CSIC (Logo) UPC ((Logo)

Perception and Manipulation

Research 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.

Research head: Carme Torras Genís.


Research Areas

Learning by demonstration

Learning 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.

Planning for perception and manipulation

We are interested in planning algorithms for object modeling, with special interest in deformable objects. High-level task formulations will be integrated with low-level geometry-based methods and simplified physical models, as well as with an on-line sensory-based treatment of uncertainty so as to come up with a specified sequence of motion commands. More...

Shape recovering of deformable objects

To develop non-iterative solutions to recover the shape of the deformable objects. This is a severely under-constrained problem and many different kinds of prior models have been introduced to restrict the space of possible shapes to a manageable size. More...

Projective geometry applied to robotics

The objective is to exploit projective geometry results to acquire object/scene models and camera motion with uncalibrated cameras. Our results have been applied to estimation of epipolar geometry, depth from zoom and time to contact computation.




Recent Publications (2012 - 2011)

  • B. Dellen and F. Wörgötter. A local algorithm for the computation of image velocity via constructive interference of global Fourier components. International Journal of Computer Vision, 92(1): 53-70, 2011. [info] [pdf]
  • B. Dellen, G. Alenyà, S. Foix and C. Torras. Segmenting color images into surface patches by exploiting sparse depth data, 2011 IEEE Workshop on Applications of Computer Vision, 2011, Kona, Hawaii, pp. 591-598. [info] [pdf]
  • G. Alenyà, B. Dellen and C. Torras. 3D modelling of leaves from color and ToF data for robotized plant measuring, 2011 IEEE International Conference on Robotics and Automation, 2011, Shanghai, pp. 3408-3414, IEEE. [info] [pdf]
  • A. Agostini, C. Torras and F. Wörgötter. A general strategy for interactive decision-making in robotic platforms. Technical Report IRI-TR-11-01, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2011. [info] [pdf]
  • S. Foix, G. Alenyà and C. Torras. Lock-in time-of-flight (ToF) cameras: a survey. IEEE Sensors Journal, 11(9): 1917-1926, 2011. [info] [pdf]
  • A. Agostini and E. Celaya. Stochastic approximations of average values using proportions of samples. Technical Report IRI-TR-11-02, Institut de Robòtica i Informàtica Industrial, CSIC-UPC, 2011. [info] [pdf]
  • L. Rozo, P. Jiménez and C. Torras. Robot learning from demonstration in the force domain, 2011 IJCAI Workshop on Agents Learning Interactively from Human Teachers, 2011, Barcelona, Spain, pp. 1-6. [info] [pdf]
  • L. Rozo, P. Jiménez and C. Torras. Robot learning from demonstration of force-based tasks with multiple solution trajectories, 15th International Conference on Advanced Robotics, 2011, Tallin, Estonia, pp. 124-129, IEEE. [info] [pdf]
  • J. Borràs Sol, F. Thomas and C. Torras. Architectural singularities of a class of pentapods. Mechanism and Machine Theory, 46(8): 1107-1120, 2011. [info] [pdf]
  • E.E. Aksoy, A. Abramov, J. Dörr, K. Ning, B. Dellen and F. Wörgötter. Learning the semantics of object-action relations by observation. The International Journal of Robotics Research , 30(10): 1229-1249, 2011. [info] [pdf]
  • M. Wallenberg, M. Felsberg, P. Forssen and B. Dellen. Channel coding for joint colour and depth segmentation, 33rd Annual Symposium of the German Association for Pattern Recognition, 2011, Frankfurt, Germany, in Pattern Recognition, Vol 6835 of Lecture Notes in Computer Science, pp. 306-315, 2011, Springer. [info] [pdf]
  • A. Goldsztejn, C. Jermann, V. Ruiz de Angulo and C. Torras. Symmetry breaking in numeric constraint problems, 17th International Conference on Principles and Practice of Constraint Programming, 2011, Perugia, Italy, in Principles and Practice of Constraint Programming, Vol 6876 of Lecture Notes in Computer Science, pp. 317-324, 2011, Springer. [info] [pdf]
  • A. Agostini, C. Torras and F. Wörgötter. Integrating task planning and interactive learning for robots to work in human environments, 2011 International Joint Conference on Artificial Intelligence, 2011, Barcelona, pp. 2386-2391. [info] [pdf]
  • A. Agostini and E. Celaya. A competitive strategy for function approximation in Q-learning, 2011 International Joint Conference on Artificial Intelligence, 2011, Barcelona, pp. 1146-1151. [info] [pdf]
  • F. Moreno-Noguer and J.M. Porta. Probabilistic simultaneous pose and non-rigid shape recovery, 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, Colorado Springs, USA, pp. 1289-1296, IEEE Press. [info] [pdf]
  • E.E. Aksoy, B. Dellen, M. Tamosiunaite and F. Wörgötter. Execution of a dual-object (pushing) action with semantic event chains, 11th IEEE-RAS International Conference on Humanoid Robots, 2011, Bled, Slovenia, pp. 576-583, IEEE Press. [info] [pdf]
