AI-Enabled Force and Torque Control for Human Robot Interaction

Physical human‑robot interaction (pHRI) needs very accurate control of the forces and torques that occur when a person touches a robot. This accuracy keeps the robot safe and compliant, even in fast‑changing, unpredictable situations. Traditional impedance and admittance controllers often fall short because they use fixed settings and depend on highly precise system models. To overcome these limits, this research looks at an AI‑based force‑and‑torque control framework. The framework blends deep neural networks and reinforcement learning with standard control methods. It takes in many kinds of sensor data—force‑torque readings, joint encoder positions, and inertial measurements—to learn how a human is interacting with the robot and what the human intends, all

in real time. By changing control gains on the fly, the system keeps the interaction stable, lowers peak contact forces, and cuts unwanted torques during cooperative tasks. The approach also gives a clear way to test how well adaptive control works on collaborative robots. The framework helps with: – modeling compliant robot behavior, – simulating human‑in‑the‑loop dynamics, and – analyzing torque profiles. Comparing this method to classic control schemes shows how to make collaborative robots more robust, adaptable, and safe for users.

Message: Hi FE, I need help with “AI-Enabled Force and Torque Control for Human Robot Interaction” in “Electrical Engineering”