Coupled dynamical system based arm–hand grasping model for learning fast adaptation strategies

Shukla, Ashwini; Billard, Aude

doi:10.1016/j.robot.2011.07.023

Cited by 51 publications

(56 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Coupling mechanisms between different control modules play an important role for ensuring a proper coordinated execution of complex tasks, such as visually guided reaching where the torso, head (including the eyes), arm and hand are simultaneously engaged. A proper coordination pattern between modules is especially crucial when performing prehensile tasks in the face of perturbations (Shukla and Billard 2011). Finally, a real-world environment can be rather highly dynamic and unpredictable.…”

Section: Robotic Visually Aided Manipulation and Obstacle Avoidancementioning

confidence: 99%

“…We analyze the kinematics of the eye, arm and finger motion to provide quantitative measurements on the phase relationships across these limbs. We extend the coupled dynamical systems (CDSs) framework, originally used for arm-hand coordination (Shukla and Billard 2011), to model the eye-arm-hand coordinated pattern measured in the human study.…”

Section: Our Contributionmentioning

confidence: 99%

“…Our recent work (Shukla and Billard 2011) shows the benefits of explicitly learning a coupling between the arm DS and the finger DS over modeling motions of the physical systems with a single extended DS. The problem associated with learning one high-dimensional dynamical model that guides the motion of two physical systems is that an explicit following of correlations shown in demonstrations between the two coupled dynamics is not guaranteed.…”

Section: Coupled Dynamical Systemsmentioning

confidence: 99%

“…The loss of coordination between the reach and grasp components might lead to failure of the overall prehensile task even when the individual dynamical systems converge to their attractors. An approach adopted in Shukla and Billard (2011) is to learn separately two dynamics and then learn a coupling between them. This approach ensures that the two DS will converge to their attractors, following a learned pattern of coordination between them.…”

Section: Coupled Dynamical Systemsmentioning

confidence: 99%

“…The approach, where the arm and hand DS are learned separately and then coupled explicitly, ensures that the behavior of the two systems is correctly synchronized, even when the motion is abruptly perturbed far from the motion recorded in human demonstrations. For more details about general properties of CDS, see Shukla and Billard (2011).…”

Section: Coupled Dynamical Systemsmentioning

confidence: 99%

See 4 more Smart Citations

Learning robotic eye–arm–hand coordination from human demonstration: a coupled dynamical systems approach

Lukic

Santos-Victor²,

Billard

2014

Biol Cybern

Self Cite

View full text Add to dashboard Cite

We investigate the role of obstacle avoidance in visually guided reaching and grasping movements. We report on a human study in which subjects performed prehensile motion with obstacle avoidance where the position of the obstacle was systematically varied across trials. These experiments suggest that reaching with obstacle avoidance is organized in a sequential manner, where the obstacle acts as an intermediary target. Furthermore, we demonstrate that the notion of workspace travelled by the hand is embedded explicitly in a forward planning scheme, which is actively involved in detecting obstacles on the way when performing reaching. We find that the gaze proactively coordinates the pattern of eye-arm motion during obstacle avoidance. This study provides also a quantitative assessment of the coupling between the eye-arm-hand motion. We show that the coupling follows regular phase dependencies and is unaltered during obstacle avoidance. These observations provide a basis for the design of a computational model. Our controller extends the coupled dynamical systems framework and provides fast and synchronous control of the eyes, the arm and the hand within a single and compact framework, mimicking similar control system found in humans. We validate our model for visuomotor control of a humanoid robot.

show abstract

Section: Robotic Visually Aided Manipulation and Obstacle Avoidancementioning

confidence: 99%

Section: Our Contributionmentioning

confidence: 99%

Section: Coupled Dynamical Systemsmentioning

confidence: 99%

Section: Coupled Dynamical Systemsmentioning

confidence: 99%

Section: Coupled Dynamical Systemsmentioning

confidence: 99%

See 3 more Smart Citations