9 results about "Soft object" patented technology

The utility model relates to the technical field of mechanical arm, specifically disclose flexible mechanical hand grabbing mechanism, include: mechanical hand main part and the mounting plate of assembly in the one end of mechanical hand main part, the bottom of mounting plate presents linear array fixed mounting with a plurality of sucking disc, the one side fixed mounting of mounting plate has the shell, the below of mounting plate presents symmetrical and is provided with two upper clamping claws, the below of two upper clamping claws all is equipped with lower clamping claw, the upper clamping claw with lower clamping claw all presents arc shape, the utility model effectively prevents material from the clamping clearance drop, makes the mechanical hand can be compatible from small -size spare to large -scale work piece's grabbing demand, expands the application scene, enhances the buffer performance, even if fragile goods or soft object is grabbed also can not damage material, promotes the flexibility and practicality of grabbing mechanism.

The invention provides a layout determination method and device of a soft object, equipment, a medium and a program product. The method comprises the following steps: acquiring an initial spatial position of a target object corresponding to a moving operation in an indoor three-dimensional space; based on the initial space position, whether a to-be-adsorbed object corresponding to the target object exists in the indoor three-dimensional space or not is determined; if at least one to-be-adsorbed object corresponding to the target object exists in the indoor three-dimensional space, carrying out compatibility detection on the at least one to-be-adsorbed object to obtain at least one adsorbed object combination; determining a target adsorption object combination from the at least one adsorption object combination based on the number of the soft loading objects contained in the at least one adsorption object combination and the spatial distance between the target object and the soft loading objects; and on the basis of the target adsorption object combination, the target object is subjected to adsorption treatment, and the final position of the target object in the indoor three-dimensional space is obtained, so that the multiple to-be-adsorbed objects can be adsorbed and aligned at the same time, and the processing efficiency and accuracy of the soft installation object layout are improved.

The invention discloses a dexterous hand and a robot, and relates to the technical field of robots, the dexterous hand comprises a palm main body, and the palm main body is further provided with a palm surface located between a wrist end and a finger end; the thumb and the auxiliary fingers can be bent relative to the palm main body so as to move towards or away from each other; at least one of the fingertip part of the thumb and the fingertip part of the auxiliary finger is provided with a first image acquisition piece, the palm surface is provided with at least one second image acquisition piece, and the control module is suitable for jointly controlling the movement of the thumb and the auxiliary finger according to image information acquired by the first image acquisition piece and the second image acquisition piece. The dexterous hand is high in degree of freedom, high in movement stability, high in gripping force, capable of achieving more accurate movement so as to achieve accurate gripping of objects and capable of gripping finer and softer objects, high in integration level, small in overall size, light in weight, low in cost and beneficial to achieving light weight of a robot.

The utility model provides a rigid-flexible coupling picking gripper. The rigid-flexible coupling picking gripper comprises a driving rack, a central driving block, finger units, inner connecting rods, first flexible sensors and flexible coating layers. The central driving block is rotationally arranged on the driving rack; the finger unit comprises a near-end phalanx, a far-end phalanx and a transmission mechanism, the near-end phalanx is embedded with the first flexible sensor, the surface of the near-end phalanx is coated with the flexible coating layer, the flexible coating layer is a protective layer outside the near-end phalanx, the flexible coating layer is in direct contact with an object when the object is grabbed, and the counter-acting force is transmitted to the first flexible sensor; a sensing function is realized; one end of the near-end phalanx is connected with the inner connecting rod and the central driving block, and the other end of the near-end phalanx is connected with the far-end phalanx through a transmission mechanism. According to the manipulator, cross-size grabbing and hard and soft object grabbing can be achieved, and the grabbing range is greatly widened.

The invention belongs to the technical field of intelligent control, and discloses a robot non-grabbing external smart operation method based on rigidity perception dual-stage reinforcement learning, and the method comprises the steps: obtaining an environment and object point cloud through a depth camera, and obtaining a serialized tactile point cloud in combination with tentative tactile contact to perceive the object rigidity; multi-source point cloud information is fused through a high-level agent, and a target pose and an interaction action type are decided; the bottom intelligent agent plans a specific contact point and a motion direction according to the motion type; and the robot updates the state after executing the action, and circulates until the target is achieved. According to the method, the object rigidity information is fused into the decision process, the self-adaptive operation from rigid objects to soft objects is supported, the strategy does not need to be pre-defined manually, and the method has good generalization ability and learning efficiency and is suitable for robot flexible operation in a complex real scene.

The invention provides an interactive simulation method and device with a software object, electronic equipment, a computer program product and a computer readable storage medium. The embodiment of the invention can be applied to interactive simulation scenes of robots, virtual reality, augmented reality and the like with software objects; the method comprises the following steps: determining N simulation organization structures from a three-dimensional simulation model of a soft object according to a hierarchical structure of the soft object; wherein N is greater than or equal to 2, and N is an integer; determining, for each simulated organization structure, structural constraints for simulating physical properties of the corresponding hierarchy; and based on the vertex of each simulation organization structure, the structural constraint of each simulation organization structure and the simulation parameters of the three-dimensional simulation model of the interaction object, determining an interaction simulation result of the interaction object and the software object. According to the method and the device, the vivid degree of interactive simulation of the interactive object and the software object can be improved.

This invention discloses a method and apparatus for displaying object deformation based on force feedback interaction. When CT data of the object to be interacted with is received, a polygonal bounding volume is constructed using the CT data. The polygonal bounding volume is then tetrahedralized to generate a tetrahedral mesh model. Based on the vertex relationships between tetrahedral units and the unit volume of each tetrahedral unit, the equivalent mass of the mesh particles in each tetrahedral unit is allocated to obtain a soft mesh model. External forces are applied to the soft mesh model in response to control commands. Based on the equivalent mass of the mesh particles and the force corresponding to the applied external force, the particle positions of each tetrahedral unit are iteratively updated to obtain the updated particle positions. The image is rendered based on the updated particle positions, outputting the deformation image corresponding to the object to be interacted with. By combining tetrahedral modeling and iterative updates of particle positions, the accuracy and consistency of force feedback control for interaction between external forces and soft objects are effectively improved.

The invention belongs to the technical field of flexible body simulation, and particularly relates to an online rendering method of a flexible body, which is applied to a GPU (Graphics Processing Unit) of a mobile terminal and comprises the following steps: acquiring a relation mapping table of a high-precision triangular mesh of a flexible body object and a corresponding low-precision tetrahedral mesh from the CPU of the mobile terminal; wherein the relation mapping table records a tetrahedron unit bound with each vertex Vt of the high-precision triangular mesh and a function relation between the vertex Vt and all vertexes Ve of the tetrahedron unit; calculating the offset of each vertex Ve of the low-precision tetrahedral mesh converged to a constraint position based on an energy density function, and updating the position of each vertex Ve of the low-precision tetrahedral mesh according to the offset; adjusting the position of the vertex Vt by using the updated vertex Ve according to the function relationship between the vertex Vt of the high-precision triangular grid and the vertex Ve of the corresponding tetrahedron unit so as to correct the spatial form of the high-precision triangular grid; and rendering is carried out based on the high-precision triangular mesh after soft object correction so as to generate a picture of the current frame of the soft body.