ACE-F: A Cross Embodiment Foldable System with Force Feedback for Dexterous Teleoperation

2025-11-25

AI Summary

Existing teleoperation systems suffer from limited haptic feedback, poor cross-robot generalization, and insufficient portability, hindering their deployment in complex contact-rich tasks. This paper proposes a lightweight, foldable soft teleoperation controller framework. Methodologically, it (1) introduces a novel virtual force mapping that translates end-effector position errors into haptic signals—enabling morphology-agnostic force feedback without dedicated force sensors, thereby facilitating high-fidelity imitation learning demonstrations; (2) integrates inverse kinematics, PD control, and inverse dynamics into a unified, safe, and precise motion control architecture; and (3) optimizes the human–machine interface to achieve mouse-like intuitiveness across diverse robotic morphologies. Experiments validate the framework’s effectiveness on multiple robot platforms. Both source code and hardware designs are publicly released.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Interaction Techniques and Devices
• Machine Learning: Imitation Learning & Inverse Reinforcement Learning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Teleoperation systems are essential for efficiently collecting diverse and high-quality robot demonstration data, especially for complex, contact-rich tasks. However, current teleoperation platforms typically lack integrated force feedback, cross-embodiment generalization, and portable, user-friendly designs, limiting their practical deployment. To address these limitations, we introduce ACE-F, a cross embodiment foldable teleoperation system with integrated force feedback. Our approach leverages inverse kinematics (IK) combined with a carefully designed human-robot interface (HRI), enabling users to capture precise and high-quality demonstrations effortlessly. We further propose a generalized soft-controller pipeline integrating PD control and inverse dynamics to ensure robot safety and precise motion control across diverse robotic embodiments. Critically, to achieve cross-embodiment generalization of force feedback without additional sensors, we innovatively interpret end-effector positional deviations as virtual force signals, which enhance data collection and enable applications in imitation learning. Extensive teleoperation experiments confirm that ACE-F significantly simplifies the control of various robot embodiments, making dexterous manipulation tasks as intuitive as operating a computer mouse. The system is open-sourced at: https://acefoldable.github.io/

Problem

• Developing teleoperation systems with integrated force feedback for complex tasks
• Enabling cross-embodiment generalization across diverse robotic platforms
• Creating portable user-friendly designs for practical deployment limitations

Innovation

• Integrated force feedback via positional deviation interpretation
• Cross-embodiment generalization through soft-controller pipeline
• Foldable human-robot interface with inverse kinematics