Research line

Perception and Manipulation Image

The research of PERCEPTION AND MANIPULATION group focuses on enhancing the perception, learning, and planning capabilities of robots to achieve higher degrees of autonomy and user-friendliness during everyday manipulation tasks. Some topics addressed are the geometric interpretation of perceptual information, construction of 3D object models, action selection and planning, reinforcement learning, and teaching by demonstration.

Head of line: Carme Torras Genís

Head of line

Tech. transfer

Our activity finds applications in several fields through collaboration with our technological partners

Research projects

We carry out projects from national and international research programmes.
→ More about our research projects

<< Back to Perception and Manipulation main page

Learning by demonstration

We devise methods to learn object-action relations to accomplish tasks at different levels of abstraction, where object models are generated from visual and depth information, and actions, involving manipulation skills, are learned from demonstrations provided by a human using multimodal algorithms that combine vision and haptics.

→ more info

Research area 1 of Perception and Manipulation

Planning for perception and manipulation

We are interested in view planning for object modeling, as well as manipulation planning, with special interest in deformable objects. High-level task formulations are integrated with low-level geometry-based methods and simplified physical models, together with an on-line sensory-based treatment of uncertainty, so as to come up with specific sequences of motion commands.

→ more info

Research area 2 of Perception and Manipulation

Perception of rigid and non-rigid objects

Our objective is to investigate computer vision algorithms for interpreting and understanding scenes from images, with applications in robotics and medical imaging. In particular, our activities are concentrated on retrieving rigid and non-rigid shape, motion and camera pose from single images and video sequences.

→ more info

Research area 3 of Perception and Manipulation

These are the latest research projects of the Perception and Manipulation research line:

  • ---: ---

    Technology Transfer Contract

    Start Date: 24/10/2003

These are the most recent publications (2024 - 2023) of the Perception and Manipulation

  • C. Torras. Ethics of social robotics: Individual and societal concerns and opportunities. Annual Review of Control, Robotics, and Autonomous Systems, 7(1), 2024, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Civit, A. Andriella, C. Barrue, M. Antonio, C. Boqué and G. Alenyà. Introducing social robots to assess frailty in older adults, 2024 ACM/IEEE International Conference on Human-Robot Interaction, 2024, Boulder, CO, USA, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Luque, D. Parent, A. Colomé, C. Ocampo-Martínez and C. Torras. Model predictive control for dynamic cloth manipulation: Parameter learning and experimental validation. IEEE Transactions on Control Systems Technology: 1-17, 2024, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • D. Blanco-Mulero, O. Barbany, G. Alcan, A. Colomé, C. Torras and V. Kyrki. Benchmarking the sim-to-real gap in cloth manipulation. IEEE Robotics and Automation Letters, 9(3): 2981-2988, 2024.

    Open/Close abstract Abstract Info Info pdf PDF
  • P. Jiménez. Inside-out states of garments. Technical Report IRI-TR-24-01, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2024.

    Open/Close abstract Abstract Info Info pdf PDF
  • C. Torras. Robótica asistencial. Retos éticos en la ayuda y acompañamiento a cuidadores y pacientes. In Soledad no deseada en la era digital, 38-46. Fundació Víctor Grífols i Lucas, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • G. Tzelepis, J. Borràs, A. Eren Erdal and G. Alenyà. Semantic state prediction in robotic cloth manipulation, 2023 Intelligent Systems Conference, 2023, Amsterdam, pp. 205-219, Springer Lecture Notes in Networks and Systems.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Andriella, C. Torras, C. Abdelnour and G. Alenyà. Introducing CARESSER: A framework for in situ learning robot social assistance from expert knowledge and demonstrations. User Modeling and User-Adapted Interaction, 33: 441-496, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • S. Forgas, R. Huertas, A. Andriella and G. Alenyà. Gendered human–robot interactions in services. International Journal of Social Robotics, 15(11): 1791-1807, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • E. Thomaz and M. Dimiccoli. Acquisition and analysis of camera sensor data (Lifelogging). In Mobile Sensing in Psychology. Methods and Applications, 277-296. Guilford Publications, 2023.

