Marco Brambilla

Among the many scenarios where humans and AI agents can collaborate, Energy Efficiency (EE) is one where such collaboration could most effectively contribute to the goal of net zero emissions, while also reducing costs and improving comfort. In this context, new AI solutions can support customers in making their energy consumption more efficient and aligned with renewable sources. In this work, we investigate the strengths and challenges of Human-AI Collaboration by proposing an AI-based Conversational Agent whose inspiration principles are derived from the theories of Human-Centered Artificial Intelligence (HCAI). It is specifically designed to augment users' capabilities in achieving EE by providing them with recommendations and practical tips. The Agent uses a Knowledge Graph (KG) trained on domain-specific energy-related documents, coupled with a RAG (Retrieval Augmented Generation) architecture to ensure factual accuracy, source accountability, fairness, and transparency. By tailoring responses to users' profiles and preferences, the system prioritizes human needs and values while addressing perceptions of technological usability and acceptability. The Agent is validated in a real-world application scenario with international customers, with the aim to test content accuracy and adaptation to the user context and uncertainties. The results show the effectiveness of the system in fostering Human-AI Collaboration for EE.

Despite the impressive performance of Artificial Intelligence (AI) systems, their robustness remains elusive and constitutes a key issue that impedes large-scale adoption. Besides, robustness is interpreted differently across domains and contexts of AI . In this work, we systematically survey recent progress to provide a reconciled terminology of concepts around AI robustness. We introduce three taxonomies to organize and describe the literature both from a fundamental and applied point of view: (1) methods and approaches that address robustness in different phases of the machine learning pipeline; (2) methods improving robustness in specific model architectures, tasks, and systems; and in addition, (3) methodologies and insights around evaluating the robustness of AI systems, particularly the tradeoffs with other trustworthiness properties. Finally, we identify and discuss research gaps and opportunities and give an outlook on the field. We highlight the central role of humans in evaluating and enhancing AI robustness, considering the necessary knowledge they can provide, and discuss the need for better understanding practices and developing supportive tools in the future.

Digitally-supported participatory methods are often used in policy-making to develop inclusive policies by collecting and integrating citizen's opinions. However, these methods fail to capture the complexity and nuances in citizen's needs, i.e., citizens are generally unaware of other's needs, perspectives, and experiences. Consequently, policies developed with this underlying gap tend to overlook the alignment of multistakeholder perspectives, and design policies based on the optimization of high-level demographic features. In our contribution, we propose a method to enable citizens understand other's perspectives and calibrate their positions. First, we collected requirements and design principles to develop our approach by involving stakeholders and experts in policymaking in a series of workshops. Then, we conducted a crowdsourcing study with 420 participants to compare the effect of different text and images, on people's initial and final motivations and their willingness to change opinions. We observed that both influence participant's opinion change, however, the effect is more pronounced for textual modality. Finally, we discuss overarching implications of designing with empathy to mediate alignment of citizen's perspectives.

Spatio-temporal trajectories are crucial for data mining tasks, requiring versatile learning methods that can accurately extract movement patterns and travel purposes. While large language models (LLMs) have shown remarkable versatility through training on extensive datasets, and trajectories share similarities with natural language, standard LLMs cannot directly handle spatio-temporal features or extract trajectory-specific information. We propose TrajCogn, a model that effectively adapts LLMs for trajectory learning. TrajCogn incorporates a novel trajectory semantic embedder to process spatio-temporal features and extract movement patterns and travel purposes, along with a trajectory prompt that integrates this information into LLMs for various downstream tasks. Experiments on three real-world datasets and four representative tasks demonstrate TrajCogn's effectiveness.

In this article, we propose a hybrid, gamified, story-driven data collection approach to spark self-empathy, resurfacing people’s perceptions and feelings about past experiences. The game is designed around the well-known paradigm of an escape room and includes a physical board, some card decks, and a mobile application. We designed our concept around a very impactful experience that most people have experienced in recent years, namely the COVID-19 pandemic. The game aims to collect and understand people’s behaviour and feelings and to study and tackle the long-term effects of the pandemic. As the player plays through the game, they customize and escape from their lockdown room by completing statements and answering a series of questions that define their story. The decoration of the lockdown room and the storytelling-driven approach are targeted at sparking people’s emotions and self-empathy towards their past selves. Ultimately, the proposed approach was proven effective in collecting data about perceptions, opinions, and feelings related to the event.