44 results about "Hand manipulation" patented technology

The utility model provides a robot hand and a robot system including the same. The robot hand includes: a plurality of robot fingers; and a robot palm configured to be operatively connected with the plurality of robot fingers, where an individual robot finger includes: a first phalanx; a second phalanx; and a first hydraulic actuator configured to operatively connect the first phalanx with the second phalanx, where the first hydraulic actuator includes a soft bellows-shaped deformable body such that, when in operation, the first and second phalanx are deformed by the flexible bellows-shaped deformable body, the flexible bellows-shaped deformable body is deformed by the flexible bellows-shaped deformable body. The first hydraulic actuator is switchable at least between a compressed state and an extended state in response to an external force and / or hydraulic pressure applied thereto. Other example embodiments are described herein. In certain embodiments, the present disclosure provides robotic hands and robotic systems including the same that exhibit high compliance, adaptability, and precise control to robotic applications, and address the challenges to achieve fine in-hand manipulation of the robot.

The invention discloses a privacy protection type service behavior monitoring method and system based on event-driven vision. The method comprises the following steps: collecting light intensity change in a service scene through an event-driven asynchronous visual sensor, and generating event stream data without texture information; a neural network model is utilized to extract desensitized structured action features from the event stream, and the features comprise a whole body posture, hand operation and a multi-granularity key point skeleton of a face area and do not contain any identifiable identity information; and performing behavior semantic analysis such as fall detection, service action compliance verification, people flow statistics and the like based on the features, and outputting a visual result for service quality supervision, risk early warning or responsibility tracing. On the premise of not obtaining, storing or transmitting any image frame, non-intrusive and high-precision monitoring of service behaviors in high-privacy sensitive scenes such as home door-to-door service, old-age nursing and medical rehabilitation is achieved, and privacy protection and intelligent supervision requirements are effectively balanced.

The utility model relates to the technical field of clamping tools, and discloses a clamping tool for an outside micrometer, which comprises a base, the middle position of the top of the base is connected with a support column, and the upper side of the front part of the support column is screwed with a limiting bolt; the clamping groove is formed in the middle of the top end of the supporting column, and the rear end of the limiting bolt penetrates through the corresponding position of an inner cavity of the clamping groove. According to the clamping tool for the outer diameter micrometer, the micrometer can be clamped through the formed clamping groove, then the clamping arm of the micrometer is clamped by rotating the limiting bolt, due to auxiliary clamping of the limiting bolt, the clamping groove can clamp the micrometers with different thicknesses, the clamping stability of the micrometer is improved, and the clamping efficiency of the micrometer is improved. And tiny vibration caused by hand operation is reduced, so that the measurement accuracy is improved.

This invention discloses a method, system, and computing device for grading the degree of human intervention in ground-based unmanned equipment. It describes the degree of human intervention using four indicators: head posture focus, facial expression focus, proportion of hand operation time, and frequency of hand operation interaction. The advantages of this invention are: it improves the objectivity of the evaluation of human intervention in ground-based unmanned equipment; and it improves the efficiency of testing and evaluation based on deep learning intelligent processing technology for video images. By integrating video data and detecting, recognizing, and tracking personnel posture and actions, as well as analyzing human-computer interaction behavior, it achieves a quantitative assessment of the degree of human intervention in ground-based unmanned equipment. This overcomes the limitations of traditional evaluations, which heavily rely on subjective qualitative evaluations by experts and lack sufficient quantitative expression capabilities. It constructs an evaluation system for the degree of human intervention in ground-based unmanned equipment with accurate perception and comprehensive quantitative analysis of video scenes, providing a certain reference for the quantitative assessment of the autonomy of ground-based unmanned equipment.

The utility model discloses a kind of flatly embedded handles, including the main body with handle slot, the support plate is symmetrically equipped with in main body bottom two sides, the space for hand operation that support plate surrounds is communicated with handle slot, main body outer connection mounting frame is set, mounting frame and main body are set in echelon, the height difference between the two constitutes installation groove, for installing limit to main body, the side of main body away from handle slot is connected with decorative plate, decorative plate and mounting frame are set in echelon, the height difference between the two forms limit groove, for installing limit to mounting frame, mounting frame and main body are equipped with hollow slot, for reducing the weight of overall handle, hollow slot is equipped with several, support column is constituted between adjacent hollow slot, for improving the connection strength of mounting frame and main body, provide a kind of built-in handle with compact structure, installation stable and beautiful and generous.

