AnyTeleop: A General Vision-Based Dexterous Robot Arm-Hand Teleoperation System
This work addresses the scalability issue in robot teleoperation for researchers and practitioners, enabling broader application across diverse hardware and settings, though it is incremental as it builds on existing teleoperation methods.
The authors tackled the problem of vision-based teleoperation systems being limited to specific robot models and environments by developing AnyTeleop, a general system that supports multiple arms, hands, realities, and camera configurations, achieving higher success rates in real-world experiments and better imitation learning performance in simulation compared to previous specialized systems.
Vision-based teleoperation offers the possibility to endow robots with human-level intelligence to physically interact with the environment, while only requiring low-cost camera sensors. However, current vision-based teleoperation systems are designed and engineered towards a particular robot model and deploy environment, which scales poorly as the pool of the robot models expands and the variety of the operating environment increases. In this paper, we propose AnyTeleop, a unified and general teleoperation system to support multiple different arms, hands, realities, and camera configurations within a single system. Although being designed to provide great flexibility to the choice of simulators and real hardware, our system can still achieve great performance. For real-world experiments, AnyTeleop can outperform a previous system that was designed for a specific robot hardware with a higher success rate, using the same robot. For teleoperation in simulation, AnyTeleop leads to better imitation learning performance, compared with a previous system that is particularly designed for that simulator. Project page: https://yzqin.github.io/anyteleop/.