可调节的视觉-语言-动作策略用于具身推理和分层控制
Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control
AI总结：
本文提出可调节策略，通过训练在丰富合成命令上的视觉-语言-动作模型，提升低层可控性，解锁预训练VLM知识，改进任务泛化能力。
摘要：
预训练的视觉-语言模型（VLMs）能够在多样设置中进行语义和视觉推断，为机器人控制提供有价值的常识先验。然而，有效地将此知识接地到机器人行为仍是一个开放性挑战。先前方法通常采用分层方法，其中VLMs在高层命令上推理，以供单独的低层策略执行，例如视觉-语言-动作模型（VLAs）。VLMs与VLAs之间的接口通常是自然语言任务指令，这从根本上限制了VLM推理如何引导低层行为。因此，我们引入了可调节策略：通过在不同抽象层次的丰富合成命令上训练VLAs，如子任务、动作和接地像素坐标。通过提高低层可控性，可调节策略能够解锁VLMs中的预训练知识，实现改进的任务泛化。我们通过使用学习的高层具身推理器和一个通过上下文学习提示的现成VLM来控制这些可调节策略，展示了这一优势。在广泛的现实世界操作实验中，这两种新方法在任务泛化和长周期任务上优于先前的具身推理VLAs和基于VLM的分层基线。
英文摘要：
Pretrained vision-language models (VLMs) can make semantic and visual inferences across diverse settings, providing valuable common-sense priors for robotic control. However, effectively grounding this knowledge in robot behaviors remains an open challenge. Prior methods often employ a hierarchical approach where VLMs reason over high-level commands to be executed by separate low-level policies, e.g., vision-language-action models (VLAs). The interface between VLMs and VLAs is usually natural language task instructions, which fundamentally limits how much VLM reasoning can steer low-level behavior. We thus introduce Steerable Policies: VLAs trained on rich synthetic commands at various levels of abstraction, like subtasks, motions, and grounded pixel coordinates. By improving low-level controllability, Steerable Policies can unlock pretrained knowledge in VLMs, enabling improved task generalization. We demonstrate this benefit by controlling our Steerable Policies with both a learned high-level embodied reasoner and an off-the-shelf VLM prompted to reason over command abstractions via in-context learning. Across extensive real-world manipulation experiments, these two novel methods outperform prior embodied reasoning VLAs and VLM-based hierarchical baselines, including on challenging generalization and long-horizon tasks. Website: steerable-policies.github.io
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。
