Abstract: This disclosure presents a novel smart complementary metal oxide semiconductor (CMOS) sensor that can detect the “bright” pixels and export the light intensity and location of the selected pixels only. The detecting function is achieved by applying a thresholding criteria method. A novel CMOS architecture is proposed. The FPA-implemented COMS is shared by two sets of column processing circuitry for selecting, processing and exporting the data from top half and bottom half of FPA respectively. The CMOS architecture comprises a re-routing scheme, multiple I/Os deployment, parallel-shifting FIFO memory buffers, and interleaved timing scheme.

Abstract: The present application relates to methods, devices and systems for transparent object three-dimensional reconstruction. The system comprises a structure light generation module, an image acquisition module, a control module and a computing module. The computing module acquires image pairs from the image acquisition module; calculates three-dimensional positions of points according to the image pairs; and performs refinement process to extract first-reflection points. The refinement process comprising: when reflection points are obtained by a first camera, the points include a first point and a second point, the first point is closer to reflection spot of laser on galvanometer mirror than the second point, remove the second point; when the first point is not obtained by a second camera, remove the first point; when the second point is obtained by the second camera, retrieve the second point, and when a discrete external virtual contour is formed, remove the discrete external virtual contour.

Abstract: Aligning a source and target model includes calculating a shape descriptor for a plurality of edge points, grouping the edge points by shape descriptor and selecting representative points for each group. Target and source point pair features (PPFs) are calculated between pairs of representative points on the target and source models, where PPFs defines the relative position and orientation of point pairs. Target PPFs are matched with each source PPF and the point pairs associated with the matched PPFs are transformed to align the location and edge direction of a target PPF point with the location and edge direction of a source PPF point. An angle is determined to align the second target PPF point with the second source PPF point, and a modal angle is found among the determined rotation angles. An output transformation is calculated using the transformations associated with the modal angle.

Abstract: One example embodiment is a robotic end effector, comprising: (a) a soft gripper and (b) an electro-hydraulic actuator assembly. The soft gripper comprises: a gripper body comprising a finger connecting portion; and at least two fingers connected to the finger connecting portion. The gripper body further comprises a gripper cavity therein. The finger connecting portion and the at least two fingers define a working space therewithin, the working space comprises an opening between proximal ends of the at least two fingers. Each of the at least two fingers further comprises a finger barb substantially extending into the opening to partially close up the opening. The electro-hydraulic actuator assembly comprises: an actuator that is operatively driven by an electric motor; and a chamber that comprises a chamber variable volume controlled by the actuator. The chamber variable volume is in liquid communication with the gripper cavity to form a closed space filled with a liquid.

Abstract: A Pilates chair exercise apparatus has a frame configured to rest on a horizontal surface, an inverted Y shaped seat support member fastened to an upper portion of the frame, a seat fastened to an upper end of the seat support, and a pair of parallel arms each having a proximal end fastened to the frame and a foot support fastened to a distal end of the arm, wherein each arm is biased away from the frame. A rotary torque unit mounted to the frame beneath the seat biases each of the arms. The rotary torque unit includes a rotary spring cassette that carries a plurality of flat coil springs each having only one end fastened to an axle at one end of one of the arms. Combinations of the springs in the spring cassette may be user selected without the user leaving the seat of the chair exercise apparatus.

Abstract: In one aspect, provided is a robotic end effector, comprising a palm; a plurality of robotic fingers that are operatively connected to the palm, each finger comprising: a finger base having a proximal end portion that is operatively connected to the palm and an opposing, distal end portion; and a suction cup, wherein each of the plurality of fingers is operatively connected to the palm at the proximal end portion and is configured to be rotatable and/or movable relative to the palm, and wherein the suction cup is configured to be movable about a pivot of the distal end portion. Other example embodiments are described herein. In certain embodiments, the disclosure provides a versatile, multi-modal robotic end effector for grasping with enhanced picks per hour (PPH).

Abstract: This application discloses image coding methods and apparatuses. One method comprises obtaining a plurality of groups of human skeleton data associated with performing an action by a human body, wherein each group of the plurality of groups of human skeleton data comprises joint data associated with a joint for performing the action. Based on joint data comprised in at least a portion of the plurality of groups of human skeleton data, a motion feature corresponding to the plurality of groups of human skeleton data is extracted, and the motion feature is encoded to obtain a motion feature image.

Abstract: An endoscope manipulator for performing robot-assisted endoscope manipulation comprises a movable robot base with a hollow trunk and a vertical lifting joint; a passive joint set with one end mounted to an upper end of the vertical lifting joint, for manually setting an initial pose of the endoscope; an active joint set mounted to another end of the passive joint set, for adjusting pose control of the endoscope intra-operatively; and a compliant endoscope holder mountable to an end-effector of the active joint set, which passively changes to a compliant state upon an external force exceeding a threshold being applied to an endoscopic lens held by the compliant endoscope holder.

Abstract: Disclosed is an apparatus for separating and sorting USB wires. The apparatus comprises a separating apparatus for separating USB wires and a sorting apparatus provided downstream the separating apparatus. The separating apparatus comprises a first slider slidable in a horizontal plane in a reciprocating way; a second slider connected to the first slider via a sliding guide; and a teeth assembly comprising a group of first teeth and a group of second teeth.

Abstract: This application discloses an image coding method comprising: obtaining a plurality of groups of human skeleton data associated with performing an action by a human body, wherein each group of the human skeleton data comprises joint data associated with a joint for performing the action; extracting, based on joint data in the plurality of groups of human skeleton data, a motion feature matrix corresponding to the plurality of groups of human skeleton data; and encoding the motion feature matrix to obtain a motion feature image.

