Purpose
In this work, the authors aim to provide a set of convenient methods for generating training data, and then develop a deep learning method based on point clouds to estimate the pose of target for robot grasping.
Design/methodology/approach
This work presents a deep learning method PointSimGrasp on point clouds for robot grasping. In PointSimGrasp, a point cloud emulator is introduced to generate training data and a pose estimation algorithm, which, based on deep learning, is designed. After trained with the emulation data set, the pose estimation algorithm could estimate the pose of target.
Findings
In experiment part, an experimental platform is built, which contains a six-axis industrial robot, a binocular structured-light sensor and a base platform with adjustable inclination. A data set that contains three subsets is set up on the experimental platform. After trained with the emulation data set, the PointSimGrasp is tested on the experimental data set, and an average translation error of about 2–3 mm and an average rotation error of about 2–5 degrees are obtained.
Originality/value
The contributions are as follows: first, a deep learning method on point clouds is proposed to estimate 6D pose of target; second, a convenient training method for pose estimation algorithm is presented and a point cloud emulator is introduced to generate training data; finally, an experimental platform is built, and the PointSimGrasp is tested on the platform.
This paper proposes a family of high-pressure capturing wing configurations that aim to improve the aerodynamic performance of hypersonic vehicles with large volumes. The predominant visual feature of such configurations is a thin wing called a high-pressure capturing wing attached to the top of an upwarp airframe. When flying in the hypersonic regime, high-pressure airflow compressed by the upper surface of the vehicle acts on the high-pressure capturing wing and significantly augments lift on the vehicle with only a small increase in drag, producing a correspondingly high increase in its lift-to-drag ratio. A series of numerical validations were carried out on the basis of both inviscid and viscous computational models in which ideal cones with different cone angles and combined conewaverider bodies with different volumes were used as airframes. The results clearly demonstrate that a configuration using a high-pressure capturing wing has a significantly higher lift (with a correspondingly high value of lift-to-drag ratio) than one without a high-pressure capturing wing, especially for vehicles with large volumes. This paper contains a preliminary, results-based report of the conditions under which high-pressure capturing wing configurations were tested.= cruising speed W = gross weight, width α = angle of attack β = shock-wave angle γ = ratio of specific heats Δn = nondimensional height of the first layer near the wall η = ratio of average pressure on different surfaces θ = wedge angle, half-cone angle ξ = volumetric efficiency ρ = density Subscripts B = body H = high-pressure capturing wing HCWL = lower surface of the high-pressure capturing wing HCWU = upper surface of the high-pressure capturing wing
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.