Task-Guided Image Compression Framework for Seamless Teleoperation
This work tackles the challenge of reliable communication under limited bandwidth.
We propose to leverage the context and task knowledge to guide the compression to favor task performance rather than image fidelity. This poster has been presented at IEEE INFOCOM May 2024, Vancouver, Canada.
Image-based teleoperation offers significant flexibility and efficiency in several applications, such as teleoperated driving; still, it highly depends on reliable communication band-width and high Signal-to-Noise Ratio (SNR), which is hard to guarantee in uncontrolled environments. This poster tackles the challenge of reliable communication under limited bandwidth. We propose to leverage the context and task knowledge to guide the compression to favor task performance rather than image fidelity. In particular, we jointly designed source-channel coding with a task performer to present an end-to-end TAsk-Guided Image Communication (TAGIC) framework, which uses Soft Introspective Variational Autoencoder (S-IntroVAE) and prioritizes the task-critical image information with limited communication bandwidth in the low SNR region. We demonstrate the effectiveness of TAGIC in a teleoperated driving scenario through the CARLA simulation platform - a widely used simulator in the autonomous driving community. Given the equivalent value of bandwidth compression ratio, TAGIC achieves a 202.6% improvement in the driving score over existing methods at low SNR.
@inproceedings{Diao_2024_TTI,author={Diao, Yufeng and Zhang, Yichi and Zhao, Guodong and De Martini, Daniele},booktitle={Proceedings of IEEE Conference on Computer Communications Workshops},title={TAGIC: Task-Guided Image Communication Framework for Seamless Teleoperation},year={2024},volume={},number={},pages={},keywords={Joint source-channel coding; Teleoperated driving; Machine learning},doi={},}
