ISEP – LSA – Comunicações em eventos científicos
URI permanente para esta coleção:
Navegar
Percorrer ISEP – LSA – Comunicações em eventos científicos por Objetivos de Desenvolvimento Sustentável (ODS) "12:Produção e Consumo Sustentáveis"
A mostrar 1 - 2 de 2
Resultados por página
Opções de ordenação
- Algae and Fish Farming: An EPS@ISEP 2022 ProjectPublication . Blomme, Rose-Farah; Domissy, Zoé; Dylik, Zuzanna; Hidding, Thomas; Röhe, Alina; Duarte, Abel J.; BENEDITA CAMPOS NEVES MALHEIRO, MARIA; JUSTO, Jorge; Ferreira, Paulo; Guedes, Pedro; Castro Ribeiro, Maria Cristina de; Silva, Manuel; Auer, Michael E.; Rüütmann, TiiaThe European Project Semester (EPS) at Instituto Superior de Engenharia do Porto (ISEP) is a capstone engineering design program where students, organised in multidisciplinary and multicultural teams, create a solution for a proposed problem, bearing in mind ethical, sustainability and market concerns. The project proposals are usually aligned with the United Nations Sustainable Development Goals (SDG). New sustainable food production methods are essential to cope with the continuous population growth and aligned with SDG2 and SDG12. In this context, this paper describes the research and work done by a team of Erasmus students enrolled in EPS@ISEP during the spring of 2022. Since sustainable algae farming can be a suitable source of food, the team's goal was the design and develop a proof-of-concept prototype, named GREEN·flow, of a symbiotic aquaponic system to farm algae and fish. The smart GREEN·flow concept comprises a modular structure and an app for control and supervision. The proposed design was driven by state-of-the-art research, targeted to a specific market niche based on a market analysis, and considering sustainability and ethics concerns, all of which are described in this manuscript. A proof-of-concept prototype was built and tested to verify that it worked as intended.
- VIRIATO: Visual-Action Reinforcement Integrator for Actor-Critic with Temporal ObservationsPublication . Campanhã, João; Neves, Francisco; Pinto, Andry; BENEDITA CAMPOS NEVES MALHEIRO, MARIA; Fonseca, Pedro; Moreira, António; Neto, Pedro; Morais, Pedro; Lima, JoséThe Visual-Action Reinforcement Integrator for Actor-Critic with Temporal Observations (VIRIATO) is a compact multi-input feature-extractor architecture designed to enable robust visual navigation of Unmanned Aerial Vehicles (UAVs) conducting close-range inspection of photovoltaic arrays. The target task of low-altitude flight over dynamic, visually variable surfaces without privileged information is inherently partially observable. VIRIATO augments stacked image observations with a short history of recent past actions, producing a richer latent state for the Soft Actor-Critic (SAC) agent. Training is performed with domain randomization to expose the policy to diverse lighting, backgrounds and panel layouts. In simulation, VIRIATO yields faster learning and improved sample efficiency compared to a standard image-only Convolutional Neural Network (CNN) feature extractor, achieving lower position and yaw errors and substantially better robustness under image perturbations while retaining high task completion rates. The architecture is intentionally simple and general: it improves temporal awareness without adding complex recurrence, and it could be adapted to other perception-driven robotic tasks. These results demonstrate that integrating historical action data with visual encoding, together with domain randomization, is an effective way to achieve reliable autonomous vision-based navigation.