GPT-Driven Gestures: Leveraging Large Language Models to Generate Expressive Robot Motion for Enhanced Human-Robot Interaction
Bibliographic record
Abstract
Expressive robot motion is a form of nonverbal communication that enables robots to convey their internal states, fostering effective human-robot interaction. A key step in designing expressive robot motions is developing a mapping from the desired states the robot will express to the robot's hardware and available degrees of freedom (design space). This letter introduces a novel framework to autonomously generate this mapping by leveraging a large language model (LLM) to select motion parameters and their values for target robot states. We evaluate expressive robot body language displayed on a Unitree Go1 quadruped as generated by a Generative Pre-trained Transformer (GPT) provided with a set of adjustable motion parameters. Through a two-part study (N = 120), we compared LLM-generated expressive motions with both randomly selected and human-selected expressions. Our results show that participants viewing LLM-generated expressions achieve a significantly higher state classification accuracy over random baselines and perform comparably with human-generated expressions. Additionally, in our post-hoc analysis we find that the Earth Movers Distance provides a useful metric for identifying similar expressions in the design space that lead to classification confusion.
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 | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".