arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1901.09792cs.ROcs.AIcs.LG
收藏

用于人工身体感知的感觉运动学习

Sensorimotor learning for artificial body perception

Technical University of Munich(慕尼黑工业大学)

German Diez-Valencia, Takuya Ohashi, Pablo Lanillos, Gordon Cheng

摘要:

人工自我感知是机器感知自己身体的能力,即,通过特定的传感器/致动器主体配置来执行动作的模态和联运突发事件的掌握。换句话说,与其传感器(例如视觉、本体感受、触觉等)相关的时空模式,它的行为和身体潜变量负责区分自己的身体和世界其他地方。本文介绍了一些最新的人工身体自我感知建模方法:从贝叶斯估计到深度学习。结果显示了这些自由模型无监督或半监督的跨模态/联运学习方法的潜力。然而,在我们实现人工多感官身体感知之前,仍然存在需要克服的挑战。

英文摘要:

Artificial self-perception is the machine ability to perceive its own body, i.e., the mastery of modal and intermodal contingencies of performing an action with a specific sensors/actuators body configuration. In other words, the spatio-temporal patterns that relate its sensors (e.g. visual, proprioceptive, tactile, etc.), its actions and its body latent variables are responsible of the distinction between its own body and the rest of the world. This paper describes some of the latest approaches for modelling artificial body self-perception: from Bayesian estimation to deep learning. Results show the potential of these free-model unsupervised or semi-supervised crossmodal/intermodal learning approaches. However, there are still challenges that should be overcome before we achieve artificial multisensory body perception.

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。

↑