オンデバイス言語モデルによるロボット計画のための最小限の人間介入での蒸留
Distilling On-device Language Models for Robot Planning with Minimal Human Intervention
クラウドに依存せずオンデバイスで動作する小型言語モデルベースのロボットプランナーを、既存のLLMプランナーから合成データを用いて蒸留するフレームワークPRISMを提案し、Llama-3.2-3Bの性能をGPT-4oの10-20%から93%以上に向上させた。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Zachary Ravichandran, Ignacio Hounie, Fernando Cladera, Alejandro Ribeiro, George J. Pappas, Vijay Kumar
分類: cs.RO, cs.AI, cs.LG
原文アブストラクト
Large language models (LLMs) provide robots with powerful contextual reasoning abilities and a natural human interface. Yet, current LLM-enabled robots typically depend on cloud-hosted models, limiting their usability in environments with unreliable communication infrastructure, such as outdoor or industrial settings. We present PRISM, a framework for distilling small language model (SLM)-enabled robot planners that run on-device with minimal human supervision. Starting from an existing LLM-enabled planner, PRISM automatically synthesizes diverse tasks and environments, elicits plans from the LLM, and uses this synthetic dataset to distill a compact SLM as a drop-in replacement of the source model. We apply PRISM to three LLM-enabled planners for mapping and exploration, manipulation, and household assistance, and we demonstrate that PRISM improves the performance of Llama-3.2-3B from 10-20% of GPT-4o's performance to over 93% - using only synthetic data. We further demonstrate that the distilled planners generalize across heterogeneous robotic platforms (ground and aerial) and diverse environments (indoor and outdoor). We release all software, trained models, and datasets at https://zacravichandran.github.io/PRISM.
