Towards Dynamic Visual Servoing for Interaction Control and Moving Targets

Abstract

In this work we present our results on dynamic visual servoing for the case of moving targets while also exploring the possibility of using such a controller for interaction with the environment. We illustrate the derivation of a feature space impedance controller for tracking a moving object as well as an Extended Kalman Filter based on the visual servoing kinematics for increasing the rate of the visual information and estimating the target velocity for both the cases of PBVS and IBVS with image point features. Simulations are carried out to validate the estimator performance during a Peg-in-Hole insertion task with a moving part. Experiments are also conducted on a real redundant manipulator with a low-cost wrist-mounted camera. Details on several implementation issues encountered during implementation are also discussed.

FrankaSim: A Dynamic Simulator for the Franka Emika Robot with Visual-Servoing Enabled Capabilities

“…The simulator is currently being used by researchers in the Rainbow team for prototyping and testing novel sensor-based control strategies, to study dynamic visual servoing 5 [21] and the combined use of vision and force sensing for precision assembly tasks. We expect that making the code available to the community will increase the number of end-users and applications addressed.…”

“…Finally, being the code of the simulator implemented as a replica of the ViSP class that wraps the libfranka, it greatly facilitates the possibility to transfer verified code to the real robot. This simulator lends itself well to simulate Dynamic Visual-Servoing [20], [21] or Vision-Force control schemes [22], [23], [24], relieving the user from the burden of implementing his/her own simulation platform.…”