Augmenting Neural Networks-based Model Approximators in Robotic Force-tracking Tasks

2025-09-10

AI Summary

Traditional direct force controllers (DFCs) rely heavily on expert tuning and prior environmental knowledge, exhibiting limited adaptability to dynamic contact conditions. To address this, we propose VAICAM—a novel framework that introduces the robot end-effector’s tangential velocity as an explicit input to a feedforward neural network for contact force prediction. VAICAM further employs an optimization-based residual action generator that collaborates with an impedance controller to compensate for modeling uncertainties and environmental variations, thereby enhancing both robustness and responsiveness of DFCs. Evaluated on a Franka Panda robot in Gazebo across multiple force-tracking trajectories, VAICAM achieves up to 32.7% lower force tracking error compared to two baseline controllers. The results demonstrate its superior capability for adaptive force control in unknown or time-varying environments.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems

Abstract

As robotics gains popularity, interaction control becomes crucial for ensuring force tracking in manipulator-based tasks. Typically, traditional interaction controllers either require extensive tuning, or demand expert knowledge of the environment, which is often impractical in real-world applications. This work proposes a novel control strategy leveraging Neural Networks (NNs) to enhance the force-tracking behavior of a Direct Force Controller (DFC). Unlike similar previous approaches, it accounts for the manipulator's tangential velocity, a critical factor in force exertion, especially during fast motions. The method employs an ensemble of feedforward NNs to predict contact forces, then exploits the prediction to solve an optimization problem and generate an optimal residual action, which is added to the DFC output and applied to an impedance controller. The proposed Velocity-augmented Artificial intelligence Interaction Controller for Ambiguous Models (VAICAM) is validated in the Gazebo simulator on a Franka Emika Panda robot. Against a vast set of trajectories, VAICAM achieves superior performance compared to two baseline controllers.

Problem

• Enhancing force-tracking in robotic manipulators with neural networks
• Addressing tangential velocity impact during fast robotic motions
• Reducing dependency on expert tuning and environmental knowledge

Innovation

• Neural Networks predict contact forces
• Optimization generates optimal residual action
• Velocity-augmented controller enhances force tracking