UTTG: A Universal Teleoperation Framework Via Online Trajectory Generation
ShengJian Fang, Yixuan Zhou, Yu Zheng, Pengyu Jiang, Siyuan Liu, Hesheng Wang
AI summary
Problem
Existing teleoperation methods suffer from hardware dependency and control frequency mismatches between low-rate human input devices and high-frequency robotic platforms, limiting scalability and requiring platform-specific tuning.
Approach
The framework automatically extracts kinematic parameters from URDF files to create a unified interface, uses an online minimum-stretch cubic spline algorithm to interpolate low-frequency human inputs into high-frequency robot commands, and incorporates a joint prediction module to reduce latency.
Key results
- Plug-and-play deployment across three diverse robotic platforms without hardware-specific tuning
- Bridging frequency gaps from 20Hz to 1000Hz outputs
- Teleoperation latency under 50ms at 30Hz and approximately 15ms at 200Hz
- Dual precise and rapid modes validated for smooth manipulation across varied tasks
Why it matters
Provides a scalable, hardware-agnostic teleoperation solution critical for hazardous environment operations and large-scale robot learning via expert demonstrations.
Abstract
Teleoperation is crucial for hazardous environ- ment operations and serves as a key tool for collecting expert demonstrations in robot learning. However, existing methods face robotic hardware dependency and control frequency mis- matches between teleoperation devices and robotic platforms. Our approach introduces a unified interface that automatically extracts kinematic parameters from Unified Robot Description Format (URDF) files, enabling plug-and-play deployment across diverse robotic systems. The proposed interpolation algorithm bridges the frequency gap between low-rate human inputs and high-frequency robotic control commands through online continuous trajectory generation, without requiring access to the closed, bottom-level control loop. To further reduce la- tency, a joint prediction module is incorporated to antici- pate operator intent and compensate for delays. Moreover, we introduce a minimum-stretch spline to optimize motion smoothness and quality. The system supports both precision and rapid operation modes for different task requirements. Experiments on three robotic platforms, including dual-arm setups, demonstrate our frameworkâs generality, smoothness, and responsiveness. Teleoperation latency remains below 50ms at 30Hz input and approaches 15ms at 200Hz input. The code is developed in C++ with a Python interface, and available at https://github.com/IRMV-Manipulation-Group/UTTG.