{"ID":2868854,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.16006","arxiv_id":"2509.16006","title":"Defining and Monitoring Complex Robot Activities via LLMs and Symbolic Reasoning","abstract":"Recent years have witnessed a growing interest in automating labor-intensive and complex activities, i.e., those consisting of multiple atomic tasks, by deploying robots in dynamic and unpredictable environments such as industrial and agricultural settings. A key characteristic of these contexts is that activities are not predefined: while they involve a limited set of possible tasks, their combinations may vary depending on the situation. Moreover, despite recent advances in robotics, the ability for humans to monitor the progress of high-level activities - in terms of past, present, and future actions - remains fundamental to ensure the correct execution of safety-critical processes. In this paper, we introduce a general architecture that integrates Large Language Models (LLMs) with automated planning, enabling humans to specify high-level activities (also referred to as processes) using natural language, and to monitor their execution by querying a robot. We also present an implementation of this architecture using state-of-the-art components and quantitatively evaluate the approach in a real-world precision agriculture scenario.","short_abstract":"Recent years have witnessed a growing interest in automating labor-intensive and complex activities, i.e., those consisting of multiple atomic tasks, by deploying robots in dynamic and unpredictable environments such as industrial and agricultural settings. A key characteristic of these contexts is that activities are...","url_abs":"https://arxiv.org/abs/2509.16006","url_pdf":"https://arxiv.org/pdf/2509.16006v1","authors":"[\"Francesco Argenziano\",\"Elena Umili\",\"Francesco Leotta\",\"Daniele Nardi\"]","published":"2025-09-19T14:19:44Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.HC\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}