The embodiment of the invention provides a method, device and equipment for in-hand operation of a robot and a computer readable storage medium. According to the method, for a three-finger robot hand configured with a touch sensor, training of an in-hand operation strategy is carried out in a physical simulator, and the learned in-hand operation strategy is applied to a real robot, a deep reinforcement learning method is used, a contact center position of a robot hand and a target object is used as partial observation to carry out strategy training, a joint model of finger joints is calibrated by considering mechanical backlash and self-locking characteristics of a robot, and an initial training state is randomized to ensure successful transfer from a training strategy to a real robot. Therefore, the flexible and continuous in-hand operation of the robot on the target object is realized. According to the method, a better strategy can be trained by using the estimated contact center position as observation, and the learned strategy has good performance in simulation and real world experiments and has good generalization ability.

The utility model relates to the technical field of driving simulation devices, and provides a simulator joystick linkage structure which comprises a box body, a left rocker and a right rocker are movably arranged on the box body, and the left rocker and the right rocker are connected through a sliding assembly and an angle linkage assembly and used for synchronous movement. And the centering unit comprises a front-back centering assembly and a left-right centering assembly, is arranged on the left rocker and the right rocker and is used for enabling the left rocker and the right rocker to simultaneously and actively restore to the initial positions. The double-person driving simulation training device can meet the requirement for hand operation during double-person driving simulation training, timely correction during training is facilitated, meanwhile, the actual driving hand feeling can be simulated, and the training effect is better.

This access method for a hand includes: moving a hand 10 to an offset position that is away from an adapter axis M in a direction intersecting the adapter axis M, and is away from an adapter 91 in the direction of the adapter axis M; moving the hand 10 from the offset position so as to approach the adapter axis M, and moving the hand 10 to an opposing position that is, in the direction of the adapter axis M, away from the adapter 91 and opposing the adapter 91 and the direction of the adapter axis M; and moving the hand 10 from the opposing position to the adapter 91 in the direction of the adapter axis M.

The application relates to the field of video applications, and provides a video desensitization method and device, electronic equipment and a computer program product. The method comprises the following steps: acquiring video data, identifying a human hand region based on the video data, obtaining N gesture recognition results and M hand contact article recognition results, determining a sensitive region and a target sensitive level according to the N gesture recognition results and the M hand contact article recognition results, and performing desensitization processing on the video data according to the sensitive region and the target sensitive level. The video desensitization method provided in the embodiment of the application can solve the technical problem that a hand contact article or hand operation of a photographed person cannot be desensitized, personal information of the photographed person is easily leaked, and the personal information safety of the photographed person is improved.

The invention discloses a vehicle-mounted air conditioner dynamic avoidance air supply method based on human body posture recognition, and relates to the technical field of intelligent vehicle-mounted air conditioners and man-machine interaction, and the method comprises the steps that human body posture data of passengers are obtained and fused, and a three-dimensional posture model containing key point coordinates is constructed; recognizing a head key point and a hand key point based on the three-dimensional attitude model, constructing a head protection sphere by taking the head key point as a sphere center, and constructing a hand operation forbidden zone by taking a steering wheel geometric center; and a cubic Bezier curve is adopted to plan a streaming path, the angle combination of the piezoelectric ceramic units in the shutter matrix is calculated, and dynamic avoidance air supply control of the vehicle-mounted air conditioner is carried out. Real-time and high-precision dynamic avoiding air supply capacity is brought to the vehicle-mounted air conditioner, compared with a traditional method, the air feeling comfort level and operation safety of passengers are remarkably improved, and discomfort or interference caused by direct airflow is effectively prevented.

The application discloses an optimization method for generating robust and physically feasible grasping poses for a robot dexterous hand, belonging to the field of robot control. The method comprises the following steps: step 1, predicting the 3D affordance of an object using a conditional variational autoencoder model, learning the geometric properties of the object in the data set, taking the point cloud of the object as the input, and outputting a 3D affordance region map related to hand operation; step 2, the dexterous hand follows the 3D affordance region map, based on the synergistic effect of the fingers and the palm, and generates a grasping pose by optimizing the total energy function containing a self-conflict optimization term between the fingers and a support optimization term, and the optimal grasping pose of the robot dexterous hand is obtained after optimization. The method uses a conditional variational autoencoder model to predict a high-precision operation region, and introduces a self-conflict optimization term between the fingers and a support optimization term between the palm and the object to optimize the generation of the grasping pose, realizes multi-finger coordination and grasping stability, and has robustness.

