Role
João Filipe Ferreira is a Senior Lecturer in Computer Science and a researcher at the Computational Intelligence and Applications Research Group (CIA).
He is Course Leader for the M.Sc. in Cybernetics and Communications. He is the Strand Leader for the undergraduate modules Foundations of Computers & Technologies (COMP10082, Technologies strand), and Module Leader for the undergraduate module Computer Technologies & Maths (ITEC10261, also Technologies Strand Leader) and the M.Sc. module Robotics & Cybernetics (ITEC40071).
His main research interests concern the broad scientific themes of Artificial Perception and Cognition in Robotics and IoT.
Career overview
João Filipe Ferreira joined NTU in 2018 where he is currently a Senior Lecturer in Computer Science. He was an Invited Assistant Professor from 2011 to 2017, and an Invited Teaching Assistant in Electrical Engineering and Computers at the University of Coimbra from February to September 2011. He was a Probationary Teaching Assistant (Assistente Estagiário) in the same area and at the same university from 2002 to 2004. He received his Ph.D. in Electrical Engineering from the University of Coimbra, specialisation in Instrumentation and Control, in July 2011. He received the M.Sc. degree in Electrical Engineering from the Faculty of Sciences and Technology, University of Coimbra (FCTUC), specialisation in Automation and Robotics, in January 2005. He received his Electrical Engineering B.Sc. degree (5-year course, specialisation in computers) from the same faculty, in July 2000.
He is currently a researcher at the Computational Intelligence and Applications Research Group (CIA), and has been a staff researcher at the ISR since 1999 (integrated member since 2011, research group manager in 2016), and a member of the IEEE and the IEEE Robotics and Automation Society (RAS) since 2012 (Officer in the Portuguese Chapter from 2014 until 2018, member of the Technical Committee on Cognitive Robotics, T-CORO, since 2015, and member of the Technical Committee on Agricultural Robotics, TC AgRA, since 2019), the IEEE Life Sciences Community since 2013, the IEEE Systems, Man, and Cybernetics Society since 2015 and the IEEE Computational Intelligence Society since 2015. He is also a member of the British Computer Society since 2019.
He is also heavily engaged in technology transfer, namely in the fields of digital electronic systems design, instrumentation and control, in close collaboration with the Laboratory of Automatics and Systems of the Instituto Pedro Nunes (IPN-LAS), Coimbra, Portugal. He was a senior consultant for Wexcedo, an SME whose mission includes the development of innovative solutions for smart houses and the “internet of things”.
Research areas
João Filipe Ferreira is a member of the Computational Intelligence and Applications Research Group (CIA) at NTU, and also an integrated member of the Institute of Systems and Robotics (ISR), a research institute of the University of Coimbra. The CIA is well equipped with state-of-the-art computational and electronics design and test equipment. Of note is a 500 core HPC cluster; and a range of high-specification robots, including an iCUB, Sawyer, and Robotniq. Robotics research is facilitated with a 75m2 robot arena with VICON tracking system.
His main research interests concern the broad scientific themes of Artificial Perception and Cognition. Within these themes, the following topics receive his main focus: probabilistic modelling of perception, perception and sensing for AI and field robotics in precision forestry and agriculture, and bioinspired perception and cognition for social robotics, co-robotics and human-robot interaction. However, his research interests are not limited to these subjects: over the years, he has also produced contributions in medical image processing and 3D scanning.
He is the main author of the 2014 textbook “Probabilistic Approaches for Robotic Perception” (Springer STAR series). He is a member of the IEEE Robotics and Automation Society since 2012 (RAS – Executive Committee member of the Portuguese Chapter from 2014 to 2018), and a member of the IEEE RAS Technical Committee on Cognitive Robotics since 2015, and member of the Technical Committee on Agricultural Robotics, TC AgRA, since 2019. He is also a member of the British Computer Society since 2019. He has been involved in several FP6, FP7 and H2020 European projects developed in consortium over the past few years and principal investigator (PI) of several nationally-funded projects.
João Filipe Ferreira has been leader of several undergraduate and graduate modules (including a doctorate studies module), having lectured to and mentored over 2,000 undergraduate and 30 graduate students since his first lecture. Following an integrated approach to teaching and research, he has also supervised/co-supervised a total of 5 undergraduate students, 11 M.Sc. students, 5 Ph.D. students and a post-doctoral fellow, either as a dissertation advisor, as a temporary supervisor during a visiting spell, or as a principal investigator. He was also a member of over 20 M.Sc. and 2 Ph.D. examining committees.
