Lang2Morph: Language-Driven Morphological Design of Robotic Hands
Organizations: CREATE Lab, Swiss Federal Institute of Technology Lausanne (EPFL), Lausanne, Switzerland. · Computer Vision Department, Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), Abu Dhabi, UAE.
Abstract
Designing task-specific robotic hands requires translating diverse task requirements into morphologies that are both functional and manufacturable. Existing parametric and optimization-based approaches provide systematic design tools, but often rely on expert-defined objectives, manual tuning, or simulation-based search. Large language models (LLMs), with broad semantic knowledge and reasoning capabilities, offer a promising way to interpret task requirements directly from natural language. We present Lang2Morph, an LLM-driven framework that maps natural-language task descriptions to fabricable robotic hand morphologies within the Open Parametric Hand (OPH) design space. Lang2Morph combines task reasoning, structured morphology generation, geometric constraints, and feedback-guided selection to produce task-conditioned hand designs. Morphology-level analyses demonstrate high design feasibility and task-dependent structural variation, while real-world experiments with three fabricated hands reveal distinct functional characteristics across manipulation tasks. These results highlight the potential of LLMs as practical interfaces for task-driven robotic hand design.
Figures & tables
| Method | Input | Manual Mapping | DFR (%) |
|---|---|---|---|
| Random | None | None | 28.9 |
| Template heuristic | Expert attrs. | Templates | 100.0 |
| Direct LLM | Language | None | 30.0 |
| Lang2Morph | Language | None | 97.8 |
| Run | Feasible Designs | DFR (%) |
|---|---|---|
| Run 1 | 29/30 | 96.7 |
| Run 2 | 29/30 | 96.7 |
| Run 3 | 27/30 | 90.0 |
| Mean std. | – |
Robotic Hand Design
Robotic hand design develops mechanical structures, actuation, and sensing for grasping and dexterous manipulation across real-world tasks.
See all 75 papers