让机器人像人一样理解任务并可交互教学，提升真实场景下的执行成功率。
WCM: World-Cognition Model for Generalizable Human-Robot Interaction
- 基于感知-逻辑-动作-知识分离架构，支持多任务并发推理与对话
- 在9个真实任务中达成73.8%平均成功率，包括未训练过的长程任务
- 支持用户交互式教学，通过思维链监督持续优化行为
语言代理已能在软件中流畅与用户交互，但机器人在物理任务中仍难以实现类似能力。现有机器人控制范式（如视觉-语言-动作策略与基于世界模型的规划器）主要优化指令执行，导致用户无法了解动作决策原因，也缺乏干预、纠正或教学机器人的机制。为此，我们提出世界认知模型（WCM），一种以用户为中心的具身智能体，基于SLAK架构（感知、逻辑、动作、知识）和异步运行时设计。该架构分离感知、推理、控制与记忆模块，运行时允许推理、对话与执行并行进行。WCM引入人机协同教学模式，使用户能交互式教授机器人复杂或长周期任务。教学过程与自主任务执行被统一为思维链监督信号，持续优化模型表现。在九个真实世界人机交互任务中，WCM实现73.8%的平均成功率，涵盖未参与思维链微调的任务以及通过教学学习的长周期任务。
原文摘要 · Abstract (English)
Language agents can now interact fluently with users in software, but robots still struggle to bring comparable interaction to physical tasks. Current robot-control paradigms, including vision-language-action policies and world-model-based planners, are mainly optimized for instruction execution, leaving users with little visibility into why an action is chosen and few mechanisms to redirect, correct, or teach the robot through interaction. To solve this problem, we present the World-Cognition Model (WCM), a human-centered embodied agent built on the SLAK architecture (Sensing, Logic, Action, and Knowledge) and an asynchronous runtime. SLAK separates perception, reasoning, control, and memory, while the runtime allows reasoning, dialogue, and execution to proceed concurrently. WCM further introduces a human-in-the-loop teaching mode that enables users to interactively teach the robot difficult or long-horizon tasks. Teaching episodes and autonomous task rollouts are refined into chain-of-thought supervision to continually improve the model. WCM achieves a 73.8% average success rate across nine real-world human-robot interaction tasks, including tasks held out from CoT fine-tuning and a long-horizon task learned through teaching.
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。