Current topics of research interest include:
Robotics and AI for a Sustainable Environment (RAISE): Despite many advances in key areas, the development of fully autonomous robotic and IoT solutions for precision/smart farming and forestry is still in a very early stage. This stems from the huge challenges imposed by many factors, in particular perception. Artificial perception for robots operating in outdoor natural environments has been studied for several decades. Nevertheless, despite many years of research a substantial amount of problems have yet to be robustly solved. Perception in agricultural and forestry robotics faces many challenges imposed at sensor-level by environmental conditions (trees and relief, weather conditions, dust, smoke, etc.), the homogeneity of natural landscapes, the diversity of natural obstacles to be avoided, and the effect of vibrations or external forces such as wind, among other technical challenges. There are also many other challenges that go beyond sensing, including safe operation (for both the robot and other living beings), multi-scale sensing and perception that allows the robot to tackle broad-range tasks such as navigation but also localised precision tasks, and covering specialised, expert-informed tasks necessary to achieve the greatest level of autonomy and usefulness possible. Potential projects in this topic include deep learning solutions for IoT in agriculture and forestry, semantic segmentation of woodland and farm scenes, development of robust, reusable and flexible perceptual architectures, and cooperative perception solutions for swarm robotics in the field.
Artificial Attention for Human-Robot Interaction: Despite remarkable advances in recent years, cognitive robotics is still lacking an understanding of the essential skills needed for the implementation robots capable of long-lasting interaction with humans in real-world applications. One of the most fundamental skills known to underpin the human ability of engaging in long-term interaction with other agents is perceptual attention, which allows for conveying and inferring intention through redirection of the senses (instilling a sense of non-verbal interaction) and the building of an internal model of the interlocutor's attentional stance, respectively. Potential projects include robust gaze direction estimation, attentional modelling, shared attention modelling, attentional processes in memory management and object of interest estimation in interaction.
Attention and Active Perception Supporting Robot Imitation Learning from Multi-Modal Human Demonstrations: Imitation learning in robots is when a robot is presented with a demonstration of a skill that it should learn to perform on its own. One-shot and few-shot learning is the act of learning to generalise from one or a few number of training examples per class, respectively. Currently, one- and few-shot learning are very challenging problems -- a probable reason for this is that scene task-relevance dictated by both the robot's knowledge of the world and the demonstrator's attentional stance is not explicitly being taken into account in what is clearly a shared attention scenario. Potential projects in this topic involve fundamental research on this issue, namely on how attention can be used to improve the performance of deep learning-based algorithms for robot imitation learning.
Opportunities to carry out postgraduate research exist and further information may be obtained from the NTU Graduate School.
If you are considering to study for PhD or MSc in any of the topics above or other related topics please do not hesitate to get in touch.
External activity
Professional Memberships:
- Member of the IEEE (2012-present)
- Member of the IEEE Robotics and Automation Society (RAS, 2012-present):
- Executive Committee member of the Portuguese Chapter from 2014 to 2018
- Member of the Technical Committee on Cognitive Robotics, T-CORO (2015-present)
- Member of the Technical Committee on Agricultural Robotics, TC AgRA (2019-present)
- Member of the IEEE RAS Technical Committee on Cognitive Robotics (2015-present)
- Member of the IEEE Life Sciences Community (2013-present)
- Member of the IEEE Systems, Man, and Cybernetics Society (2015-present)
- Member of the IEEE Computational Intelligence Society (2015-present)
- Member of the British Computer Society (BCS, 2019-present)
Sponsors and collaborators
To date, João Filipe Ferreira has been awarded nearly 350K£ in research grants overall.
Ongoing grants:
- SEMFIRE (Safety, Exploration and Maintenance of Forests with the Integration of Ecological Robotics – CENTRO-01-0247-FEDER-032691), 2018-present - funded by FEDER/PORTUGAL 2020 (Portugal)
- CORE (Centre of Operations for Rethinking Engineering – CENTRO-01-0247-FEDER-037082), 2018-present - funded by FEDER/PORTUGAL 2020 (Portugal)
Past grants:
- CASIR (Coordinated Control of Stimulus-Driven and Goal-Directed Multisensory Attention Within the Context of Social Interaction with Robots – PTDC/EEI-AUT/3010/2012), 2013-2015 - funded by FCT/COMPETE (Portugal)
External links to collaborating partners:
- University of Coimbra, Portugal
- Institute of Systems and Robotics, Portugal
- Instituto Pedro Nunes, Portugal
Publications
Journal Papers:
MACHADO, P., FERREIRA, J.F., OIKONOMOU, A. and MCGINNITY, T.M., 2023. NeuroHSMD: neuromorphic hybrid spiking motion detector. ACM Transactions on Reconfigurable Technology and Systems. ISSN 1936-7406.
