RoboAgent: 通过基本能力串联实现具身任务规划
RoboAgent: Chaining Basic Capabilities for Embodied Task Planning
AI总结：
本文提出RoboAgent，通过串联基本能力实现具身任务规划，利用单个VLM构建能力驱动的规划框架，结合多阶段训练方法提升规划效果。
摘要：
本文聚焦具身任务规划，研究代理如何通过视觉观察环境并执行原子动作完成任务。尽管最近的视觉-语言模型（VLMs）在多模态理解和推理上表现优异，但其在涉及多轮交互、长周期推理和扩展上下文分析的具身规划中表现有限。为弥合这一差距，我们提出了RoboAgent，一种能力驱动的规划流程，其中模型主动调用不同子能力。每个能力维护自己的上下文，并根据调度器提供的查询生成中间推理结果或与环境交互。该框架将复杂规划分解为一系列基本视觉-语言问题，这些问题是VLMs能更好地处理的，从而实现更透明和可控的推理过程。调度器和所有能力均通过单个VLM实现，不依赖外部工具。为了训练此VLM，我们采用多阶段范式，包括：（1）使用专家计划的行为克隆，（2）使用模型收集的轨迹进行DAgger训练，（3）由专家策略引导的强化学习。在这些阶段中，我们利用环境模拟器的内部信息为每个能力构建高质量的监督，并进一步引入增强和合成数据以提升模型在更多样化场景中的表现。在广泛使用的具身任务规划基准上进行的大量实验验证了所提方法的有效性。我们的代码将在https://github.com/woyut/RoboAgent_CVPR26提供。
英文摘要：
This paper focuses on embodied task planning, where an agent acquires visual observations from the environment and executes atomic actions to accomplish a given task. Although recent Vision-Language Models (VLMs) have achieved impressive results in multimodal understanding and reasoning, their performance remains limited when applied to embodied planning that involves multi-turn interaction, long-horizon reasoning, and extended context analysis. To bridge this gap, we propose RoboAgent, a capability-driven planning pipeline in which the model actively invokes different sub-capabilities. Each capability maintains its own context, and produces intermediate reasoning results or interacts with the environment according to the query given by a scheduler. This framework decomposes complex planning into a sequence of basic vision-language problems that VLMs can better address, enabling a more transparent and controllable reasoning process. The scheduler and all capabilities are implemented with a single VLM, without relying on external tools. To train this VLM, we adopt a multi-stage paradigm that consists of: (1) behavior cloning with expert plans, (2) DAgger training using trajectories collected by the model, and (3) reinforcement learning guided by an expert policy. Across these stages, we exploit the internal information of the environment simulator to construct high-quality supervision for each capability, and we further introduce augmented and synthetic data to enhance the model's performance in more diverse scenarios. Extensive experiments on widely used embodied task planning benchmarks validate the effectiveness of the proposed approach. Our codes will be available at https://github.com/woyut/RoboAgent_CVPR26.
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。
