CHILD (Controller for Humanoid Imitation and Live Demonstration): a Whole-Body Humanoid Teleoperation System

2025-07-31

AI Summary

Existing teleoperation systems for humanoid robots lack support for fine-grained, joint-level whole-body control and dynamic force feedback, hindering execution of complex mobile manipulation tasks. This paper proposes a compact, reconfigurable whole-body teleoperation system featuring a lightweight, fully articulated controller—novelly integrated into a standard infant carrier—that enables adaptive force feedback and intuitive joint-space mapping. The system employs a modular mechanical design, low-latency haptic actuators, and a cross-platform-compatible architecture, ensuring compatibility with diverse dual-arm and humanoid robot platforms. Experimental evaluations demonstrate its effectiveness in dynamic locomotion, object grasping, and whole-body coordinated manipulation. All hardware designs are open-sourced, significantly enhancing teleoperation safety, flexibility, and reproducibility.

Technology Category

• Intelligent Robots: Manipulation
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Novel mobile and WoT systems, and system-of-systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Recent advances in teleoperation have demonstrated robots performing complex manipulation tasks. However, existing works rarely support whole-body joint-level teleoperation for humanoid robots, limiting the diversity of tasks that can be accomplished. This work presents Controller for Humanoid Imitation and Live Demonstration (CHILD), a compact reconfigurable teleoperation system that enables joint level control over humanoid robots. CHILD fits within a standard baby carrier, allowing the operator control over all four limbs, and supports both direct joint mapping for full-body control and loco-manipulation. Adaptive force feedback is incorporated to enhance operator experience and prevent unsafe joint movements. We validate the capabilities of this system by conducting loco-manipulation and full-body control examples on a humanoid robot and multiple dual-arm systems. Lastly, we open-source the design of the hardware promoting accessibility and reproducibility. Additional details and open-source information are available at our project website: https://uiuckimlab.github.io/CHILD-pages.

Problem

• Enables joint-level teleoperation for humanoid robots
• Supports whole-body control and loco-manipulation tasks
• Incorporates adaptive force feedback for safety

Innovation

• Compact reconfigurable teleoperation system
• Joint level control for humanoids
• Adaptive force feedback integration