MACHADO, P., OIKONOMOU, A., FERREIRA, J.F. and MCGINNITY, T.M., 2021. HSMD: an object motion detection algorithm using a Hybrid Spiking Neural Network Architecture. IEEE Access. ISSN 2169-3536
LANILLOS, P., FERREIRA, J.F. and DIAS, J., 2017. A Bayesian hierarchy for robust gaze estimation in human–robot interaction. International Journal of Approximate Reasoning, 87, pp. 1-22. ISSN 0888-613X
MARTINS, R., FERREIRA, J.F., CASTELO-BRANCO, M. and DIAS, J., 2017. Integration of touch attention mechanisms to improve the robotic haptic exploration of surfaces. Neurocomputing, 222, pp. 204-216. ISSN 0925-2312
FERREIRA, J.F. and DIAS, J., 2014. Attentional mechanisms for socially interactive robots – a survey. IEEE Transactions on Autonomous Mental Development, 6 (2), pp. 110-125. ISSN 1943-0604
Authored Books:
FERREIRA, J.F. and DIAS, J.M., 2014. Probabilistic approaches for robotic perception. Springer tracts in advanced robotics, 91 . Cham, Switzerland: Springer International. ISBN 9783319020051
Conference Papers:
BITTNER, D., FERREIRA, J.F., ANDRADA, M.E., BIRD, J.J. and PORTUGAL, D., 2022. Generating synthetic multispectral images for semantic segmentation in forestry applications. In: Innovation in Forestry Robotics: Research and Industry Adoption Workshop - IEEE Conference on Robotics and Automation (ICRA 2022), Philadelphia (PA), USA, 23-27 May 2022.
ANDRADA, M.E., FERREIRA, J.F., KANTOR, G., PORTUGAL, D. and ANTUNES, C.H., 2022. Model pruning in depth completion CNNs for forestry robotics with simulated annealing. In: Innovation in Forestry Robotics: Research and Industry Adoption Workshop - IEEE Conference on Robotics and Automation (ICRA 2022), Philadelphia (PA), USA, 23-27 May 2022.
NUNES, R., FERREIRA, J. and PEIXOTO, P., 2022. Procedural generation of synthetic forest environments to train machine learning algorithms. In: Innovation in Forestry Robotics: Research and Industry Adoption Workshop - IEEE Conference on Robotics and Automation (ICRA 2022), Philadelphia (PA), USA, 23-27 May 2022.
ANDRADA, M.E., FERREIRA, J.F., PORTUGAL, D. and COUCEIRO, M.S., 2022. Integration of an artificial perception system for identification of live flammable material in forestry robotics. In: Proceedings of the 2022 IEEE/SICE International Symposium on System Integration (SII). Institute of Electrical and Electronics Engineers (IEEE), pp. 103-108. ISBN 9781665445399
MACHADO, P., BONNELL, J., BRANDENBURGH, S., FERREIRA, J.F., PORTUGAL, D. and COUCEIRO, M., 2021. Robotics use case scenarios. In: M. JAHRE, D. GÖHRINGER and P. MILLET, eds., Towards ubiquitous low-power image processing platforms. Cham, Switzerland: Springer, pp. 151-172. ISBN 9783030535315 (Forthcoming)
PORTUGAL, D., FERREIRA, J.F. and COUCEIRO, M.S., 2020. Requirements specification and integration architecture for perception in a cooperative team of forestry robots. In: M. RUSSO, X. DONG and A. MOHAMMAD, eds., Towards Autonomous Robotic Systems: 21st Annual Conference, TAROS 2020, Nottingham, UK, September 16, 2020, Proceedings. Lecture notes in computer science (12228). Cham: Springer, pp. 329-344. ISBN 9783030634858
LOURENÇO, D., DE CASTRO CARDOSO FERREIRA, J. and PORTUGAL, D., 2020. 3D local planning for a forestry UGV based on terrain gradient and mechanical effort. In: IROS 2020 Workshop on Perception, Planning and Mobility in Forestry Robotics (WPPMFR 2020), Las Vegas, NV, USA (virtual workshop), 29 October 2020.
