Control-Aware Command Generation for Asynchronous Control and Action Inference with Vision-Based Policies towards Fast Execution
Control-Aware Command Generation for Asynchronous Control and Action Inference with Vision-Based Policies towards Fast Execution
This paper introduces an asynchronous inference and control framework that enables fast task execution while maintaining smooth and stable robot motions without modifying the underlying policy learning process. By formulating the generation of continuous target positions from discontinuous model predictions as a tracking control problem, the method makes asynchronous inference practical for real robots. The approach further accelerates execution through adaptive action skipping based on the variance of predicted positions. Experiments with Action Chunking Transformer and OpenVLA-OFT on a bimanual robot demonstrate substantial speedups while preserving high task success rates.
The authors propose a control-aware command generation framework that achieves faster execution on bimanual robots by treating asynchronous inference as a tracking control problem and using adaptive action skipping, with results reported for Action Chunking Transformer and OpenVLA-OFT.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
of predicted positions. Experiments with Action Chunking Transformer and OpenVLA-OFT on a bimanual robot demonstrate substantial speedups while preserving high task success rates.
Open source S4
duce an asynchronous inference and control framework that enables fast task execution while maintaining smooth and stable robot motions. By formulating the generation of continuous target positions from discontinuous model predictions as a tracking control problem, our method makes asynchronous inference practical for real robots. We further accelerate execution through adaptive action skipping based on the variance
Open source S3
arXiv:2611.11089v2 Announce Type: replace Abstract: Vision-based control policies, including vision-language-action models, have enabled robots to perform increasingly complex tasks. However, their execution speed is often limited by the high computational cost of action inference. In this work, we investigate what can be achieved at the control level without modifying the underlying policy learning process. We intro
Open source S2
Source：arXiv Robotics — research abstracts · arxiv.org