8 results about "Tactile Perceptions" patented technology

The application discloses a kind of robot dexterous operation systems, methods, equipment and media for transparent object, belong to robot dexterous operation and three-dimensional perception field, system includes: point cloud data construction module, can be constructed and noisy to obtain noisy hand-object interaction point cloud by physical simulation;Point cloud feature extraction module can extract high-dimensional latent features from noisy hand-object interaction point cloud;Query prediction module can infer object shape and pose by query point generation and decoder decoding;Perception coding module can extract features from global point cloud, hand-object interaction point cloud and tactile information to obtain multi-source perception features;Multi-modal feature fusion module can realize feature integration through self-attention mechanism and cross-attention mechanism calculation, and output fusion features;Action generation strategy module can generate differentiated action instructions for robot arm and dexterous hand based on fusion features.The system can achieve higher adaptability and stronger generalization capability in transparent object operation task.

The application discloses a kind of dexterous hand's negative pressure tactile perception system and perception method, characterized by including vacuum pump and primary pressure measuring air path, each finger of dexterous hand is provided with vacuum perception port on each finger joint, each vacuum perception port is connected with three-stage pressure measuring air path by flexible air pipe, the three-stage pressure measuring air path connected with the vacuum perception port on the same finger is connected with the same secondary pressure measuring air path, all secondary pressure measuring air paths are connected with primary pressure measuring air path;Advantages are that the negative pressure tactile perception system can install each pressure measuring air path in the arm of robot, and is connected to the vacuum perception port of finger joint through flexible air pipe, so that the air pressure sensor for pressure measurement is away from dexterous hand, avoids being affected by the cold or magnetic field of contact object, and ensures the accuracy of tactile perception.

The application discloses a kind of dexterous hand's negative pressure tactile perception system and perception method, characterized by including vacuum pump and primary pressure measuring air path, each finger of dexterous hand is provided with vacuum perception port on each finger joint, each vacuum perception port is connected with three-stage pressure measuring air path by flexible air pipe, the three-stage pressure measuring air path connected with the vacuum perception port on the same finger is connected with the same secondary pressure measuring air path, all secondary pressure measuring air paths are connected with primary pressure measuring air path;Advantages are that the negative pressure tactile perception system can install each pressure measuring air path in the arm of robot, and is connected to the vacuum perception port of finger joint through flexible air pipe, so that the air pressure sensor for pressure measurement is away from dexterous hand, avoids being affected by the cold or magnetic field of contact object, and ensures the accuracy of tactile perception.

The invention provides a wearable tactile balance interaction system and method, and the system comprises a tactile device, a balance pad and a host, and the host is in data connection with the tactile device and the balance pad. Wherein the tactile device comprises a plurality of devices for tactile stimulation; a tactile instruction is obtained through a host, the tactile device is controlled through the tactile instruction to sequentially indicate different balance actions, balance sensing information collected and fed back through the tactile device and the balance pad is obtained, and a balance stability index is calculated according to the balance sensing information. And further adjusting the haptic device through the balance stability index.

The application provides an object attribute perception method and device based on dexterous hand touch and a storage medium, and belongs to the technical field of touch perception. The method comprises the following steps: controlling a dexterous hand provided with a three-dimensional force sensor array to perform initial light touch scanning on a target object, and acquiring preliminary profile information of the target object; determining a key region of the surface of the target object based on the preliminary profile information, wherein the key region comprises a high-curvature region and / or a flat region; determining a corresponding perception strategy according to the type of the key region; and controlling the dexterous hand to perform the corresponding perception strategy in the key region, and acquiring a physical attribute perception result. The application can adapt to object characteristics and collaboratively perceive multiple attributes of the object.

The application discloses a wood material tactile subjective perception prediction method, which comprises the following steps: step one, preparing a wood material sample set, collecting subjective scores of wood material samples in the dimensions of smoothness, roughness, stickiness and softness, and constructing a tactile subjective perception database; step two, collecting surface images of the wood material samples and vibration signals generated by fingers rubbing the surfaces, and extracting visual features and tactile features from the surface images and the vibration signals respectively. The wood material tactile subjective perception prediction method provided by the application fuses visual and tactile multi-scale features, constructs a fine-grained feature system to improve prediction accuracy, introduces a finishing gate variable to adaptively distinguish different surface states and enhance the model generalization ability, then adopts high-dimensional feature robust processing and elastic net regularization to effectively inhibit small sample overfitting, and finally ensures the model robustness and prediction reliability.

The invention provides an intelligent control method and system for a high-degree-of-freedom dexterous hand based on collaborative dimensionality reduction, and the method comprises the steps: 1, collecting the external perception information of the somatosensory and tactile sensation of the dexterous hand through a sensor, and carrying out the preprocessing of the perception information, and obtaining input data; 2, establishing a mapping model from a high-dimensional dexterous hand to a low-dimensional collaborative space based on a collaborative concept, and generating an activation coefficient of the low-dimensional collaborative space according to the preprocessed perception information; 3, mapping the activation coefficient to a control space of the high-dimensional dexterous hand to generate a control instruction, and driving an actuator of the dexterous hand to realize a target action; 4, after new sensing information is collected in real time, the step 1 is executed, closed-loop control is formed, and the mapping model is dynamically adjusted. According to the method, the complex control problem of the high-degree-of-freedom dexterous hand is converted into the activation coefficient generation problem of the low-dimension cooperative space, and the technical problems that in high-dimension control, the calculated amount is large, and the real-time performance is poor are solved.

The invention discloses an integrated joint-fingertip-contact target multi-mode sensing method, and relates to the field of robot sensing. In order to solve the defects that in the prior art, a sensor is high in integration cost, complex in structure and incomprehensive in sensing information, and unified multi-mode sensing of a joint-fingertip-target cannot be achieved, the technical scheme provided by the invention comprises the following steps of: obtaining the displacement of a rope and the deformation of a spring; calculating a joint angle according to the rope displacement; calculating a joint driving torque according to the spring deformation amount; calculating a fingertip position according to the joint angle; reversely deducing fingertip contact force according to the joint driving torque; estimating target softness according to the contact force and the displacement; and recording a fingertip trajectory according to the contact state to identify a target contour. The method is suitable for multi-mode sensing work of the rope-driven dexterous hand in a complex operation task, and is especially suitable for application scenes of flexible grabbing, touch recognition and interaction control of a target object.