Vision-Assisted Control for Manipulation Using Virtual Fixtures

Abstract

This work focuses on the implementation of a vision-based motion guidance method, called virtual fixtures, on admittance-controlled human-machine cooperative robots with compliance. The robot compliance here refers to the structural elastic deformation of the device. The system uses computer vision as a sensor for providing a reference trajectory, and the virtual fixture control algorithm then provides haptic feedback to implemented direct, shared manipulation. It then discusses experiments to evaluate both speed and accuracy of the proposed constraints on human speed and accuracy versus free motion in a steady-hand paradigm. The result indicates improvements in the performance of human in the desired task execution.

Development and Application of a New Steady-Hand Manipulator for Retinal Surgery

“…Over the past few years, our group has developed several admittance control guidance methods, often called virtual fixtures [2], [1], [7]. In general, these methods operate as WeB8.5 follows: given sensed handle forces and torques f ∈ (6) exerted by the operator, a tool velocity screw is computed as…”

Position referenced force augmentation in teleoperated hydraulic manipulators operating under delayed and lossy networks: A pilot study

“…It is worth mentioning that the proposed force scheme should not be mistaken with the impedance-type virtual fixture scheme [27][28][29] . In an impedance-type virtual fixture scheme, the haptic force is proportional to the difference between the actual and desired positions at the slave end-effector, and its direction is orthogonal to the intended trajectory of the haptic device [30][31][32] .…”

Implicit active constraints for a compliant surgical manipulator

“…Park et al recently proposed a constraint model capable of rapidly compensating for cardiac motion [9], allowing a catheter to be navigated along the centerline of a deforming vessel to the target site. Simple constraints in the form of curved lines are unstable under the closed loop force control [10]. To access the intra-mural motion of the myocardium, Ren et al [11] proposed guidance constraints with explicit spatial details computed by a potential field.…”