Semi-Autonomous Grabber Attachment for a Drone
Bibliographic record
Abstract
A design for a semi-autonomous robotic grabber attachment for a drone is presented, targeted for use in the Unmanned Systems Canada student engineering competition. The grabber is designed to grip an unknown and potentially hazardous object having a maximum dimension of 20 × 20 × 20 cm and a maximum weight of 2 kg. The grabber implements a three-arm configuration actuated by servo motors. Each 3D printed arm is 37 cm long and has two degrees of freedom, facilitating complex movements. Sensory data from a camera and infrared distance sensor is used to identify contact points on the target object. A grip is achieved by instructing the arms to push into the identified points of contact. Different grabbing strategies, classified by contact angle, can be selected depending on the geometry of the target object. Force-sensitive resistors are sometimes able detect a secure grip. The grabber operation is controlled by a Python program compiled on a Raspberry Pi 4 that can be executed over a Wi-Fi connection. Without an on-board power supply, the grabber prototype had a mass less than 5 kg, has a maximum width of 42 cm, and costs approximately $675 CAN. \n \nThe results of preliminary tests with the grabber are also presented. The grabber is operated from a position and instructed to grab five objects with different geometries. The computer vision system is capable of classifying objects with circular and rectangular contours using an external webcam as a substitute for the on-board camera. The grabber is successful at gripping objects with simple and irregular geometries if their total mass is less than 500 g. The difficulty in gripping heavier objects is primarily attributed to poor contact by the arms. It is concluded that further design iterations are required to meet the initial design goals. These iterations include modifying the material on the arms to increase friction, incorporating more sensors to enable 3D characterization of the target object, and optimizing the points of contact to prevent the arms from slipping. For competition purposes, an on-board power supply and a functioning on-board camera is also required.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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".