Dense Policy：动作的双向自回归学习
Dense Policy: Bidirectional Autoregressive Learning of Actions
AI总结：
本文提出 Dense Policy，通过双向扩展、仅编码器的从粗到细自回归学习实现对数时间动作序列预测，并在机器人操作实验中超越现有整体生成式策略。
摘要：
主流视觉运动策略主要依赖生成模型进行整体动作预测，而当前预测下一 token 或动作块的自回归策略表现并不理想。这促使人们寻找更有效的学习方法，以释放自回归策略在机器人操作中的潜力。本文提出一种双向扩展的学习方法，称为 Dense Policy，旨在为动作预测中的自回归策略建立新范式。该方法采用轻量级仅编码器架构，以从粗到细的方式，将动作序列从初始单帧迭代展开为目标序列，并实现对数时间推理。大量实验验证，我们的 dense policy 具有优越的自回归学习能力，并且能够超越现有的整体生成式策略。我们的策略、示例数据和训练代码将在论文发表后公开。项目页面：https://selen-suyue.github.io/DspNet/。
英文摘要：
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/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