The application discloses a wearable human-machine operation data acquisition system and method based on relative visual inertial measurement, which is used for robot imitation learning. The system comprises a chest reference node and a hand operation node, each node comprising a camera and an inertial measurement unit, and the poses of the trunk and the hand in a global coordinate system are obtained through a visual inertial odometer respectively. A central processing unit calculates the relative pose of the hand relative to the chest in real time, effectively decouples the overall movement of the human body and the fine action of the hand, and introduces a rotation compensation mechanism based on the angular velocity of the chest reference node, so as to eliminate the false displacement caused by body rotation. The system outputs a strictly time-synchronized, standardized format relative pose sequence, multi-view images and inertial data, which can be directly used for imitation learning algorithm training. The application solves the problems of poor mobility, motion coupling and complex deployment of the traditional teaching system, and realizes high-precision and high-robustness data acquisition in a free-moving scene.

The invention belongs to the technical field of teaching evaluation, and particularly relates to an intelligent evaluation method and system for common car teaching based on an AI large model. The method comprises the following steps: acquiring student general car practical operation data, inputting the practical operation data into an intelligent evaluation model, and outputting scores and a total score corresponding to each score composition model by the intelligent evaluation model according to pre-defined score composition modules and corresponding weights. Wherein the intelligent evaluation model comprises a target detection model and an AI large model, and the target detection model is used for identifying lathe parts and student hand operations in the video data; the AI large model is used for outputting scores corresponding to the score composition models according to the sensor data, each frame of lathe part and student hand operation, a hand operation action sequence formed by each frame of student hand operation and a lathe part action sequence formed by each frame of lathe part, so that the score composition is quickly and accurately analyzed, and the score composition is analyzed. Therefore, the evaluation dimension is more comprehensive, the evaluation in all aspects during practical training can be known, and the practical operation subdivision problem can be known.

The invention discloses an automatic driving takeover behavior prediction model construction method and device, a storage medium and a driver takeover behavior optimization adjustment method, and the prediction model construction method comprises the steps: 1, obtaining driver operation data and a vehicle driving state of each time step in a historical time period, encoding and then constructing a takeover behavior historical time sequence; 2, performing normalization processing on the historical time sequence to obtain a data set; and step 3, training the basic model by using the data set to obtain a hand operation state prediction model and a foot operation state prediction model. The equipment and the storage medium are used for realizing the prediction model construction method. According to the driver takeover behavior optimization and adjustment method, a prediction model formed by a prediction model construction method is utilized to predict the hand operation state and the foot operation state of a driver in the future time step, and the hand operation state and the foot operation state serve as the basis for the driver to optimize and adjust the hand operation and the foot operation of the driver. According to the invention, effective optimization and adjustment of the takeover behavior of the driver can be realized.

The invention provides a wearable electrical stimulation perception enhancement device and method. The device comprises a detection stimulation module and a control module. The detection stimulation module comprises a neck sleeve, a plurality of electrodes installed on the inner side of the neck sleeve, a myoelectricity data processing unit and an electric stimulation driving unit. In the man-machine interaction process, different information is provided for a user by applying electrical stimulation with different intensities and different frequencies to electrodes at different positions of the user. According to the invention, information is transmitted through the tactile channel at the neck with strong perception ability, the cognitive load of vision and hearing can be effectively reduced, and the success rate of information transmission and the work performance are improved; moreover, compared with the traditional vibration stimulation, the electrical stimulation adopted by the invention has the advantage that the electrical stimulation is not easy to be masked by movement, and the perceptibility of the tactile signal is improved. Moreover, the method has the advantage that the hand operation of the user is not easily influenced when the method acts on the shoulder and neck of the human body, and the information interaction density can be improved in a navigation scene.

The invention provides an electronic equipment manipulation method and electronic equipment. The electronic equipment manipulation method comprises the steps that hand operation information at least related to the posture of an operation body is acquired; determining an operation mode of the operation body based on the hand operation information; and controlling the electronic equipment to a state corresponding to the operation mode according to an association relationship between the operation mode and a preset operation function of the electronic equipment.

Soft inflatable pouch robots with many independent degrees of freedom are created from multiple layers of thin thermoplastic films. The method uses inkjet-printed solvent ink or laser printer toner to pattern pouch layers, enabling the integration of pouch actuators, structures, channels, and pneumatic ports within one process. A fluid manifold allows addressable and controlled inflation of the inflatable features of the device. A 4-finger 8-independent-DoF pouch hand performing in-hand manipulation, and a 10-independent-DoF continuum manipulator performing planar pick-and-place illustrate the design functionalities.