    Open/Close abstract Abstract Info Info
  • G. Canal, C. Torras and G. Alenyà. Generating predicate suggestions based on the space of plans: an example of planning with preferences. User Modeling and User-Adapted Interaction, 33: 333-357, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • C. Torras and L.G. Ludescher. Writing science fiction as an inspiration for AI research and ethics dissemination. In Human-Centered Artificial Intelligence: Advanced Lectures, 322-344. Cham: Springer International Publishing, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • C. Torras. Robótica assistencial: una aposta per l'envelliment saludable i sostenible. In Bioética: una mirada cap al futur, 216-225. Fundació Víctor Grífols i Lucas, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • S. Forgas, R. Huertas, A. Andriella and G. Alenyà. Does the personality of consumers influence the assessment of the experience of interaction with social robots?. International Journal of Social Robotics, 2023, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Olivares-Alarcos, S. Foix and G. Alenyà. Time to contact for robot safety stop in close collaborative tasks. In Human-robot collaboration: unlocking the potential for industrial applications, 87-104. Institution of Engineering Technology, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • C. Torras. Desplegament ètic de la robòtica assistencial per a un envelliment saludable i sostenible. In La medicina al segle xxi, avenços i límits, 35-44. Universitat d'Estiu i Tardor d'Andorra, Govern d'Andorra, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • M. Arduengo, A. Colomé, J. Lobo, L. Sentis and C. Torras. Gaussian-process-based learning from demonstration. Journal of Ambient Intelligence and Humanized Computing, 2023, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • R. Pérez, A. Espersen and A. Agudo. Robust wind turbine blade segmentation from RGB images in the wild, 2023 IEEE International Conference on Image Processing, 2023, Kuala Lumpur, Malaysia, pp. 1025-1029.

    Open/Close abstract Abstract Info Info pdf PDF
  • C. Torras. Eduquem les criatures... també les artificials!. Serra d'Or, 760: 28-29, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • S. Forgas, R. Huertas, A. Andriella and G. Alenyà. Social robot-delivered customer-facing services: an assessment of the experience. The Service Industries Journal, 43(3): 154-184, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. San-Miguel, V. Puig and G. Alenyà. Condition-based design of variable impedance controllers from user demonstrations. Control Engineering Practice, 140: 105658, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • C. Torras. Humans i robots: ¿qui modela qui?. El Món d'Ahir, 26: 134-143, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • F. Amadio, J.A. Delgado-Guerrero, A. Colomé and C. Torras. Controlled Gaussian process dynamical models with application to robotic cloth manipulation. International Journal of Dynamics and Control , 11: 3209-3219, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • S. Izquierdo, G. Alenyà and C. Rizzo. Adaptive Human-Robot Collaboration: evolutionary learning of action costs using an action outcome simulator, 32nd IEEE International Symposium on Robot and Human Interactive Communication, 2023, Busan, Korea, pp. 1901-1907.

    Open/Close abstract Abstract Info Info pdf PDF
  • L.M. Lach, N. Funk, R. Haschke, S. Lemaignan, H. Ritter, J. Peters and G. Chalvatzaki. Placing by touching: An empirical study on the importance of tactile sensing for precise object placing, 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2023, Detroit, MI, USA, pp. 8964-8971.

    Open/Close abstract Abstract Info Info pdf PDF
  • J. Borràs, A. Boix, S. Foix and C. Torras. A virtual reality framework for fast dataset creation applied to cloth manipulation with automatic semantic labelling, 2023 IEEE International Conference on Robotics and Automation, 2023, London (UK), pp. 11605-11611.

    Open/Close abstract Abstract Info Info pdf PDF
  • R. Cupec, I. Vidovic, V. Simundic, P. Pejic, S. Foix and G. Alenyà. Teaching a robot where doors and drawers are and how to handle them, 32nd IEEE International Symposium on Robot and Human Interactive Communication, 2023, Busan, Korea, pp. 2288-2294.

    Open/Close abstract Abstract Info Info pdf PDF
  • L.M. Lach, N. Funk, R. Haschke, H. Ritter, J. Peters and G. Chalvatzaki. Tactile sensing for stable object placing, 2023 Workshop on Touch Processing: a new Sensing Modality for AI at NeurIPS 2023 , 2023, New Orleans (LA), USA, pp. 1-10.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Agudo. Detail-aware uncalibrated photometric stereo, 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, 2023, Rhodes Island, Greece, pp. 1-5, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • M. Pérez and A. Agudo. Sensor-agnostic multimodal fusion for multiple object tracking from camera, radar, lidar and V2X, 2023 FISITA 2023 World Congress, 2023, Barcelona, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • L.M. Lach, R. Haschke, D. Tateo, J. Peters, H. Ritter, J. Borràs and C. Torras. Towards transferring tactile-based continuous force control policies from simulation to robot, 2023 Workshop on Touch Processing: a new Sensing Modality for AI at NeurIPS 2023 , 2023, New Orleans (LA), USA, pp. 10.

