Robot control uses torque feedback to fix valve misalignment
Robotic Valve Turning: Axial Misalignment Correction Using Reaction Torque Feedback
Robotics
Summary
Turning valves with robots can be tricky because the robot’s gripper might not line up perfectly with the valve. Vision tools sometimes struggle to see exactly how things are positioned, especially if something is blocking the view. The authors created a way for the robot to feel how much force (torque) it’s pushing with and use that to adjust itself. This method helps the robot automatically correct its angle to turn valves more accurately and reliably without relying on cameras.
What this means in practice
- •For industrial automation teams: Improve robotic control systems for turning valves by using torque feedback to correct misalignment without relying on cameras.
- •For robotic maintenance technicians: Enable robots to autonomously adjust their grip and angle when manipulating valves in environments where vision sensors may fail.
Authors
Amit Kumar, Sri Harsha Turlapati, Gautami Golani, Yang Lin, Ravi N. Banavar, Domenico Campolo
Abstract
In this work, we propose a haptic update control law that uses reaction torques to correct axial misalignment during robotic valve manipulation. Unlike vision-based estimates, which can be affected by calibration errors, occlusion, and uncertainty in the contact geometry, reaction torques arise directly from the physical interaction between the gripper and valve. A geometric relationship exists between the error (misalignment) vector and these torques. The primary aim of this work is to propose a stable controller exploiting this geometric property. Our control law is proven to be uniformly asymptotically stable. Simulations are performed for verification. Furthermore, we experimentally test the robustness of our method using a Kinova Gen3 robotic arm for initial misalignments ranging from $-15^\circ$ to $15^\circ$ at 3 different valve positions and report the resulting data distribution. The absolute value of the median misalignment across all 18 test cases is found to be within $2.46^\circ$ and that of reaction torques within $0.23\mathrm{Nm}$.