提出可复用的具身智能模块，提升系统部署与集成效率。
Embodied Operators and Benchmarking: Toward Reusable and Deployable Embodied Intelligence Systems
- 将具身智能功能拆解为可组合的标准化模块，明确输入输出规范。
- 构建多维评估框架，覆盖正确性、效率、稳定性等8个维度。
- 适合系统设计者、部署工程师及具身智能平台开发者参考。
具身智能系统不仅需要端到端策略模型，还需可复用的功能模块，用于将多模态观测、机器人状态、人类示范和任务上下文转化为结构化表示、决策、轨迹、控制参考和系统服务。本文将此类模块定义为具身操作符（embodied operators），并将其作为具身智能流程中独立且可组合的单元进行研究。我们明确了其定义边界，强调任务语义、标准输入输出契约、可部署性、可复用性及多层可优化性。进一步构建了涵盖五类的分类体系：检测与分割、空间定位与3D理解、手部运动恢复、具身基础模型与任务决策操作符，以及规划、控制与系统支持操作符。每类总结代表性功能、技术范式、应用角色与实际局限。除分类外，提出多维基准评估框架，从正确性、端到端效率、资源消耗、时间稳定性、可移植性、接口兼容性、部署可靠性及下游任务效用等方面评估操作符。还讨论工作流级操作符加速及操作符组合、数据标准化、世界模型、视觉-语言-动作安全、边缘部署与真实场景应用价值等开放挑战。总体认为，具身操作符应作为整体可部署组件进行优化与评估，为可复用、可扩展、可验证的具身智能系统奠定基础。
原文摘要 · Abstract (English)
Embodied intelligence systems require not only end-to-end policy models, but also reusable functional modules that transform multimodal observations, robot states, human demonstrations, and task contexts into structured representations, decisions, trajectories, control references, and system services. This work defines these modules as embodied operators and studies them as independent yet composable units in embodied intelligence pipelines. We clarify their definition boundary, emphasizing task semantics, standardized input-output contracts, deployability, reusability, and multi-layer optimizability. We further construct a taxonomy covering five categories: detection and segmentation, spatial localization and 3D understanding, hand motion recovery, embodied foundation models and task-decision operators, and planning, control, and system support operators. For each category, we summarize representative functions, technical paradigms, application roles, and practical limitations. Beyond taxonomy, we propose a multi-dimensional benchmark framework that evaluates embodied operators in terms of correctness, end-to-end efficiency, resource usage, temporal stability, portability, interface compatibility, deployment reliability, and downstream task utility. We also discuss workflow-level operator acceleration and open challenges in operator composition, data standardization, world models, VLA safety, edge deployment, and real-world application value. Overall, this work argues that embodied operators should be optimized and evaluated as holistic deployable components, providing a foundation for reusable, scalable, and verifiable embodied intelligence systems.
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。