...
首页> 外文期刊>Kunstliche Intelligenz >Optimal multi-sensor fusion in the context of goal-oriented behavior: A robot study
【24h】

Optimal multi-sensor fusion in the context of goal-oriented behavior: A robot study

机译:面向目标的行为中的最佳多传感器融合:机器人研究

获取原文
获取原文并翻译 | 示例
   

获取外文期刊封面封底 >>

       

摘要

An important component of animal cognition and goal-oriented behavior is the integration of multiple sources of information. Although, in the animals like rats, visual cues seem to be an important source, their navigational capabilities do not cease in the dark, suggesting that the other modalities such as proprioception contributes as well. However, it is not yet clear how the integration of multiple sources of information could be performed to assure optimal performance. Here we take suggestions form the domain of multi-modal speech perception to investigate how in the context of the Distributed Adaptive Control (DAC) architecture, view-dependent visual cues and instantaneous allocentric spatial information can be integrated. We evaluate our model in a robot foraging task. On the basis of our results we suggest mechanisms that could facilitate the transformation of egocentrically defined actions into allocentric behavior.
机译:动物认知和目标导向行为的重要组成部分是多种信息源的整合。尽管在像大鼠这样的动物中,视觉提示似乎是重要的来源,但是它们的导航能力并不会在黑暗中停止,这表明诸如本体感受之类的其他方式也起作用。但是,尚不清楚如何执行多个信息源的集成以确保最佳性能。在这里,我们从多模态语音感知领域提出建议,以研究如何在分布式自适应控制(DAC)体系结构中整合视图相关的视觉提示和瞬时同心圆空间信息。我们在机器人觅食任务中评估模型。根据我们的结果,我们提出了可以促进以自我为中心的行为转变为同心行为的机制。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号