DE CASTRO CARDOSO FERREIRA, J., 2020. Forestry robotics — the right bet at the right time? In: IROS 2020 Workshop on Perception, Planning and Mobility in Forestry Robotics (WPPMFR 2020), Las Vegas, NV, USA (virtual workshop), 29 October 2020.
ANDRADA, M.E., DE CASTRO CARDOSO FERREIRA, J., PORTUGAL, D. and COUCEIRO, M., 2020. Testing different CNN architectures for semantic segmentation for landscaping with forestry robotics. In: IROS 2020 Workshop on Perception, Planning and Mobility in Forestry Robotics (WPPMFR 2020), Las Vegas, NV, USA (virtual workshop), 29 October 2020.
BRANDENBURG, S., MACHADO, P., SHINDE, P., FERREIRA, J.F. and MCGINNITY, T.M., 2019. Object classification for robotic platforms. In: ROBOT 2019: Fourth Iberian Robotics Conference, Porto, Portugal, 20-22 November 2019.
MARTINS, G.S., FERREIRA, J.F., PORTUGAL, D. and COUCEIRO, M.S., 2019. MoDSeM: towards semantic mapping with distributed robots. In: K. ALTHOEFER, J. KONSTANTINOVA and K. ZHANG, eds., Towards autonomous robotic systems. Proceedings of the 20th Annual Conference, TAROS 2019, London, 3-5 July 2019. Part II. Lecture notes in computer science (11650). Cham: Springer, pp. 131-142. ISBN 9783030253318
MARTINS, S., FERREIRA, J.F., PORTUGAL, D. and COUCEIRO, M.S., 2019. MoDSeM: modular framework for distributed semantic mapping. 'Embedded intelligence: enabling & supporting RAS technologies'. In: 2nd UK-RAS Robotics and Autonomous Systems Conference, Loughborough, 2019.
LANILLOS, P., FERREIRA, J.F. and DIAS, J., 2015. Designing an artificial attention system for social robots. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015), Hamburg, Germany, 28 September - 2 October 2015. Piscataway, NJ: Institute of Electrical and Electronics Engineers, pp. 4171-4178. ISBN 9781479999958
FERREIRA, J.F., LANILLOS, P. and DIAS, J., 2015. Fast exact Bayesian inference for high-dimensional models. In: 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015): Workshop on Unconventional Computing for Bayesian Inference, Hamburg, Germany, 28 September 2015.
LANILLOS, P., FERREIRA, J.F. and DIAS, J., 2015. Multisensory 3D saliency for artificial attention systems. In: 3rd Workshop on Recognition and Action for Scene Understanding (REACTS), Valletta, Malta, 5 September 2015.
Research datasets and databases
NUNES, R., FERREIRA, J. and PEIXOTO, P., 2022. SynPhoRest - synthetic photorealistic forest dataset with depth information for machine learning model training. [Dataset]
BITTNER, D., ANDRADA, M.E., PORTUGAL, D. and FERREIRA, J.F., 2021. SEMFIRE forest dataset for semantic segmentation and data augmentation. [Dataset]
Press expertise
Has contributed popular science pieces in robotics and AI in publications such as "The Conversation". See, for example:
- Five of the world’s tiniest robots, João Filipe Ferreira, June 15, 2022
Robotics and AI for a Sustainable Environment -- RAISE @ NTU
João Filipe Ferreira, through his projects at NTU in partnership with other institutions, has started the Robotics and AI for a Sustainable Environment (RAISE) Initiative.
Its aim is to facilitate producing research in the use of robotics and AI to this effect both in the UK and abroad. The introduction of these technologies is hoped to contribute to the achievement of several of the United Nations’ sustainable development goals. For example, it could help to promote sustainable economic growth by increasing productivity and reducing running costs, thereby making agriculture and forestry a more viable industry for small private landowners (SDG 8: Decent Work and Economic Growth). It could also contribute to the goal of reducing inequalities by providing skilled job opportunities for people in rural areas (SDG 10: Reduced Inequalities) and potentially reducing the harsh working conditions and health hazards associated with agricultural and forestry work (SDG 3: Good Health and Well-Being). Additionally, the use of advanced sensors, machinery and robotics in agriculture and forestry is expected help to promote responsible consumption and production by reducing waste, optimising the use of natural resources and protecting the environment (SDG 12: Responsible Consumption and Production; SDG 15: Life on Land).



