| August to September 2023 |
Spatial Cognition and Artificial Intelligence:
Methods for In-The-Wild Behavioural Research in Visual Perception
The tutorial on “Spatial Cognition and Artiﬁcial Intelligence” addresses the conﬂuence of empirically based behavioural research in the cognitive and psychological sciences with computationally driven analytical methods rooted in artiﬁcial intelligence and machine learning. This conﬂuence is addressed in the backdrop of human behavioural research concerned with “in-the-wild” naturalistic embodied multimodal interaction. The tutorial presents:
- an interdisciplinary perspective on conducting evidence-based (possibly large-scale) human behaviour research from the viewpoints of visual perception, environmental psychology, and spatial cognition.
- artiﬁcial intelligence methods for the semantic interpretation of embodied multimodal interaction (e.g., rooted in behavioural data), and the (empirically driven) synthesis of interactive embodied cognitive experiences in real-world settings relevant to both everyday life as well to professional creative-technical spatial thinking.
- 3. the relevance and impact of research in cognitive human-factors (e.g., in spatial cognition) for the design and implementation of next-generation human-centred AI technologies.
Spatio-Temporal Reasoning and Learning (STRL)
Opposing the false dilemma of logical reasoning vs machine learning, we argue for a synergy between these two paradigms in order to obtain hybrid, human-centred AI systems that will be robust, generalisable, explainable, and ecologically valid. Indeed, it is well-known that machine learning only includes statistical information and, therefore, on its own is inherently unable to capture perturbations (interventions or changes in the environment), or perform explainable reasoning and planning. Ideally, (the training of) machine learning models should be tied to assumptions that align with physics and human cognition to allow for these models to be re-used and re-purposed in novel scenarios. On the other hand, it is also the case that logic in itself can be brittle too, and logic further assumes that the symbols with which it can reason are available a priori. It is becoming ever more evident in the literature that modular AI architectures should be prioritised, where the involved knowledge about the world and the reality that we are operating in is decomposed into independent and recomposable pieces, as such an approach should only increase the chances that these systems behave in a causally sound manner.
The aim of this workshop is to formalize such a synergy between logical reasoning and machine learning that will be grounded on spatial and temporal knowledge. We argue that the formal methods developed within the spatial and temporal reasoning community, be it qualitative or quantitative, naturally build upon (commonsense) physics and human cognition, and could therefore form a module that would be beneficial towards causal representation learning. A (relational) spatio-temporal knowledge base could provide a foundation upon which machine learning models could generalise, and exploring this direction from various perspectives is the main theme of this workshop.