To provide a novel puncture needle for perforation capable of advantageously obtaining a treatment space within the right atrium while satisfactorily ensuring good transmission of hand manipulation force to the tip.　The puncture needle for perforation has a two-stage bent shape in which the tip side inserted into an atrium connects a proximal side bent section and a distal side bent section by a straight section, has a "bending angle θp of the proximal side bent section">"bending angle θd of the distal side bent section", and has a separation distance L of the needle tip with respect to an extension line of the straight section extending from the proximal side bent section toward the proximal side of 40 mm≥L≥70 mm.

The invention relates to a robot teleoperation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the following steps: acquiring hand posture data of key points of a hand of a human body; performing pose calculation on the hand pose data to obtain a hand joint angle of the robot; performing pose conversion on the wrist pose data of the hand pose data to obtain wrist joint pose data of the hand of the robot; resolving the wrist joint pose data according to a preset inverse kinematics model to obtain a two-arm joint angle of the robot; and performing teleoperation on the robot according to the hand joint angle and the double-arm joint angle to obtain a hand operation result of the robot. By means of the method, the joint angles of the hands and the two arms of the robot can be calculated in real time at the plate end of the robot to achieve teleoperation, and balance of precision, usability and cost is achieved.

A pen format liquid collection device includes an elongate generally tubular housing (12, 112, 212, 312) able to be held by hand and having an opening at one end, and at least one liquid take-up element (30, 130, 230, 330) mounted in the housing so as to be positioned or positionable to project at the opening, the at least one liquid take-up element then further postionable by hand manipulation of the housing to contact a volume of liquid to thereby take-up a sample of the liquid to be analysed. At least one retention element (230a, 330a) is supported in the housing. The at least one liquid take-up element and the at least one retention element are arranged whereby they are relatively movable into contact, and the at least one retention element is adapted on contact to in turn take-up the sample and retain the sample or a component thereof for in situ analysis or later recovery while protected within the housing. The liquid take-up element is preferably a capillary.

In one aspect, a robotic hand is provided, the robotic hand comprising: a plurality of robotic fingers; and a robot palm configured to be operatively connected with the plurality of robot fingers, where an individual robot finger includes: a first phalanx; a second phalanx; and a first hydraulic actuator configured to operatively connect the first phalanx with the second phalanx, where the first hydraulic actuator includes a soft bellows-shaped deformable body such that, when in operation, the first and second phalanx are deformed by the flexible bellows-shaped deformable body, the flexible bellows-shaped deformable body is deformed by the flexible bellows-shaped deformable body. The first hydraulic actuator is switchable at least between a compressed state and an extended state in response to an external force and / or hydraulic pressure applied thereto. Other example embodiments are described herein. In certain embodiments, the present disclosure provides robotic hands and systems that exhibit high compliance, adaptability, and precise control to robotic applications, and address the challenges to achieve fine in-hand manipulation of the robot.

The invention discloses a dynamic airtight operation sleevelet system of a negative pressure isolation sickbed and a using method of the dynamic airtight operation sleevelet system, and relates to the technical field of medical isolation protection equipment.The dynamic airtight operation sleevelet system comprises a flexible sleevelet body connected to an isolation bulkhead, and the flexible sleevelet body comprises an arm sleeve section and a hand operation section which are sequentially connected; the dynamic airtight module is arranged on the hand back part of the hand operation section; the inflation expansion cavity is formed in the hand operation section; the sensing unit is arranged on the hand back part of the hand operation section and used for detecting the extraction state of the limbs of the user; the control unit is in signal connection with the sensing unit; inflation expansion is automatically triggered by sensing limb extraction actions, a dynamic sliding sealing interface is formed between an arm and the inner wall of the sleeve, a traditional static sealing mode depending on friction force is changed, the air tightness is guaranteed, meanwhile, the wearing and taking-off resistance is reduced, and operation is smooth and rapid.

In one aspect, provided is a robotic hand, comprising a plurality of robotic fingers; and a robotic palm, configured to operatively connect with the plurality of robotic fingers, wherein individual robotic finger comprises: a first phalanx; a second phalanx; and a first hydraulic actuator, configured to operatively connect the first phalanx with the second phalanx, wherein the first hydraulic actuator comprises a soft, bellows-type deformable body, such that when in operation, the first hydraulic actuator is switchable between at least a compression status and an extension status, in response to external force and / or hydraulic pressure applied thereto. Other example embodiments are described herein. In certain embodiments, the disclosure provides robotic hands and systems that showed high degrees of compliance, adaptability, and precise control for robotic applications and addressed the challenge of achieving robotic fine in-hand manipulation.

