Automatic Compliance Checking (ACC) within the Architecture, Engineering, and Construction (AEC) sector necessitates automating the interpretation of building regulations to achieve its full potential. Converting textual rules into machine-readable formats is challenging due to the complexities of natural language and the scarcity of resources for advanced Machine Learning (ML). Addressing these challenges, we introduce CODE-ACCORD, a dataset of 862 sentences from the building regulations of England and Finland. Only the self-contained sentences, which express complete rules without needing additional context, were considered as they are essential for ACC. Each sentence was manually annotated with entities and relations by a team of 12 annotators to facilitate machine-readable rule generation, followed by careful curation to ensure accuracy. The final dataset comprises 4,297 entities and 4,329 relations across various categories, serving as a robust ground truth. CODE-ACCORD supports a range of ML and Natural Language Processing (NLP) tasks, including text classification, entity recognition, and relation extraction. It enables applying recent trends, such as deep neural networks and large language models, to ACC.

Affordances - i.e. possibilities for action that an environment or objects in it provide - are important for robots operating in human environments to perceive. Existing approaches train such capabilities on annotated static images or shapes. This work presents a novel dataset for affordance learning of common household tasks. Unlike previous approaches, our dataset consists of video sequences demonstrating the tasks from first- and third-person perspectives, along with metadata about the affordances that are manifested in the task, and is aimed towards training perception systems to recognize affordance manifestations. The demonstrations were collected from several participants and in total record about seven hours of human activity. The variety of task performances also allows studying preparatory maneuvers that people may perform for a task, such as how they arrange their task space, which is also relevant for collaborative service robots.

Derived from the embodied cognition hypothesis, image schemas are conceptual primitives thought to capture the spatiotemporal relationships underlying human conceptualisations. However, many embodied experiences are not spatiotemporal but rather based on the different sensory modalities. In order to provide a more comprehensive perspective of conceptual primitives, this paper looks at the traditional five senses and sketches an initial perspective of how some conceptual primitives could be systematically approached.

In recent years, generative AI systems for music composition have transformed not only music generation but the field of computational creativity as a whole. In contrast to the black-boxes of deep learning techniques, classic algorithms offer a transparent alternative to music generation that does not require training data and, due to the autonomous process, such systems could be argued to reflect a more genuine creative process. One such algorithmic system is cellular automata. Designed as grids of binary nodes, cellular automata use mathematical rules to transition between different states that can be used to generate music. The initial state and the particular transition rules allow different patterns to emerge which can be translated into musical compositions. In this paper, we introduce AUTOMATONE, a semi-interactive music generator based on the cellular automaton Conway’s Game of Life. To ensure the quality of the music output, AUTOMATONE is based on pentatonic scales and uses four different state-transition systems to generate beats of different tempos.

The recent remarkable success of generative AI models to create text and images has already started altering our perspective of intelligence and the “uniqueness” of humanity in this world. Simultaneously, arguments on why AI will never exceed human intelligence are ever-present as seen in Landgrebe and Smith (2022). To address whether machines may rule the world after all, this paper zooms in on one of the aspects of intelligence Landgrebe and Smith (2022) neglected to consider: creativity. Using Rhodes four Ps of creativity as a starting point, this paper evaluates the creative ability in visual generative AI models with respect to the state of the art in creativity theory. The most part of the reflective evaluation is performed through a case study in generating illustrations of dogs using the generative AI tool Midjourney. 

Situationally-aware artificial agents operating with competence in natural environments face several challenges: spatial awareness, object affordance detection, dynamic changes and unpredictability. A critical challenge is the agent’s ability to identify and monitor environmental elements pertinent to its objectives. Our research introduces a neurosymbolic modular architecture for reactive robotics. Our system combines a neural component performing object recognition over the environment and image processing techniques such as optical flow, with symbolic representation and reasoning. The reasoning system is grounded in the embodied cognition paradigm, via integrating image schematic knowledge in an ontological structure. The ontology is operatively used to create queries for the perception system, decide on actions, and infer entities’ capabilities derived from perceptual data. The combination of reasoning and image processing allows the agent to focus its perception for normal operation as well as discover new concepts for parts of objects involved in particular interactions. The discovered concepts allow the robot to autonomously acquire training data and adjust its subsymbolic perception to recognize the parts, as well as making planning for more complex tasks feasible by focusing search on those relevant object parts. We demonstrate our approach in a simulated world, in which an agent learns to recognize parts of objects involved in support relations. While the agent has no concept of handle initially, by observing examples of supported objects hanging from a hook it learns to recognize the parts involved in establishing support and becomes able to plan the establishment/destruction of the support relation. This underscores the agent’s capability to expand its knowledge through observation in a systematic way, and illustrates the potential of combining deep reasoning with reactive robotics in dynamic settings.

From conference website: 

The International Conference on Computational Creativity is the premier forum for disseminating research on computational and AI creativity, bringing together researchers interested in exploring the ever increasing capacities of technology in creative domains such as writing, visual arts and music. State-of-the-art AI-algorithms can now create works that to a casual observer are comparable to those of human professionals, but many have questioned whether this is sufficient (or even necessary) for a computer to be considered to be “acting creatively”. This conference and its associated workshops exist to discuss the how and what of computational participation in creativity.

Come join us in the beautiful Swedish town of Jönköping ([ˈjœ̂nːˌɕøːpɪŋ]) at Midsummer and discuss questions like: by which metrics should we judge the creativity of AI output? Can an AI tool augment the creativity of its human users? What are the ethical implications of algorithms taking on creative roles? And, of course: can an AI be creative at all? These questions and more are at the heart of the sub-field of AI known as Computational Creativity (CC), defined as “the art, science, philosophy, and engineering of computational systems which, by taking on particular responsibilities, exhibit behaviors that unbiased observers would deem to be creative”.

Progress in AI raises agent alignment problems. In this paper, we look at the problem of instructing an agent, i.e. informing it about a regularity in the world it did not previously know. We study an idealized case: agents reasoning with logical theories. The idealization helps to understand the space of possibilities of the problem, and illustrates potential pitfalls and solutions. We believe non-monotonic theories more plausibly approximate human practical and commonsense reasoning so our agents here also use non-monotonic inference. However, instructing a non-monotonic theory does not always result in better alignment. One main cause of this phenomenon is humans omitting the kind of information used by a non-monotonic inference system to resolve conflicts between its parts. We illustrate this with theories induced from a dataset consisting of situated objects. We argue that obtaining non-monotonic theories that respond better to instruction requires additional restrictions on the formalism and theory update procedure.

Image schemas are mental patterns learned from perceptual experiences capturing conceptual constructions in expressions. In linguistic analysis, their visualizations are often context-dependent without a generalizable structure. Addressing this, we introduce The Diagrammatic Image Schema Language: a formal representation language that systematizes a set of visual combination rules for different conceptual primitives from the cognitive science literature. These primitives are distinguished from a formal point of view to allow for more general application. DISL also contains a logical exchange format in which the diagrams may be made machine-readable. Using DISL, the semantic structure of complex scenarios can be represented and computed.