• DOI:10.48550/arXiv.2211.15566
• Corpus ID: 254043470

Neuro-Symbolic Spatio-Temporal Reasoning

@article{Lee2022NeuroSymbolicSR,
  title={Neuro-Symbolic Spatio-Temporal Reasoning},
  author={Jae Hee Lee and Michael Sioutis and Kyra Ahrens and Marjan Alirezaie and Matthias Kerzel and Stefan Wermter},
  journal={ArXiv},
  year={2022},
  volume={abs/2211.15566}
}

• Jae Hee Lee, Michael Sioutis, +3 authors S. Wermter
• Published 28 November 2022
• Computer Science
• ArXiv

Knowledge about space and time is an essential prerequisite for solving problems in the physical world: An artificial intelligence (AI) agent, when situated in a physical environment and interacting with objects, often needs to reason about positions of and relations between objects; and as soon as the agent plans its actions to solve a task, it needs to consider the temporal aspect (e.g., what actions to perform over time). Spatio-temporal knowledge, however, is required beyond interacting with the physical world, and is also often transferred to the abstract world of concepts through analogies and metaphors (e.g., “a threat that is hanging over our heads”). As spatial and temporal reasoning is ubiquitous, different attempts have been made to integrate this into AI systems. In the area of knowledge representation, spatial and temporal reasoning has been largely limited to modeling objects and relations and developing reasoning methods to verify statements about them [1, 2, 3, 4]; even so, it has found its way into applications in many areas and domains that include cognitive robotics [5], qualitative model generation from video [6], ambient intelligence [7], and data mining [8]. On the other hand, neural network researchers have tried to teach models to learn spatial relations from data despite limited reasoning capabilities [9, 10, 11]. Bridging the gap between these two approaches in a mutually beneficial way could allow us to tackle many complex tasks, such as natural language processing, visual question answering, and semantic image segmentation (cf. [12, 13, 14]).