arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2512.07041cs.RO
收藏

CERNet:用于统一机器人运动、识别和置信度估计的类嵌入预测编码RNN

CERNet: Class-Embedding Predictive-Coding RNN for Unified Robot Motion, Recognition, and Confidence Estimation

Equipe Traitement de l’Information et Systèmes Laboratory (ETIS Laboratory), CNRS UMR8051, CY Cergy-Paris Université, ENSEA, Cergy, France(信息与系统实验室(ETIS实验室),CNRS UMR8051,CY塞克-巴黎大学,ENSEA,塞克,法国)

Hiroki Sawada, Alexandre Pitti, Mathias Quoy

AI总结:

CERNet通过类嵌入预测编码RNN实现机器人运动生成、识别和置信度估计的统一模型,显著降低轨迹误差并提升实时识别准确率。

摘要:

机器人与人类互动时,不仅要实时生成学习到的运动,还要推断观察到的行为意图并估计自身推断的置信度。本文提出了一种统一模型,即CERNet,该模型在单个分层预测编码递归神经网络(PC-RNN)中实现所有三种能力,该网络配备了类嵌入向量。CERNet利用动态更新的类嵌入向量来统一运动生成和识别。该模型运行在两种模式中:生成模式和推断模式。在生成模式中,类嵌入约束隐藏状态动态到特定类的子空间;在推断模式中,它被优化以最小化预测误差,从而实现实时识别。在26个肌理教学字母的人形机器人上验证了该模型,其分层模型在与参数匹配的单层基线相比,轨迹再现误差降低了76%,在外部扰动下保持运动保真度,并能在线推断演示轨迹类别,准确率分别为68% Top-1和81% Top-2。此外,内部预测误差自然反映了模型对识别的置信度。这种在紧凑PC-RNN框架内集成了鲁棒生成、实时识别和内在不确定性估计的方法,为物理机器人的运动记忆提供了一种紧凑且可扩展的解决方案,有望应用于意图敏感的人机协作。

英文摘要:

Robots interacting with humans must not only generate learned movements in real-time, but also infer the intent behind observed behaviors and estimate the confidence of their own inferences. This paper proposes a unified model that achieves all three capabilities within a single hierarchical predictive-coding recurrent neural network (PC-RNN) equipped with a class embedding vector, CERNet, which leverages a dynamically updated class embedding vector to unify motor generation and recognition. The model operates in two modes: generation and inference. In the generation mode, the class embedding constrains the hidden state dynamics to a class-specific subspace; in the inference mode, it is optimized online to minimize prediction error, enabling real-time recognition. Validated on a humanoid robot across 26 kinesthetically taught alphabets, our hierarchical model achieves 76% lower trajectory reproduction error than a parameter-matched single-layer baseline, maintains motion fidelity under external perturbations, and infers the demonstrated trajectory class online with 68% Top-1 and 81% Top-2 accuracy. Furthermore, internal prediction errors naturally reflect the model's confidence in its recognition. This integration of robust generation, real-time recognition, and intrinsic uncertainty estimation within a compact PC-RNN framework offers a compact and extensible approach to motor memory in physical robots, with potential applications in intent-sensitive human-robot collaboration.

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。

↑