The utility model provides a kind of hand operation device and surgical robot, wherein hand operation device includes: far end deflection joint, for doing deflection motion in horizontal plane;Far end pitch joint is connected with far end deflection joint, and far end pitch joint is used to do pitch motion;Translation joint is connected with far end pitch joint, and translation joint is used to do translation motion;Far end roll joint is connected with translation joint, and far end roll joint is used to do roll motion;Near end pitch joint is connected with far end roll joint, and near end pitch joint is used to do pitch motion;Near end deflection joint is connected with near end pitch joint, and near end deflection joint is used to do deflection motion;Near end roll joint is connected with near end deflection joint, and near end roll joint is used to do roll motion.By adopting the above technical scheme, the operation precision of surgery is significantly improved, the motion range is expanded, the stability is enhanced, the operation comfort and the sense of presence of surgery are improved.

The charger comprises a housing, the upper side of the outer surface of the housing is provided with sliding grooves I, the four sliding grooves I are symmetrically arranged along the center line of the housing, the inner parts of the sliding grooves I are provided with connecting rods, the lower ends of the connecting rods are slidably connected with the housing, the upper ends of the connecting rods are provided with clamping plates I, and the clamping plates I are provided with clamping plates II; the lower ends of the first clamping plates are slidably connected with the shell, and the two first clamping plates are symmetrically arranged along the center line of the shell. The charger convenient for rapid counterpoint plugging provided by the utility model has good convenience and efficiency, operation can be completed by only one hand under the condition that the hand operation space is limited, good stability of the whole device is ensured, and meanwhile, the good characteristic of convenient disassembly of the device is still kept.

The utility model discloses a positioning device for sensor processing, which relates to the technical field of sensor processing and comprises a shell, a butt joint unit and a positioning unit. According to the utility model, sensor shells with different sizes can be effectively clamped, and production and processing are facilitated by hand operation: the finger push groove can facilitate fingers to push the bearing sliding seat to slide outwards, so that the loaded sensitive element is slidably fed into the shell of the sensor; the sensitive element can be released by pressing the other end of the movable pressing plate; a reliable positioning unit is also arranged, and the probing depth of the sensitive element relative to the port of the sensor shell can be determined by comparing the feeding contrast ruler on the side surface with the edge of the shell, so that the effect of positioning and mounting is realized; whether the sensitive element is clamped in the center or not can be judged by observing whether the scale marks on the two sides of the sensitive element and corresponding to the centering contrast ruler are consistent in reading or not, and follow-up pushing installation is facilitated.

The invention discloses an optimization method for generating a steady and physically feasible grabbing posture for a robot dexterous hand, and belongs to the field of robot control. The method comprises the following steps of: 1, predicting 3DAfordance of an object by using a conditional variation auto-encoder model, learning geometric attributes of the object in a data set, and outputting a 3DAfordance area chart related to hand operation by taking object point cloud as input; and step 2, the dexterous hand optimizes and generates a grabbing posture by optimizing a total energy function comprising a self-conflict optimization item and a support optimization item among fingers based on the synergistic effect of the fingers and the palm according to the 3DAfordance area graph, and the optimal grabbing posture of the robot dexterous hand is obtained after optimization. According to the method, a condition variation self-encoder model is used for predicting a high-precision operation area, a self-conflict optimization item between fingers and a support optimization item between a palm and an object are introduced to optimize and generate a grabbing posture, multi-finger coordination is achieved, grabbing is stable, and robustness is achieved.

Robot control device (10), comprising: a process time prediction unit (11) for predicting a robot process time (T1), which is a time required by a robot (30) to cause a hand (31) of the robot (30) to reach a target position (P) get ) achieved, and a manual operation time (T gsp ), where this is a time from the time at which an action of the hand (31) is commanded until the time at which the hand (31) carries out an action of grasping an object at the target position (P get ) finished, acts; and a hand operation start instruction unit (13) for issuing an instruction to start an operation of the hand (31) at a time determined based on the predicted robot operation time (T1) and the predicted hand operation time (T gsp ) is determined, whereby the process time prediction unit (11) predicts the robot process time (T1) by calculation, which integrates the robot control system information, which includes a control parameter to determine the responsiveness of a control system of the robot (30).