passive extension forces are optimized in order to achieve this behavior. An additional passive tendon is disclosed that may be used as a constraint preventing the gripper from entering undesirable parts of the joint workspace. A method for optimizing the dimensions of the links in order to achieve enveloping grasps of a large range of objects is disclosed and applied to a set of common household objects.

A tendon-driven robotic gripper is disclosed for performing fingertip and enveloping grasps. One embodiment comprises two fingers, each with two links, and is actuated using a single active tendon. During unobstructed closing, the distal links remain parallel, creating exact fingertip grasps. Conversely, if the proximal links are stopped by contact with an object, the distal links start flexing, creating a stable enveloping grasp. The route of the active tendon and the parameters of the springs providing passive extension forces are optimized in order to achieve this behavior. An additional passive tendon is disclosed that may be used as a constraint preventing the gripper from entering undesirable parts of the joint workspace. A method for optimizing the dimensions of the links in order to achieve enveloping grasps of a large range of objects is disclosed and applied to a set of common household objects.

A mechanical hand is provided that can increase the operation stroke and also the gripping force of a pair of gripping members. The hand includes first and second sliders, a driving source, a rotating plate, a first clamping link. Of these components, the first and second sliders are provided on a hand body so as to be linearly movable in opening and closing directions and the driving source is provided in the hand body. The rotating plate is rotatably driven by the driving source. The first clamping link is linked with the rotating plate so as to be only rotatable on a first shaft, and is linked with the first slider so as to be only rotatable on a second shaft. Moreover, the second clamping link is linked with the rotating plate so as to be only rotatable on a third shaft, and is linked with the second slider so as be only rotatable on a fourth shaft. The first and second sliders move linearly in the opening and closing directions by making the driving source rotate the rotating plate.

A robot tendon system having a robot arm having an exterior surface, and further rigid elements, each of which is moveably attached to the robot arm or to another of the further rigid elements. Further, a tendon retaining element defines a set of closed channels, and has a major exterior surface that is attached to the major surface of the robot arm. Finally, tendons extend through the closed channels and are attached to the rigid elements.

A tendon-driven robotic gripper is disclosed for performing fingertip and enveloping grasps. One embodiment comprises two fingers, each with two links, and is actuated using a single active tendon. During unobstructed closing, the distal links remain parallel, creating exact fingertip grasps. Conversely, if the proximal links are stopped by contact with an object, the distal links start flexing, creating a stable enveloping grasp. The route of the active tendon and the parameters of the springs providing passive extension forces are optimized in order to achieve this behavior. An additional passive tendon is disclosed that may be used as a constraint preventing the gripper from entering undesirable parts of the joint workspace. A method for optimizing the dimensions of the links in order to achieve enveloping grasps of a large range of objects is disclosed and applied to a set of common household objects.

Dual load lock chambers for use in a multi-chamber processing system are disclosed herein. In some embodiments, a dual load lock chamber, includes a first load lock chamber having a first interior volume and a first substrate support, wherein the first substrate support includes a first plurality of support surfaces vertically spaced apart by a first predetermined distance; at least one heat transfer device disposed within the first substrate support to heat or cool the first plurality of substrates; and a second load lock chamber disposed adjacent to the first load lock chamber and having a second interior volume and a second substrate support, wherein the second substrate support includes a second plurality of support surfaces vertically spaced apart by a second predetermined distance that less than the first predetermined distance.

An instrument driver comprises a base and a jaw assembly coupled to the base. The jaw assembly includes a first jaw having a gripping surface and a second jaw having a gripping surface. The instrument driver further comprises a driver assembly operably coupled to the jaw assembly to advance an elongated member relative to the base by translating the first and second jaws toward each other, thereby closing the jaw assembly and gripping the member between the respective gripping surfaces of the first and second jaws, translating the jaw assembly in a first axial direction when the jaw assembly is closed, translating the first and second jaws away from each other, thereby opening the jaw assembly and releasing the member from between the respective gripping surfaces of the first and second jaws, and translating the jaw assembly in a second axial direction when the jaw assembly is opened.

A robotic surgical instrument comprising: a shaft; an articulation at a distal end of the shaft configured to articulate an end effector, the articulation driveable by a pair of driving elements; and an instrument interface at a proximal end of the shaft, the instrument interface comprising: an instrument interface element configured to drive the pair of driving elements, the instrument interface element displaceable over a displacement range, the pair of driving elements fast with the instrument interface element such that a displacement of the instrument interface element is transferred to the pair of driving elements; a tensioning mechanism configured to tension the pair of driving elements; and an alignment mechanism configured to set the displacement position of the instrument interface element to a predetermined alignment position when the end effector has a predetermined configuration, the alignment mechanism being independent of the tensioning mechanism.

A tendon-driven robotic gripper is disclosed for performing fingertip and enveloping grasps. One embodiment comprises two fingers, each with two links, and is actuated using a single active tendon. During unobstructed closing, the distal links remain parallel, creating exact fingertip grasps. Conversely, if the proximal links are stopped by contact with an object, the distal links start flexing, creating a stable enveloping grasp. The route of the active tendon and the parameters of the springs providing passive extension forces are optimized in order to achieve this behavior. An additional passive tendon is disclosed that may be used as a constraint preventing the gripper from entering undesirable parts of the joint workspace. A method for optimizing the dimensions of the links in order to achieve enveloping grasps of a large range of objects is disclosed and applied to a set of common household objects.

Deep machine learning methods and apparatus related to manipulation of an object by an end effector of a robot. Some implementations relate to training a semantic grasping model to predict a measure that indicates whether motion data for an end effector of a robot will result in a successful grasp of an object; and to predict an additional measure that indicates whether the object has desired semantic feature(s). Some implementations are directed to utilization of the trained semantic grasping model to servo a grasping end effector of a robot to achieve a successful grasp of an object having desired semantic feature(s).