Robust AI-Driven Target-Object-Free Hybrid Vision/Force Control of Industrial Robotic Systems
Bibliographic record
Abstract
This article introduces a robust AI-driven hybrid vision/force control (HVFC) method for industrial robots. The proposed HVFC method exploits Superpoint, a pretrained deep convolutional neural network (DCNN), as the AI agent to extract interest points for image-based visual servoing (IBVS), making it a target-object-free method. This tackles the limited workspace issue of eye-in-hand robots interacting with a workpiece due to the short distance between the camera and the workpiece, including a target object or landmarks. A learning-by-demonstration (LBD) method is also developed to generate the desired interest points associated with the desired path on the workpiece for interaction. To handle the issue of a high and variable number of interest points for use in IBVS, a set of six independent image features is extracted from the detected interest points, resulting in an invertible image interaction matrix, leading to global stability and a robust control process. To perform HVFC, a hierarchical orthogonal sliding manifold is defined, allowing force control in the normal direction and IBVS in the rest. Further, a filtered terminal integral sliding-mode controller is developed to stabilize the manifold, resulting in high tracking accuracy and robust performance against uncertainties and measurement noises. The experimental results of polishing and sanding the surfaces of a flat plastic board, a wooden airplane propeller, and a metal pegboard demonstrate the feasibility and superiority of the proposed HVFC-LBD method over conventional counterparts in terms of workspace expansion, robustness, and tracking accuracy.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".