    Open/Close abstract Abstract Info Info pdf PDF
  • E. Corona, G. Alenyà, G. Pons-Moll and F. Moreno-Noguer. LayerNet: high-resolution semantic 3D reconstruction of clothed people. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • M. Pérez and A. Agudo. Robust multimodal and multi-object tracking for autonomous driving applications, 2023 International Conference on Advanced Robotics, 2023, Abu Dhabi, UAE, IEEE, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • D.F. Ordoñez, M. Martin, A. Agudo and F. Moreno-Noguer. On discrete symmetries of robotics systems: A group-theoretic and data-driven analysis, 2023 Robotics: Science and Systems Conference, 2023, Daegu, Republic of Korea.

    Open/Close abstract Abstract Info Info pdf PDF
  • E. Caldarelli, A. Colomé, C. Ocampo-Martínez and C. Torras. Quadratic dynamic matrix control for fast cloth manipulation, 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2023, Detroit, MI, USA, pp. 8178-8185.

    Open/Close abstract Abstract Info Info pdf PDF
  • F. Coltraro, J. Fontana, J. Amorós, M. Alberich-Carramiñana, J. Borràs and C. Torras. A representation of cloth states based on a derivative of the Gauss Linking Integral. Applied Mathematics and Computation, 457: 128165, 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • M. Dalmasso, J.E. Domínguez, I.J. Torres, P. Jiménez, A. Garrell Zulueta and A. Sanfeliu. Shared task representation for human–robot collaborative navigation: The collaborative search case. International Journal of Social Robotics: 1-27, 2023, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Olivares-Alarcos, A. Andriella, S. Foix and G. Alenyà. Robot explanatory narratives of collaborative and adaptive experiences, 2023 IEEE International Conference on Robotics and Automation, 2023, London (UK), pp. 11964-11971.

    Open/Close abstract Abstract Info Info pdf PDF
  • E. Caldarelli, A. Chatalic, A. Colomé, L. Rosasco and C. Torras. Heteroscedastic Gaussian processes and random features: scalable motion primitives with guarantees, 2023 Conference on Robot Learning, 2023, Atlanta, GA, USA, pp. 3010-3029, PMLR.

    Open/Close abstract Abstract Info Info pdf PDF
  • F. Coltraro, J. Amorós, M. Alberich-Carramiñana and C. Torras. Reconstruction of sampled surfaces with boundary via Morse theory, 2023 Congreso Español de Informática Gráfica, 2023, Mallorca, pp. 21-24.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Dhamanaskar, M. Dimiccoli, E. Corona, A. Pumarola and F. Moreno-Noguer. Enhancing egocentric 3D pose estimation with third person views . Pattern Recognition, 138(109358), 2023.

    Open/Close abstract Abstract Info Info pdf PDF
  • E.B. Bueno Benito, B. Tura and M. Dimiccoli. Leveraging triplet loss for unsupervised action segmentation, 2023 CVPR Workshop on Learning with Limited Labelled Data, 2023, Vancouver, Canadá, pp. 4922-4930, IEEE.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Suárez, A. Andriella, C. Torras and G. Alenyà. User interactions and negative examples to improve the learning of semantic rules in a cognitive exercise scenario, 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2023, Detroit, MI, USA, pp. 7953-7960.

    Open/Close abstract Abstract Info Info pdf PDF
  • A. Urdapilleta and A. Agudo. Comparative study of feature localization methods for endoscopy image matching, 2023 IEEE International Conference on Image Processing Challenges and Workshops, 2023, Kuala Lumpur, Malaysia, IEEE, to appear.

    Open/Close abstract Abstract Info Info pdf PDF
  • G.D. Delmas, P. Weinzaepfel, F. Moreno-Noguer and G. Rogez. PoseFix: correcting 3D human poses with natural language, 2023 International Conference on Computer Vision, 2023, Paris, France.

    Open/Close abstract Abstract Info Info pdf PDF

Perception and Manipulation Laboratory

The Perception and Manipulation Laboratory is the main facility devoted to experimentation on the topics of the research line. It occupies 142 m² in the second floor of the Faculty, and a large part hosts a life-scale mock-up of a (quite) small apartment (35 m²). Two PAL one-armed mobile TIAGo robots dwell within the apartment, but are occasionally taken out for experimentation elsewhere. There is also a manipulation area equipped with two WAM robot arms and a KINOVA manipulator, and workplaces are distributed along the perimeter. Next to the laboratory, with a direct view through a window, there is the Scientific and Technical Lab support office.

The Laboratory is further equipped with commercial and self-developed grippers, sensing devices, and augmented reality appliances. Laboratory service offers quick experimental setup, several standardized software tools, and expertise in robot control and perception algorithms. It also hosted the Humanoids Lab Initiative in the past, and we still keep 15 small humanoid robots for educational or promotional purposes.

Perception and Manipulation Laboratory
Group photo

Researchers

PhD Students

Master Students

TFG Students

Support Staff