A Biologically Inspired Program-Level Imitation Approach for Robots
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Robots may learn new skills from humans to better assist us with everyday tasks. We propose a novel, biologically inspired imitation approach to enable robots to understand and perform complex actions using high-level programs that incorporate sequential regularities between sub-goals a robot can recognize and physically achieve. To learn a new task, human-provided demonstrations—obtained by a robot through different modalities such as kinesthetic teaching or behavioural observation—are processed by an algorithm to discover multiple possible arrangements of sub-goals that achieve the task goal. When performing the task, the robot first evaluates the available sequences in the program based on user-defined criteria, through mental simulation of the real task, to find the optimal sequence of actions. The selected sequence is then executed using the hierarchical structure of actions embedded in the program. We implemented the proposed learning architecture on an iCub humanoid robot and evaluated the effectiveness of the system in multiple scenarios. Our approach accommodates variations in human teaching styles and is expected to help robots perform tasks with greater flexibility and efficiency, opening the way to more adaptable and intelligent robots.
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.
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) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 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 it