paper-with-me

홈 › Papers

Moto: Latent Motion Token as the Bridging Language for Learning Robot Manipulation from Videos

2024-12-05 · Yi Chen, Yuying Ge, Weiliang Tang, Yizhuo Li, Yixiao Ge, Mingyu Ding, Ying Shan, Xihui Liu

Recent developments in Large Language Models pre-trained on extensive corpora have shown significant success in various natural language processing tasks with minimal fine-tuning. This success offers new promise for robotics, which has long been constrained by the high cost of action-labeled data. We ask: given the abundant video data containing interaction-related knowledge available as a rich "corpus", can a similar generative pre-training approach be effectively applied to enhance robot learning? The key challenge is to identify an effective representation for autoregressive pre-training that benefits robot manipulation tasks. Inspired by the way humans learn new skills through observing dynamic environments, we propose that effective robotic learning should emphasize motion-related knowledge, which is closely tied to low-level actions and is hardware-agnostic, facilitating the transfer of learned motions to actual robot actions. To this end, we introduce Moto, which converts video content into latent Motion Token sequences by a Latent Motion Tokenizer, learning a bridging "language" of motion from videos in an unsupervised manner. We pre-train Moto-GPT through motion token autoregression, enabling it to capture diverse visual motion knowledge. After pre-training, Moto-GPT demonstrates the promising ability to produce semantically interpretable motion tokens, predict plausible motion trajectories, and assess trajectory rationality through output likelihood. To transfer learned motion priors to real robot actions, we implement a co-fine-tuning strategy that seamlessly bridges latent motion token prediction and real robot control. Extensive experiments show that the fine-tuned Moto-GPT exhibits superior robustness and efficiency on robot manipulation benchmarks, underscoring its effectiveness in transferring knowledge from video data to downstream visual manipulation tasks.

📄 PDF Abstract BibTeX arXiv:2412.04445

Code (1)

tencentarc/moto 공식 구현 pytorch

Tasks

Robot Manipulation

Similar Papers 제목 키워드 기반

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

2026-03-19 · Chenyang Gu, Mingyuan Zhang, Haozhe Xie, Zhongang Cai 외 arxiv

Prior motion generation largely follows two paradigms: continuous diffusion models that excel at kinematic control, and discrete token-based generators that are effective for semantic conditioning. To combine their stren…

Motion Synthesis

Robot Learning with Sensorimotor Pre-training

2023-06-16 · Ilija Radosavovic, Baifeng Shi, Letian Fu, Ken Goldberg 외

We present a self-supervised sensorimotor pre-training approach for robotics. Our model, called RPT, is a Transformer that operates on sequences of sensorimotor tokens. Given a sequence of camera images, proprioceptive r…

Motion Planning

Think Before You Move: Latent Motion Reasoning for Text-to-Motion Generation

2025-12-30 · Yijie Qian, Juncheng Wang, Yuxiang Feng, Chao Xu 외 arxiv

Current state-of-the-art paradigms predominantly treat Text-to-Motion (T2M) generation as a direct translation problem, mapping symbolic language directly to continuous poses. While effective for simple actions, this Sys…

Motion Planning

FoMoVLA: Bridging Visual Foresight and Motion Guidance for Vision-Language-Action Models

2026-07-16 · Wei Li, Peijin Jia, Yuan Ma, Xuefeng Jiang 외 arxiv

Vision-Language-Action (VLA) models have achieved impressive results in visuomotor policy learning, yet remain fundamentally reactive, mapping current observations and language to actions without explicit forward predict…

Zero-shot GeneralizationPoint Tracking

From Observation to Action: Latent Action-based Primitive Segmentation for VLA Pre-training in Industrial Settings

2025-11-26 · Jiajie Zhang, Sören Schwertfeger, Alexander Kleiner arxiv

We present a novel unsupervised framework to unlock vast unlabeled human demonstration data from continuous industrial video streams for Vision-Language-Action (VLA) model pre-training. Our method first trains a lightwei…