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 2201.10266cs.AIcs.CVcs.LGcs.LOcs.RO
收藏

结合常识推理和知识获取指导机器人中的深度学习

Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics

University of Birmingham(伯明翰大学);The University of Auckland(奥克兰大学)

Mohan Sridharan, Tiago Mota

摘要:

基于深度网络模型的算法正在用于机器人和人工智能中的许多模式识别和决策任务。训练这些模型需要大量的标记数据集和大量的计算资源,这在许多领域都不容易获得。同时,也很难探索这些模型的内部表示和推理机制。作为解决底层知识表示、推理和学习挑战的一步,本文描述的架构从认知系统的研究中汲取灵感。作为一个激励的例子,我们考虑一个辅助机器人试图减少混乱,在任何给定的场景中,通过推理的对象的遮挡和稳定的对象配置的图像中的场景。在这种情况下,我们的架构逐步学习和修改对象之间的空间关系的接地,并使用此接地从输入图像中提取空间信息。非单调逻辑推理与此信息和不完整的常识领域的知识是用来作出决定的稳定性和闭塞。对于无法通过这种推理处理的图像,自动识别与手头任务相关的区域,并用于训练深度网络模型以做出所需的决策。用于训练深度网络的图像区域也用于增量地获取先前未知的状态约束,这些状态约束与现有知识合并以用于后续推理。使用模拟和真实图像进行的实验评估表明,与仅基于深度网络的基线相比,我们的架构提高了决策的可靠性,并减少了训练数据驱动的深度网络模型所涉及的工作。

英文摘要:

Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not readily available in many domains. Also, it is difficult to explore the internal representations and reasoning mechanisms of these models. As a step towards addressing the underlying knowledge representation, reasoning, and learning challenges, the architecture described in this paper draws inspiration from research in cognitive systems. As a motivating example, we consider an assistive robot trying to reduce clutter in any given scene by reasoning about the occlusion of objects and stability of object configurations in an image of the scene. In this context, our architecture incrementally learns and revises a grounding of the spatial relations between objects and uses this grounding to extract spatial information from input images. Non-monotonic logical reasoning with this information and incomplete commonsense domain knowledge is used to make decisions about stability and occlusion. For images that cannot be processed by such reasoning, regions relevant to the tasks at hand are automatically identified and used to train deep network models to make the desired decisions. Image regions used to train the deep networks are also used to incrementally acquire previously unknown state constraints that are merged with the existing knowledge for subsequent reasoning. Experimental evaluation performed using simulated and real-world images indicates that in comparison with baselines based just on deep networks, our architecture improves reliability of decision making and reduces the effort involved in training data-driven deep network models.

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。

↑