  • J. M. Mirats Tur and J. Camps. A three-dof actuated robot. IEEE Robotics and Automation Magazine, 18(3): 96-103, 2011. [info] [pdf]
  • E. Simo-Serra, F. Moreno-Noguer and A. Perez. Design of non-anthropomorphic robotic hands for anthropomorphic tasks, 2011 ASME International Design Engineering Technical Conference, 2011, Washington, DC, USA, pp. 1-10, to appear. [info] [pdf]
  • F. Moreno-Noguer. Deformation and illumination invariant feature point descriptor, 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, Colorado Springs, USA, pp. 1593-1600, IEEE Press. [info] [pdf]
  • S. Foix, G. Alenyà and C. Torras. Towards plant monitoring through next best view, 14th International Conference of the Catalan Association for Artificial Intelligence, 2011, Lleida, in Artificial Intelligence Research and Development, Vol 232 of Frontiers in Artificial Intelligence and Applications, pp. 101-109, IOS Press. [info] [pdf]
  • G. Alenyà, F. Moreno-Noguer, A. Ramisa and C. Torras. Active perception of deformable objects using 3D cameras, 2011 Workshop de Robótica Experimental, 2011, Seville, pp. 434-440. [info] [pdf]
  • J. Borràs Sol, F. Thomas and C. Torras. Singularity-invariant families of line-plane 5-SPU platforms. IEEE Transactions on Robotics, 27(5): 837-848, 2011. [info] [pdf]
  • M. Villamizar, H. Grabner, J. Andrade-Cetto, A. Sanfeliu, L. Van Gool and F. Moreno-Noguer. Efficient 3D object detection using multiple pose-specific classifiers, 2011 British Machine Vision Conference, 2011, Dundee, UK, pp. 20.1-20.10. [info] [pdf]
  • A. Ramisa, G. Alenyà, F. Moreno-Noguer and C. Torras. Determining where to grasp cloth using depth information, 14th International Conference of the Catalan Association for Artificial Intelligence, 2011, Lleida, in Artificial Intelligence Research and Development, Vol 232 of Frontiers in Artificial Intelligence and Applications, pp. 199-207, IOS Press. [info] [pdf]
  • M. Douze, A. Ramisa and C. Schmid. Combining attributes and Fisher vectors for efficient image retrieval, 2011 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, Colorado Springs, USA, pp. 745-752, IEEE Press. [info] [pdf]
  • J.J. McAuley, A. Ramisa and T.S. Caetano. Optimization of robust loss functions for weakly-labeled image taxonomies: An ImageNet case study, 8th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognition, 2011, St. Petersburg, Russia, in Energy Minimization Methods in Computer Vision and Pattern Recognition, Vol 6819 of Lecture Notes in Computer Science, pp. 355-368, 2011, Springer. [info] [pdf]
  • E. Serradell, A. Romero, R. Leta, C. Gatta and F. Moreno-Noguer. Simultaneous correspondence and non-rigid 3D reconstruction of the coronary tree from single X-ray images, 2011 International Conference on Computer Vision, 2011, Barcelona, pp. 850-857, IEEE. [info] [pdf]
  • M. Villamizar, F. Moreno-Noguer, J. Andrade-Cetto and A. Sanfeliu. Detection performance evaluation of boosted random Ferns, 5th Iberian Conference on Pattern Recognition and Image Analysis, 2011, Las Palmas de Gran Canaria, in Pattern Recognition and Image Analysis, Vol 6669 of Lecture Notes in Computer Science, pp. 67-75, 2011, Springer. [info] [pdf]
  • J. Borràs Sol, F. Thomas and C. Torras. New geometric approaches to the singularity analysis of parallel platforms, 2011 Workshop de Robótica Experimental, 2011, Seville, pp. 173-180. [info] [pdf]
  • C. Torras. Comentario al aforismo 74. In El arte de aprender. Soluciones desde la prudencia, 74-75. Fundación EOI, Ministerio de Industria, Turismo y Comercio, 2011. [info] [pdf]
  • I. Abío, M. Alberich-Carramiñana and V. González-Alonso. The ultrametric space of plane branches. Communications in Algebra, 39(11): 4206-4220, 2011. [info] [pdf]
  • N. Krüger, C. Geib, J. Piater, R. Petrick, M. Steedman, F. Wörgötter, A. Ude, T. Asfour, D. Kraft, D. Omrcen, A. Agostini and R. Dillman. Object-action complexes: grounded abstractions of sensory-motor processes. Robotics and Autonomous Systems, 59(10): 740-757, 2011. [info] [pdf]
  • A. Alexey, K. Pauwels, J. Papon, F. Wörgötter and B. Dellen. Depth-supported real-time video segmentation with the Kinect, 2012 IEEE Workshop on Applications of Computer Vision, 2012, Breckenridge, CO, USA, pp. 457-464. [info] [pdf]
  • P. Jiménez. Survey on model-based manipulation planning of deformable objects. Robotics and Computer-Integrated Manufacturing, 28(2): 154-163, 2012. [info] [pdf]
  • P. Jiménez. Survey on assembly sequencing: a combinatorial and geometrical perspective. Journal of Intelligent Manufacturing, 2012, to appear. [info] [pdf]
  • S. Ulbrich, V. Ruiz de Angulo, T.. Asfour, C. Torras and R. Dillman. General robot kinematics decomposition without intermediate markers. IEEE Transactions on Neural Networks, 23(4): 620-630, 2012. [info] [pdf]
  • A. Ramisa, D. Aldavert, S. Vasudevan, R. Toledo and R. López de Mántaras. Evaluation of three vision based object perception methods for a mobile robot. Journal of Intelligent and Robotic Systems, 2012, to appear. [info] [pdf]