发表机构
THU; PKU; HKUST (GZ)（清华大学; 北京大学; 香港科技大学（广州））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出具身智能可信赖性的四层系统框架，构建涵盖多维度的可信赖性水平层级，为具身智能的可信赖部署、评估等提供依据。
AI 中文摘要
具身智能将学习到的感知与决策能力，同实时计算、控制及物理交互相结合。由于故障可能引发直接的物理或操作危害，仅完成任务不足以确立可信赖性。我们将可信赖的具身智能定义为：在环境与系统变化下，持续可靠执行指定任务，同时将风险维持在可接受范围内的能力，将此目标称为持续安全成功。其支撑机制分为四个相互依赖的层级：模型层生成具备校准不确定性与明确安全偏好的任务胜任动作提案；系统层通过集成感知、计算、控制、硬件防护、故障隔离及回退机制，可靠实现授权动作；证据层通过评估、验证、确认、可追溯性及结构化保障论证，证实有界主张；部署层通过运行时监控、权限管理、干预、事件响应及受控更新，维持主张有效性。由于假设与故障会在各层级间传播，仅靠模型能力、孤立防护或基准性能无法确立端到端可信赖性。结合具身AI、机器人学、控制、可信计算、分布式系统及自动驾驶领域知识，我们进一步提出非规范性的可信赖性水平层级，该层级在任务能力、安全、系统保障、操作治理及支撑证据维度，对有界部署主张的强度进行分级，为有界部署、比较评估、研究优先级设定及未来标准化提供基础。
英文摘要
Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction. Because failures can cause immediate physical or operational harm, task completion alone does not establish trustworthiness. We define trustworthy embodied intelligence as the sustained capacity to execute specified tasks reliably under environmental and system variation while maintaining risk within acceptable bounds. We term this objective sustained safe success. Its supporting mechanisms are organized into four interdependent layers. The model layer generates task-competent action proposals with calibrated uncertainty and explicit safety preferences. The system layer realizes authorized actions dependably through integrated sensing, computation, control, hardware safeguards, fault containment, and fallback. The evidence layer substantiates bounded claims through evaluation, verification, validation, traceability, and structured assurance arguments. The deployment layer maintains claim validity through runtime monitoring, authority management, intervention, incident response, and controlled updates. Because assumptions and failures propagate across these layers, neither model capability, isolated safeguards, nor benchmark performance alone can establish end-to-end trustworthiness. Drawing on embodied AI, robotics, control, dependable computing, distributed systems, and autonomous driving, we further propose a non-normative hierarchy of trustworthiness levels. This hierarchy grades the strength of bounded deployment claims across task capability, safety, system assurance, operational governance, and supporting evidence, providing a basis for bounded deployment, comparative evaluation, research prioritization, and future standardization.
CommentsWebsite: https://xsparkai.com/sparklab/towards-trustworthy-eai
