Diffusion Transformer Policy
- URL: http://arxiv.org/abs/2410.15959v1
- Date: Mon, 21 Oct 2024 12:43:54 GMT
- Title: Diffusion Transformer Policy
- Authors: Zhi Hou, Tianyi Zhang, Yuwen Xiong, Hengjun Pu, Chengyang Zhao, Ronglei Tong, Yu Qiao, Jifeng Dai, Yuntao Chen,
- Abstract summary: Diffusion Transformer Policy pretrained on diverse robot data can generalize to different embodiments.
The proposed approach achieves state-of-the-art performance with only a single third-view camera stream in the Calvin novel task setting.
- Score: 48.50988753948537
- License:
- Abstract: Recent large visual-language action models pretrained on diverse robot datasets have demonstrated the potential for generalizing to new environments with a few in-domain data. However, those approaches usually predict discretized or continuous actions by a small action head, which limits the ability in handling diverse action spaces. In contrast, we model the continuous action with a large multi-modal diffusion transformer, dubbed as Diffusion Transformer Policy, in which we directly denoise action chunks by a large transformer model rather than a small action head. By leveraging the scaling capability of transformers, the proposed approach can effectively model continuous end-effector actions across large diverse robot datasets, and achieve better generalization performance. Extensive experiments demonstrate Diffusion Transformer Policy pretrained on diverse robot data can generalize to different embodiments, including simulation environments like Maniskill2 and Calvin, as well as the real-world Franka arm. Specifically, without bells and whistles, the proposed approach achieves state-of-the-art performance with only a single third-view camera stream in the Calvin novel task setting (ABC->D), improving the average number of tasks completed in a row of 5 to 3.6, and the pretraining stage significantly facilitates the success sequence length on the Calvin by over 1.2. The code will be publicly available.
Related papers
- FAST: Efficient Action Tokenization for Vision-Language-Action Models [98.15494168962563]
We propose a new compression-based tokenization scheme for robot actions, based on the discrete cosine transform.
Based on FAST, we release FAST+, a universal robot action tokenizer, trained on 1M real robot action trajectories.
arXiv Detail & Related papers (2025-01-16T18:57:04Z) - CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction [28.761494362934087]
Coarse-to-Fine AutoRegressive Policy (CARP) is a novel paradigm for visuomotor policy learning.
It redefines the autoregressive action generation process as a coarse-to-fine, next-scale approach.
CARP achieves competitive success rates, with up to a 10% improvement, and delivers 10x faster inference compared to state-of-the-art policies.
arXiv Detail & Related papers (2024-12-09T18:59:18Z) - Autoregressive Action Sequence Learning for Robotic Manipulation [32.9580007141312]
Existing autoregressive architectures generate end-effector waypoints sequentially as word tokens in language modeling.
We extend causal transformers' single-token prediction to support predicting a variable number of tokens in a single step.
We propose the Autoregressive Policy architecture, which solves manipulation tasks by generating hybrid action sequences.
arXiv Detail & Related papers (2024-10-04T04:07:15Z) - Emergent Agentic Transformer from Chain of Hindsight Experience [96.56164427726203]
We show that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
This is the first time that a simple transformer-based model performs competitively with both temporal-difference and imitation-learning-based approaches.
arXiv Detail & Related papers (2023-05-26T00:43:02Z) - Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation [52.94101901600948]
We develop PerAct, a language-conditioned behavior-cloning agent for multi-task 6-DoF manipulation.
PerAct encodes language goals and RGB-D voxel observations with a Perceiver Transformer, and outputs discretized actions by "detecting the next best voxel action"
Our results show that PerAct significantly outperforms unstructured image-to-action agents and 3D ConvNet baselines for a wide range of tabletop tasks.
arXiv Detail & Related papers (2022-09-12T17:51:05Z) - An Empirical Study of Training End-to-End Vision-and-Language
Transformers [50.23532518166621]
We present METER(textbfMultimodal textbfEnd-to-end textbfTransformtextbfER), through which we investigate how to design and pre-train a fully transformer-based VL model.
Specifically, we dissect the model designs along multiple dimensions: vision encoders (e.g., CLIP-ViT, Swin transformer), text encoders (e.g., RoBERTa, DeBERTa), multimodal fusion (e.g., merged attention vs. co-
arXiv Detail & Related papers (2021-11-03T17:55:36Z) - UPDeT: Universal Multi-agent Reinforcement Learning via Policy
Decoupling with Transformers [108.92194081987967]
We make the first attempt to explore a universal multi-agent reinforcement learning pipeline, designing one single architecture to fit tasks.
Unlike previous RNN-based models, we utilize a transformer-based model to generate a flexible policy.
The proposed model, named as Universal Policy Decoupling Transformer (UPDeT), further relaxes the action restriction and makes the multi-agent task's decision process more explainable.
arXiv Detail & Related papers (2021-01-20T07:24:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.