35 citations · 52 across the 13 of their papers we have counts for
13 papers
HAT: Hypothesis-Anchored Tracking for Video Monocular Spacecraft Pose Estimation
André Lopo, Atabak Dehban, Rodrigo Ventura
Monocular 6-DoF pose estimation of non-cooperative targets is important for on-orbit servicing and debris removal. A single-image estimator can confuse near-symmetric spacecraft or…
CAD2DMD-SET: Synthetic Generation Tool of Digital Measurement Device CAD Model Datasets for fine-tuning Large Vision-Language Models
João Valente, Atabak Dehban, Rodrigo Ventura
Recent advancements in Large Vision-Language Models (LVLMs) have demonstrated impressive capabilities across various multimodal tasks. They continue, however, to struggle with triv…
FLORA: Efficient Synthetic Data Generation for Object Detection in Low-Data Regimes via finetuning Flux LoRA
Alvaro Patricio, Atabak Dehban, Rodrigo Ventura
Recent advances in diffusion-based generative models have demonstrated significant potential in augmenting scarce datasets for object detection tasks. Nevertheless, most recent mod…
HERB: Human-augmented Efficient Reinforcement learning for Bin-packing
Gojko Perovic, Nuno Ferreira Duarte, Atabak Dehban +3
Packing objects efficiently is a fundamental problem in logistics, warehouse automation, and robotics. When dealing with highly diverse 3D objects (household or grocery items), clo…
AI-Powered Augmented Reality for Satellite Assembly, Integration and Test
Alvaro Patricio, Joao Valente, Atabak Dehban +3
The integration of Artificial Intelligence (AI) and Augmented Reality (AR) is set to transform satellite Assembly, Integration, and Testing (AIT) processes by enhancing precision,…
Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
Manuel Serra Nunes, Atabak Dehban, Yiannis Demiris +1
Despite the significant advances in Deep Reinforcement Learning (RL) observed in the last decade, the amount of training experience necessary to learn effective policies remains on…
3DSGrasp: 3D Shape-Completion for Robotic Grasp
Seyed S. Mohammadi, Nuno F. Duarte, Dimitris Dimou +8
Real-world robotic grasping can be done robustly if a complete 3D Point Cloud Data (PCD) of an object is available. However, in practice, PCDs are often incomplete when objects are…
Robotic Learning the Sequence of Packing Irregular Objects from Human Demonstrations
André Santos, Nuno Ferreira Duarte, Atabak Dehban +1
We tackle the challenge of robotic bin packing with irregular objects, such as groceries. Given the diverse physical attributes of these objects and the complex constraints governi…
SENSORIMOTOR GRAPH: Action-Conditioned Graph Neural Network for Learning Robotic Soft Hand Dynamics
João Damião Almeida, Paul Schydlo, Atabak Dehban +1
Soft robotics is a thriving branch of robotics which takes inspiration from nature and uses affordable flexible materials to design adaptable non-rigid robots. However, their flexi…
Action-conditioned Benchmarking of Robotic Video Prediction Models: a Comparative Study
Manuel Serra Nunes, Atabak Dehban, Plinio Moreno +1
A defining characteristic of intelligent systems is the ability to make action decisions based on the anticipated outcomes. Video prediction systems have been demonstrated as a sol…
Applying Domain Randomization to Synthetic Data for Object Category Detection
João Borrego, Atabak Dehban, Rui Figueiredo +3
Recent advances in deep learning-based object detection techniques have revolutionized their applicability in several fields. However, since these methods rely on unwieldy and larg…
Automatic generation of object shapes with desired functionalities
Mihai Andries, Atabak Dehban, José Santos-Victor
3D objects (artefacts) are made to fulfill functions. Designing an object often starts with defining a list of functionalities that it should provide, also known as functional requ…
Learning at the Ends: From Hand to Tool Affordances in Humanoid Robots
Giovanni Saponaro, Pedro Vicente, Atabak Dehban +3
One of the open challenges in designing robots that operate successfully in the unpredictable human environment is how to make them able to predict what actions they can perform on…