PORTO @ Archivio Istituzionale della Ricerca

A Neuro-Symbolic Framework for LLM-Driven Task Planning and Execution in Industrial Assembly

Enhancing Trust in Collaborative Assembly Through Resilient Adversarial Reinforcement Learning

Featured Application: This work employs Adversarial Reinforcement Learning in the context of industrial collaborative assembly, thereby facilitating the robust adaptation of robots to human errors and unpredictable behaviors, ensuring the reliable completion of assembly tasks. Collaborative robots, or cobots, are designed to improve productivity and safety in industrial settings. However, effective Human–Robot Collaboration (HRC) relies heavily on the human operator’s trust in the robotic par...

Influence of Directed Energy Deposition Build Orientation on the Final Mechanical Properties of Large Ti-6Al-4V Components

Directed Energy Deposition (DED) is an additive manufacturing technology rapidly consolidating for the fabrication and repair of complex aerospace Ti-6Al-4V components, ensuring high deposition rates and large build volumes. However, in high build-rate regimes, process-induced phenomena, such as oxygen pick-up, overheating, and residual porosity, introduce material anisotropy. While residual porosity can largely be mitigated by Hot Isostatic Pressing (HIP), dissolved oxygen cannot be removed ...

Le Alpi come campo di sperimentazione

For the Turin School of Architecture, the Alps have long constituted a privileged field in which teaching, research, and design could intersect with territorial governance, heritage conservation, and social change. Starting from the postwar debates of the Bardonecchia conferences, the chapter traces the gradual shift from the heroic modernist vision of mountain development to more interdisciplinary approaches to the study of alpine territories. It reconstructs the School’s studies on rural ar...