TuringPAI:オンデバイス物理AIの基盤モデル群
TuringPAI: A Foundation for On-Device Physical AI
視覚言語理解・自動運転・ロボット操作を担う小型モデル群TuringPAIを提案し、車載SoC上でのリアルタイム動作やLIBEROでの高成功率を実現した。
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: Qiman Wu, Hanlin Chen, Yuhua Wei, Mingyuan Wang, Shaman Tang, Minghao Li, Rui Xin, Xingye Liu, Zhichao Yang, Yiqi Yu, Hongyan Pei, Xiaowen Tian, YingYing Liu, Shiwen Liu, Jiahui Hu, Yizhao Wang, Yuheng Zhang, Anhua Liu, Yue He, Shuang Su, Da Zhu, Hua Zhou, Pengfei Diao, Haojie Yang, Weichao Huang, Hang Zhang, Honggou Yang, Xianming Liu
分類: cs.CV, cs.RO
原文アブストラクト
Physical AI requires models that understand spatial relationships and dynamic environments and translate observations into actions under limited onboard compute. We present TuringPAI, a family of models for on-device Physical AI comprising TuringPAI-VL for shared vision-language understanding, TuringPAI-Drive for autonomous driving, and TuringPAI-Embodied for robotic manipulation. TuringPAI-VL is a 0.65B model built on HybridViT-MLQ, which combines convolutional local aggregation with Transformer-based global modeling. Multi-scale Latent Queries integrate spatial features and observation history within the same visual Transformer, providing a compact, structured interface to the language model. Training combines general vision-language data with geometric, cross-view, and temporal supervision. TuringPAI-VL supports general multimodal understanding and improves quantitative geometric perception over Qwen2-VL-2B, while providing a shared initialization for the two downstream VLA models. For autonomous driving, TuringPAI-Drive maintains all evaluated ADE/FDE metrics within 1.2\% of a full-token HybridViT baseline using the MLQ interface and achieves comparable aggregate scores in an in-house simulation evaluation. Using XPeng Native Runtime (XNRT) on a single NVIDIA Orin-X SoC, TuringPAI-Drive generates trajectories at 12\,Hz in on-vehicle operation. For robotic manipulation, TuringPAI-Embodied achieves a 96.8\% average success rate across the four LIBERO suites. These results demonstrate a shared vision-language foundation for driving and robotic manipulation under practical on-device constraints.
