Adaptive torque control using a connectionist reinforcement learning agent

13 years 5 months ago

Download www.eusflat.org

The correction of angular misalignment between mating components is a fundamental requirement for their successful assembly. In this paper we present how a learning agent based on the Stochastic Gradient Ascent (SGA) algorithm can be used to command appropriate rotations of a robotic manipulator's hand in order to minimise such misalignments and allow the completion of a peg in hole task. The learning capabilities of the proposed methodology are proven both with simulation and real time implementation using a PUMA 6 DOF industrial manipulator.

Lorenzo Brignone, Martin Howarth, S. Sivayoganatha

Real-time Traffic

Angular Misalignment | DOF Industrial Manipulator | EUSFLAT 2001 | EUSFLAT 2007 | Robotic Manipulator Hand |

claim paper

» Reinforcement Learning and the Bayesian Control Rule

» Automated Design of Adaptive Controllers for Modular Robots using Reinforcement Learning

» Dynamic Scheduling in Petroleum Process using Reinforcement Learning

» Guiding Inference Through Relational Reinforcement Learning

» The Dynamics of MultiAgent Reinforcement Learning

» A BiologicallyInspired Cognitive Agent Model Integrating Declarative Knowledge and Reinfor...

» Automatic computer game balancing a reinforcement learning approach

» Adaptive Distributed Control of Constrained MultiAgent Systems

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2001
Where	EUSFLAT
Authors	Lorenzo Brignone, Martin Howarth, S. Sivayoganathan, V. Balendran

Comments (0)

Sciweavers

Adaptive torque control using a connectionist reinforcement learning agent

Angular Misalignment | DOF Industrial Manipulator | EUSFLAT 2001 | EUSFLAT 2007 | Robotic Manipulator Hand |

Explore & Download

Productivity Tools

Document Tools

Image Tools

Sciweavers