提出双向自回归动作预测新方法，提升机器人操作精度
Dense Policy: Bidirectional Autoregressive Learning of Actions
- 采用轻量编码器架构，分步细化生成动作序列
- 对齐现有生成式策略，在多个任务上实现更优表现
- 适合需要高精度动作预测的机器人控制场景
主流视觉-运动策略多依赖生成模型进行整体动作预测，而现有自回归策略（逐个片段预测）表现欠佳。本文提出双向扩展学习方法Dense Policy，建立自回归策略新范式。该方法采用轻量级编码器架构，从初始单帧出发，以粗到精方式对动作序列进行迭代展开，实现对数时间推理。大量实验表明，所提策略在自回归学习能力上显著优于现有方法，并超越当前主流生成式策略。论文将公开示例数据与训练代码。项目页面：https://selen-suyue.github.io/DspNet/
原文摘要 · Abstract (English)
Mainstream visuomotor policies predominantly rely on generative models for holistic action prediction, while current autoregressive policies, predicting the next token or chunk, have shown suboptimal results. This motivates a search for more effective learning methods to unleash the potential of autoregressive policies for robotic manipulation. This paper introduces a bidirectionally expanded learning approach, termed Dense Policy, to establish a new paradigm for autoregressive policies in action prediction. It employs a lightweight encoder-only architecture to iteratively unfold the action sequence from an initial single frame into the target sequence in a coarse-to-fine manner with logarithmic-time inference. Extensive experiments validate that our dense policy has superior autoregressive learning capabilities and can surpass existing holistic generative policies. Our policy, example data, and training code will be publicly available upon publication. Project page: https: //selen-suyue.github.io/DspNet/.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。