Operational Space Control: A Theoretical and Empirical Comparison

By Jun Nakanishi, Rick E. Cory, Michael N. Mistry, Jan Peters, Stefan Schaal. 2008

405 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Cognitive Neuroscience, 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 Cognitive Neuroscience

In Control and Systems Engineering

Citations in the corpus

Reinforcement learning in robotics: A survey (2013, methodology): “In the ball-paddling example, we may simplify by controlling the robot in racket space (which is lowerdimensional as the racket is orientation-invariant around the string’s mounting point) with an operational space control law (Nakanishi et al., 2008).”
Learning to Control a Low-Cost Manipulator using Data-Efficient Reinforcement Learning (2011, methodology): “Trajectory-following methods such as Jacobian-transpose control [13] are not suitable in our case: A desired trajectory is not known in advance.”
Model-Based Control of Soft Robots: A Survey of the State of the Art and Open Challenges (2021, background): “Thus, direct extensions of standard operational space controllers [170] can be used to ensure that (33) holds for the full dynamic model (2) and possibly in presence of strong underactuation (m << n).”
Learning, planning, and control for quadruped locomotion over challenging terrain (2011, background): “Other approaches, which require inversion of the RBD inertia matrix can create significant problems in face of modeling errors (Nakanishi et al. 2008).”
Learning Forward Models for the Operational Space Control of Redundant Robots (2010, background): “Readers can refer to Sentis and Khatib (2005) for a more recent work and Nakanishi et al (2008) for a survey.”
Variable Impedance Control of Redundant Manipulators for Intuitive Human–Robot Physical Interaction (2015, background): “As observed in [30], control law (10) is able to ensure stability in practice both for the end effector task and in the null space.”
Lessons from the Amazon Picking Challenge: Four Aspects of Building Robotic Systems (2016, neutral): “This permits combining precise and repeatable joint-space controllers (for moving the arm-mounted camera to a predefined view position), task-space controllers [37] involving base and arm (for reaching in and out of the shelf), and task-space motion involving only the arm (for fine-positioning insid”
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].”
Using model knowledge for learning inverse dynamics (2010, methodology): “or having physically impossible values) and, hence, physical consistency constraints have to be imposed on the regression problem [6], [7].”
Model learning for robot control: a survey (2011, methodology): “It is hard to create sufficiently rich data sets so that physically plausible parameters can be identified (Nakanishi et al. 2008), and when identified online, additional persistent excitation issues occur (Narendra and Annaswamy 1987).”
Learning and generalization of motor skills by learning from demonstration (2009, methodology): “To execute DMPs on the robot we used a velocity based inverse kinematics controller as described in [13], [8].”