Dynamical Systems Approach for the Autonomous Avoidance of Obstacles and Joint-limits for an Redundant Robot Arm

Iossifidis, Ioannis; Schöner, Gregor

doi:10.1109/iros.2006.282468

Cited by 45 publications

(30 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this simulated scenario, the user grasps the tip, moves it far away from the task region (with a non-negligible effort, since a motion command is always present). The learned skill is reproduced in 3 See [18] for further details and proof of closed loop stability. 4 The number of components is set empirically, by visual inspection, in order to reach a good trade-off between the model complexity and fit of the data.…”

Section: B Experimental Resultsmentioning

confidence: 99%

“…Several rescaling techniques have been proposed to modulate the contribution of each subsystem to the overall robot motion. Usually the contribution of each motion primitive is suitably modulated in order to adapt the motion to goal variations and collision avoidance [2], along with suppression of unwanted movements in the null space [4] or avoidance of joint limits reaching [3].…”

Section: Related Work and Proposed Approachmentioning

confidence: 99%

See 1 more Smart Citation

Bilateral physical interaction with a robot manipulator through a weighted combination of flow fields

Pistillo

Calinon

Caldwell

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

Abstract-When collaboration between human users and robots involves physical interaction, the importance of the safety issue arises. We propose a method to transfer to robots several tasks demonstrated by the user through kinesthetic teaching and subsequently learned using a weighted combination of dynamical systems (DS). The approach used to encode the desired skills ensures a safe robot behavior during the task reproduction, allowing physical interaction with the user who can employ the manipulator as a tangible interface. By using a force sensor-less impedance controller with a back-drivable robot, this concept is exploited in two physical human-robot interaction (pHRI) scenarios. The first considers an emergency situation in which the user can stop or pause a task execution by grasping and moving the robot away from the region of space associated to the skill. The second studies the possibility to select one among several learned tasks and switch to its execution by physically guiding the robot towards the task region.

show abstract

Section: B Experimental Resultsmentioning

confidence: 99%

Section: Related Work and Proposed Approachmentioning

confidence: 99%

Bilateral physical interaction with a robot manipulator through a weighted combination of flow fields

Pistillo

Calinon

Caldwell

2011

2011 IEEE/RSJ International Conference on Intelligent Robots and Systems

View full text Add to dashboard Cite

show abstract

“…Both problems get even more complex when the environment changes over time (e.g., there are moving targets or obstacles). In such cases, rather than solving the inverse problems analytically, various heuristic approaches are being used [5,7], such as roadmaps [2,17], cell decomposition [20], potential fields [18], or other dynamical systems approaches [16]. Hayashi [15] presents a method in which the joint angles are represented by a continuous function of time and the joint index, generating smooth movement plans.…”

Section: Introductionmentioning

confidence: 99%

Kernel representations for evolving continuous functions

2012

View full text Add to dashboard Cite

Abstract. To parameterize continuous functions for evolutionary learning, we use kernel expansions in nested sequences of function spaces of growing complexity. This approach is particularly powerful when dealing with non-convex constraints and discontinuous objective functions. Kernel methods offer a number of beneficial properties for parameterizing continuous functions, such as smoothness and locality, which make them attractive as a basis for mutation operators. Beyond such practical considerations, kernel methods make heavy use of inner products in function space and offer a well established regularization framework. We show how evolutionary computation can profit from these properties. Searching function spaces of iteratively increasing complexity allows the solution to evolve from a simple first guess to a complex and highly refined function. At transition points where the evolution strategy is confronted with the next level of functional complexity, the kernel framework can be used to project the search distribution into the extended search space. The feasibility of the method is demonstrated on challenging trajectory planning problems where redundant robots have to avoid obstacles.

show abstract

“…This was applied in a reaching task for controlling a humanoid's reaching motion, where the robot performed smooth motion while avoiding configurations near the joint limits. In a reaching while avoiding an obstacle task, Iossifidis & Schöner (2006) used attractor dynamics, where the target object acts as a point attractor on the end effctor. Both the end-effector and the redundant elbow joint avoided the obstacle as the arm reaches for an object.…”

mentioning

confidence: 99%

“…Both the end-effector and the redundant elbow joint avoided the obstacle as the arm reaches for an object. The way to combine the demonstrated path with the robots own plan distinguishes our use of the NSP from from previous work (Hersch & Billard, 2008), (Ijspeert et al, 2002) and (Iossifidis & Schöner, 2006). Another difference is the use of the hand state space for PbD; most approaches for motion planning in the literature uses joint space (Ijspeert et al, 2002) while some other approaches use the Cartesian space.…”

mentioning

confidence: 99%