6documents trouvés
Walking on non-planar surfaces using an inverse dynamic stack of tasks
O.RAMOS PONCE, N.MANSARD, O.STASSE, P.SOUERES
GEPETTO
Manifestation avec acte : IEEE-RAS International Conference on Humanoid Robots ( HUMANOIDS ) 2012 du 29 novembre au 01 décembre 2012, Osaka (Japon), 2012, 7p. , N° 12654
Lien : http://hal.archives-ouvertes.fr/hal-00738243
Diffusable
Plus d'informations
Abstract
This paper presents a method to handle walking on non-planar surfaces. The method obtains the trajectory of the center of mass and the next position of the foot from a pattern generator. Then, an inverse dynamics control scheme with a quadratic programming optimization solver is used to let the foot go from its initial to its final position, controlling also the center of mass and the waist. This solver is able to handle an arbitrary number of contact points. When the swinging foot is going down, collision points are detected and they are added as contact points to the model as soon as they appear. If there are three or more contact points, the foot can safely step, but if there are one or two contact points, the foot rotates properly to generate the largest support polygon. Using this heuristic, the foot can stand on non-planar surfaces. The results show the simulation of HRP-2 walking on a surface with obstacles.
Capture, recognition and imitation of anthropomorphic motion
S.HAK, N.MANSARD, O.RAMOS PONCE, L.SAAB, O.STASSE
GEPETTO
Manifestation avec acte : IEEE International Conference on Robotics and Automation (ICRA 2012), St Paul (USA), 14-18 Mai 2012, pp.3539-3540 , N° 12276
Lien : http://hal.archives-ouvertes.fr/hal-00706661
Diffusable
Plus d'informations
Abstract
This work presents an overview of our current research works in generation, recognition and editing of anthropomorphic motion using a unified framework: the stack of tasks. It is based on the task function formalism classically used for motion generation. A task function maps the joint space of a robot to a dedicated space which is usually linked to the sensors of the robot: the task space. The task spaces are suitable to perform motion analysis and task recognition because the tasks are described in those spaces. The generation is originally based on inverse kinematics but can be generalized to produce full-dynamic motions. The tasks are defined by a tasks space, a reference behavior and a task Jacobian. The reference behaviors are originated from human trajectories. Specific tasks are then integrated to retarget and to edit the reference motion in order to respect the dynamic constraints, the limits of the robot and the general aspect.
Dynamic whole-body motion generation under rigid contacts and other unilateral constraints
L.SAAB, O.RAMOS PONCE, F.KEITH, N.MANSARD, P.SOUERES, J.Y.FOURQUET
GEPETTO, INRIA Rhône-Alpes, ENIT Tarbes
Rapport LAAS N°12014, Janvier 2012, 14p.
Diffusable
126189Tracking in presence of total occlusion and size variation using mean shift and kalman filter
O.RAMOS PONCE, M.A.MIRZAEI, F.MERIENNE
GEPETTO, ENSAM, ParisTech, LE2I
Manifestation avec acte : IEEE/SICE International Symposium on System Integration ( SII ) 2011 du 20 décembre au 22 décembre 2011, Kyoto (Japon), Décembre 2011, 6p. , N° 11863
Lien : http://hal.archives-ouvertes.fr/hal-00749631
Diffusable
Plus d'informations
Abstract
The classical mean shift algorithm for tracking in perfectly arranged conditions constitutes a good object tracking method. However, in the real environment it presents some limitations, especially under the presence of noise, objects with varying size, or occlusions. In order to deal with these problems, this paper proposes a reliable object tracking algorithm using mean shift and the Kalman filter, which was added to the traditional algorithm as a predictor when no reliable model of the object being tracked is found. Experimental work demonstrates that the proposed mean shift Kalman filter algorithm improves the tracking performance of the classical algorithms in complicated real scenarios. The results involve the tracking of an object in a gray level and in a color sequence, with varying size and in presence of total occlusion.
Dynamic motion capture and edition using a stack of tasks
O.RAMOS PONCE, L.SAAB, S.HAK, N.MANSARD
GEPETTO
Manifestation avec acte : IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS 2011), Bled (Slovénie), 26-28 Octobre 2011, pp.224-230 , N° 11430
Lien : http://hal.archives-ouvertes.fr/hal-00600959/fr/
Diffusable
Plus d'informations
Abstract
This paper presents a complete methodology to quickly reshape a dynamic motion demonstrated by a human and to adapt the dynamics of the human to the dynamics of the robot. The method uses an inverse dynamics control scheme with a quadratic programming optimization solver. The motion data recorded using a motion capture system is introduced into the control scheme as a reference posture task to be followed by the joints trajectory respecting the dynamic limitations as well as the contact constraints. The motion is further modified using arbitrary tasks to let the robot imitate the original motion more closely or to make voluntary changes for aesthetic reasons. The results show the method applied to the humanoid robot HRP-2 imitating a human "pop dance".
Generic dynamic motion generation with multiple unilateral constraints
L.SAAB, O.RAMOS PONCE, N.MANSARD, P.SOUERES, J.Y.FOURQUET
ENIT Tarbes, GEPETTO
Manifestation avec acte : IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011), San Francisco (USA), 25-30 Septembre 2011, 8p. , N° 11678
Diffusable
126041