GRASPLAT: Enabling dexterous grasping through novel view synthesis
IEEE International Conference on Intelligent Robots and Systems (IROS 2025)
Nuno Ferreira Duarte
nferreiraduarte@isr.tecnico.ulisboa.pt
Nuno Ferreira Duarte is a Researcher at ISR-Lisboa in Instituto Superior Técnico.
He received his Ph.D (Summa cum laude) in 2023. His PhD was a Joint-Degree between Instituto Superior Técnico (IST-Lisbon) and École Polytechnique Fédérale de Lausanne (EPFL) advised by Professor José Santos-Victor
and Professor Aude Billard.
He received a M.Sc (Cum laude) from the University of Lisbon, Instituto Superior Tecnico (IST-Lisbon), Institute of Systems and Robotics (ISR), advised by Professor Pedro U. Lima. He also interned at California Institute of Technology (Caltech SURF Program) under the supervision of Professor Richard Murray.
His work bridges Robotics and Computer Vision with a focus on action understanding and object manipulation. He studies human physiological behavior and its connections to neurological and psychological processes to develop robot models that comprehend human actions. A key focus is using non-verbal cues as a shared communication language between humans and robots, enabling robots to both understand human actions and be understood by humans. He is also interested in studying robotic grasping from a vision-based background. The challenges that most intice him are distinguishing between careful and non-careful motions (important for fragile or dangerous objects), learning how to handle artifacts or fragments (crucial for archeology), and inferring objects’ shape from partial visual observations (necessary in household environments).
He received a M.Sc (Cum laude) from the University of Lisbon, Instituto Superior Tecnico (IST-Lisbon), Institute of Systems and Robotics (ISR), advised by Professor Pedro U. Lima. He also interned at California Institute of Technology (Caltech SURF Program) under the supervision of Professor Richard Murray.
His work bridges Robotics and Computer Vision with a focus on action understanding and object manipulation. He studies human physiological behavior and its connections to neurological and psychological processes to develop robot models that comprehend human actions. A key focus is using non-verbal cues as a shared communication language between humans and robots, enabling robots to both understand human actions and be understood by humans. He is also interested in studying robotic grasping from a vision-based background. The challenges that most intice him are distinguishing between careful and non-careful motions (important for fragile or dangerous objects), learning how to handle artifacts or fragments (crucial for archeology), and inferring objects’ shape from partial visual observations (necessary in household environments).
Top Publications
Learning the Sequence of Packing Irregular Objects from Human Demonstrations: Towards Autonomous Packing Robots
IEEE International Conference on Biomedical Robotics and Biomechatronics (BIOROB 2024)
3DSGrasp: 3D Shape-completion for robotic grasp
IEEE International Conference on Robotics and Automation (ICRA 2023)
The Role of Object Physical Properties in Human Handover Actions: Applications in Robotics
IEEE Transactions on Cognitive and Developmental Systems 2022
The Gaze Dialogue Model: Nonverbal Communication in HHI and HRI
IEEE Transactions on Cybernetics 2022
Action Anticipation: Reading the Intentions of Humans and Robots
IEEE Robotics and Automation Letters (RAL-Letters 2018)
Action Alignment from Gaze Cues
European Conference on Computer Vision (ECCV 2018)