Abstract: This application discloses an image coding method comprising: obtaining a plurality of groups of human skeleton data associated with performing an action by a human body, wherein each group of the human skeleton data comprises joint data associated with a joint for performing the action; extracting, based on joint data in the plurality of groups of human skeleton data, a motion feature matrix corresponding to the plurality of groups of human skeleton data; and encoding the motion feature matrix to obtain a motion feature image.

Abstract: The present disclosure discloses a rotary joint electromagnetic locking device and a rotary joint, the rotary joint electromagnetic locking device comprising a first electromagnetic sucker, a sliding plate, a rotary plate, a connecting shaft connecting the first electromagnetic sucker and the sliding plate, and a second electromagnetic sucker, different from the prior art. When the first electromagnetic sucker and the second electromagnetic sucker have no adsorption force, the sliding plate and the rotary plate can be locked to each other; when the second electromagnetic sucker has an adsorption force, the rotary plate or the first electromagnetic sucker is adsorbed by the second electromagnetic sucker, making the sliding plate and the rotary plate to be further locked; when the first electromagnetic sucker has an adsorption force, the sliding plate can be adsorbed to the first contact surface of the first electromagnetic sucker, making the sliding plate released from the rotary plate.

Abstract: Various aspects of a systems and method for place recognition based on a 3D point cloud are disclosed herein. A computer-implemented method for place recognition based on a 3D point cloud, comprising: capturing a 3D point cloud of an area in which the mobile agent is traveling; extracting local features of each point in the captured 3D point cloud; generating a global descriptor of each point of the 3D point cloud using a deep neural network, based on the extracted local features; constructing a place descriptor map of the area based on the generated global descriptors; and recognizing the area by using the generated place descriptor map.

Abstract: Various aspects of a systems and method for place recognition based on a 3D point cloud are disclosed herein, A computer-implemented method for place recognition based on a 3D point cloud, comprising: capturing a 3D point cloud of an area in which the mobile agent is traveling; extracting local features of each point in the captured 3D point cloud; generating a global descriptor of each point of the 3D point cloud using a deep neural network, based on the extracted local features; constructing a place descriptor map of the area based on the generated global descriptors; and recognizing the area by using the generated place descriptor map.

Abstract: A skeleton posture determining method and apparatus, and a computer readable storage medium belong to the field of human body posture recognition, where the method includes obtaining a first skeleton posture including location information of a plurality of joints, determining a description parameter of at least one target joint of the joints, obtaining, through screening, a correct joint from the at least one target joint based on the description parameter, and performing fitting based on location information of the correct joint to obtain a second skeleton posture, where the second skeleton posture includes location information of at least one joint, and the at least one target joint is in a one-to-one correspondence with the at least one joint. Hence, the method, the apparatus, and the computer readable storage medium can improve recognition accuracy of a human body posture.

Abstract: Various aspects of a systems and method for reconstructing a surface of a three-dimensional (3D) target are disclosed herein. The method may comprise projecting a sequence of patterns to the surface of the target; capturing a first stereo endoscopic image and a second stereo endoscopic image from the patterns reflected from the surface; performing a coarse matching for the captured first and second stereo endoscopic images to acquire a set of matching candidates; and performing a precise matching for the acquired set of matching candidates to acquire reconstruction pixels for reconstructing the surface.

Abstract: The present disclosure discloses a rotary joint electromagnetic locking device and a rotary joint, the rotary joint electromagnetic locking device comprising a first electromagnetic sucker, a sliding plate, a rotary plate, a connecting shaft connecting the first electromagnetic sucker and the sliding plate, and a second electromagnetic sucker, different from the prior art. When the first electromagnetic sucker and the second electromagnetic sucker have no adsorption force, the sliding plate and the rotary plate can be locked to each other; when the second electromagnetic sucker has an adsorption force, the rotary plate or the first electromagnetic sucker is adsorbed by the second electromagnetic sucker, making the sliding plate and the rotary plate to be further locked; when the first electromagnetic sucker has an adsorption force, the sliding plate can be adsorbed to the first contact surface of the first electromagnetic sucker, making the sliding plate released from the rotary plate.

Abstract: This application discloses an image coding method comprising: obtaining a plurality of groups of human skeleton data associated with performing an action by a human body, wherein each group of the human skeleton data comprises joint data associated with a joint for performing the action; extracting, based on joint data in the plurality of groups of human skeleton data, a motion feature matrix corresponding to the plurality of groups of human skeleton data; and encoding the motion feature matrix to obtain a motion feature image.

Abstract: Various aspects of a systems and method for reconstructing a surface of a three-dimensional (3D) target are disclosed herein. The method may comprise projecting a sequence of patterns to the surface of the target; capturing a first stereo endoscopic image and a second stereo endoscopic image from the patterns reflected from the surface; performing a coarse matching for the captured first and second stereo endoscopic images to acquire a set of matching candidates; and performing a precise matching for the acquired set of matching candidates to acquire reconstruction pixels for reconstructing the surface.

Abstract: Disclosed is an apparatus for separating and sorting USB wires. The apparatus comprises a separating apparatus for separating USB wires and a sorting apparatus provided downstream the separating apparatus. The separating apparatus comprises a first slider slidable in a horizontal plane in a reciprocating way; a second slider connected to the first slider via a sliding guide; and a teeth assembly comprising a group of first teeth and a group of second teeth.