Large Language Model for Assisted Robot Programming in Micro-Assembly
Bibliographic record
Abstract
In the context of the rapid development of micro-devices and photonics, the importance of efficient automation solutions is becoming increasingly important. The automation of assembly processes in particular is a decisive factor, as assembly is responsible for a large proportion of costs. The programming of robots, particularly in the field of micro-assembly, requires extensive specialist knowledge due to the complexity of the assembly systems and processes. Increasingly more powerful large language models (LLMs) enable their use in robot programming. These allow interaction through natural language, providing an intuitive user interface. In this work, we utilize a LLM to assist users in programming new micro-assembly processes. We develop an assistant that we integrate into a Robot Operating System 2 (ROS2) framework. This framework enables the control and programming of a micro-assembly robot via ROS2 services. The assistant has access to these services and information about the components. Based on user requests, the assistant can parameterize these services and arrange them sequentially according to the assembly task. The assembly sequence can subsequently be modified by the user, either by using the assistant again or manually. We test the performance of the developed assistant using example tasks and demonstrate that, particularly, shorter sequences can be reliably generated. Finally, we present potential improvements and extensions of the application.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.010 | 0.004 |
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".