Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields

By Dae-Hyung Park, Heiko Hoffmann, Peter Pastor, Stefan Schaal. 2008

295 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, background): “, Park et al. (2008). The transformation function f (z) alters the output of the first system, in Equation (7), so that the second system, in Equation (8), can represent complex nonlinear patterns and it is given by”
Learning and generalization of motor skills by learning from demonstration (2009, methodology): “Here, we exploit this property for obstacle avoidance [9] by adding a coupling term p(x,v) to the differential equations of motion”
A Dynamical System-based Approach to Modeling Stable Robot Control Policies via Imitation Learning (2012, background): “, 2009), flight control (Perk & Slotine, 2006), obstacle avoidance (Park et al., 2008; Hoffmann et al., 2009), lifting (Bitzer & Vijayakumar, 2009), playing table-tennis (Kober, Mulling, et al.”
Learning collision-free reaching skill from primitives (2012, background): “In their framework, reaching trajectories were learned from teacher demonstration and generalized to new targets.”
Movement templates for learning of hitting and batting (2010, background): “The transformation function f ( z ) alters the output of the ﬁrst system, in Eq.”
Learning control Lyapunov function to ensure stability of dynamical system-based robot reaching motions (2014, methodology): “During the last decade, DS has been used to model discrete motions [6, 7, 29, 30], rhythmic motions [31, 32], hitting motions [33, 34, 7], obstacle avoidance [35, 36, 37], etc.”
Combining active learning and reactive control for robot grasping (2010, background): “Robot grasping research has focused on coarse object representations of novel objects [43, 25, 30, 8], and using additional sensor arrays when in close proximity to the object [12, 41].”
Biologically-inspired dynamical systems for movement generation: Automatic real-time goal adaptation and obstacle avoidance (2009, methodology): “To compute the control torques at the arm joints, we used inverse kinematics and dynamics [9]; the inverse kinematics took also into account the orientation of the hand [10].”
Learning motor primitives for robotics (2009, background): “Additional feedback terms can be added as in [2], [4], [5], [13].”
Imitation and Reinforcement Learning (2010, background): “Feedback terms can also be added as in [5] and [12].”
Learning to select and generalize striking movements in robot table tennis (2012, unknown): “In this case, a potential field centered around the obstacle (as described by Park et al. (2008) and Kroemer et al. (2010)) could be used.”