Optimum grasp planner and vision‐guided grasping using a three‐finger hand
Bibliographic record
Abstract
Purpose The capability to perform dexterous operations in an autonomous manner would greatly enhance the productivity of robotic operations. In this paper, we present a new methodology for vision‐based grasping of objects or parts using a three‐finger hand as a gripper of a robotic manipulator. Design/methodology/approach The hand employed in our work, called SARAH, was designed for robotic operations on the space station, however, the main steps of our procedure can be applied for tasks in a manufacturing environment. Our methodology involves two principal stages: automatic synthesis of grasps for planar and revolute objects with SARAH and vision‐based pose estimation of the object to be grasped. For both stages, we assume that a model of the object is available off‐line. Findings In the paper, numerical results are presented for grasp synthesis of several objects with SARAH to demonstrate the feasibility and optimality of the synthesized grasps. Experimental results are also obtained with SARAH as the end‐effector of a seven‐degree‐of‐freedom robotic arm, demonstrating the feasibility of the integrated vision‐based grasping. Research limitations/implications The methodology described in the paper, although represents a substantial step towards automated grasping with a robotic manipulator, still requires some decision making from the user. Further work can improve the pose identification aspects of the algorithm to make them more robust and free of human intervention. As well, the grasp synthesis procedure can be expanded to handle more complex and possibly moving objects, as well as to allow for different grasp types than those considered here. Practical implications The work demonstrates feasibility of autonomous grasp execution in industrial setting by using a three‐finger hand as a robotic gripper. Originality/value The results presented in the paper demonstrate the feasibility of synthesising optimised grasps which take into account the kinematics of the gripper. We also demonstrate a real implementation of vision‐based grasping by using a robotic manipulator with a three‐finger hand.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".