Structural Segmentation and Large Language Model Make Behavior Tree More Explainable
Bibliographic record
Abstract
Behavior trees have found extensive applications in the field of robotics due to their modular and reusable characteristics. They are employed to enable autonomous actions in robots, including control of robot motion, assessment of the robot's state, and the planning of the robot's action sequences. Behavior trees offer the advantage of effectively representing complex behaviors and adapting well to various environments and tasks. However, when reusing behavior trees constructed for prior projects, comprehension of the functional-ity of intricate behavior trees can pose a challenge for technical personnel. To expedite the comprehension of new behavior trees and enhance task development efficiency, this paper introduces a method for behavior tree explanation based on behavior tree segmentation and large language models. This method performs structural segmentation of behavior trees based on the hierarchical structure of tasks. It leverages the natural language capabilities of open-source large language models to obtain function explanations of behavior trees, thereby assisting technical personnel in understanding their functional-ity. Through experimentation, the paper initially demonstrates the feasibility of utilizing large language models to interpret behavior trees. It further validates that the superiority of the proposed methodology in terms of accuracy and stability compared to the mere utilization of the intrinsic capabilities of large language models.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.003 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".