ICINCO 2025 (22nd International Conference on Informatics in Control, Automation and Robotics) received 158 paper submissions from 42 countries. To evaluate each submission, a double-blind paper review was performed by the Program Committee. After a stringent selection process, 43 papers were published and presented as full papers, i.e. completed work (12 pages/25' oral presentation), 86 papers were accepted as short papers (51 as oral presentation). The organizing committee included the ICINCO Conference Chair: Dimitar Filev, Ford Research, United States, and the ICINCO 2025 Program Chairs: Giuseppina Carla Gini, Politecnico di Milano, Italy, and Radu-Emil Precup, Politehnica University of Timisoara, Romania. At the closing session, the conference acknowledged a few papers that were considered excellent in their class, presenting a "Best Paper Award", "Best Student Paper Award", "Best Poster Award", and "Best Industrial Paper Award" for the conference.

Machine Learning (ML) is an expressive framework for turning data into computer programs. Across many problem domains -- both in industry and policy settings -- the types of computer programs needed for accurate prediction or optimal control are difficult to write by hand. On the other hand, collecting instances of desired system behavior may be relatively more feasible. This makes ML broadly appealing, but also induces data sensitivities that often manifest as unexpected failure modes during deployment. In this sense, the training data available tend to be imperfect for the task at hand. This thesis explores several data sensitivities of modern machine learning and how to address them. We begin by discussing how to prevent ML from codifying prior human discrimination measured in the training data, where we take a fair representation learning approach. We then discuss the problem of learning from data containing spurious features, which provide predictive fidelity during training but are unreliable upon deployment. Here we observe that insofar as standard training methods tend to learn such features, this propensity can be leveraged to search for partitions of training data that expose this inconsistency, ultimately promoting learning algorithms invariant to spurious features. Finally, we turn our attention to reinforcement learning from data with insufficient coverage over all possible states and actions. To address the coverage issue, we discuss how causal priors can be used to model the single-step dynamics of the setting where data are collected. This enables a new type of data augmentation where observed trajectories are stitched together to produce new but plausible counterfactual trajectories.

Artificial intelligence's (AI) progress holds great promise in tackling pressing societal concerns such as health and climate. Large Language Models (LLM) and the derived chatbots, like ChatGPT, have highly improved the natural language processing capabilities of AI systems allowing them to process an unprecedented amount of unstructured data. However, the ensuing excitement has led to negative sentiments, even as AI methods demonstrate remarkable contributions (e.g. in health and genetics). A key factor contributing to this sentiment is the misleading perception that LLMs can effortlessly provide solutions across domains, ignoring their limitations such as hallucinations and reasoning constraints. Acknowledging AI fallibility is crucial to address the impact of dogmatic overconfidence in possibly erroneous suggestions generated by LLMs. At the same time, it can reduce fear and other negative attitudes toward AI. This necessitates comprehensive AI literacy interventions that educate the public about LLM constraints and effective usage techniques, i.e prompting strategies. With this aim, a pilot educational intervention was performed in a high school with 21 students. It involved presenting high-level concepts about intelligence, AI, and LLMs, followed by practical exercises involving ChatGPT in creating natural educational conversations and applying established prompting strategies. Encouraging preliminary results emerged, including high appreciation of the activity, improved interaction quality with the LLM, reduced negative AI sentiments, and a better grasp of limitations, specifically unreliability, limited understanding of commands leading to unsatisfactory responses, and limited presentation flexibility. Our aim is to explore AI acceptance factors and refine this approach for more controlled future studies.

In this short position paper we highlight our ongoing work on symbolic -- logical, transparent, explainable, verifiable, much verifiable heterogeneous multi-agent systems and, in particular, the slower, may be overwhelmed by data,... complex (and often non-functional) issues that impact the choice of structure within each agent. So, our aim is to capture, in the goal specification G, key aspects that need to be considered/achieved relating to this goal.

The world is structured in countless ways. It may be prudent to enforce corresponding structural properties to a learning algorithm's solution, such as incorporating prior beliefs, natural constraints, or causal structures. Doing so may translate to faster, more accurate, and more flexible models, which may directly relate to real-world impact. In this dissertation, we consider two different research areas that concern structuring a learning algorithm's solution: when the structure is known and when it has to be discovered.

Classifiers trained on data sets possessing an imbalanced class distribution are known to exhibit poor generalisation performance. This is known as the imbalanced learning problem. The problem becomes particularly acute when we consider incremental classifiers operating on imbalanced data streams, especially when the learning objective is rare class identification. As accuracy may provide a misleading impression of performance on imbalanced data, existing stream classifiers based on accuracy can suffer poor minority class performance on imbalanced streams, with the result being low minority class recall rates. In this paper we address this deficiency by proposing the use of the Hellinger distance measure, as a very fast decision tree split criterion. We demonstrate that by using Hellinger a statistically significant improvement in recall rates on imbalanced data streams can be achieved, with an acceptable increase in the false positive rate.