Bi-AQUA: Bilateral Control-Based Imitation Learning for Underwater Robot Arms via Lighting-Aware Action Chunking with Transformers

TL;DR

Bi-AQUA introduces a novel underwater bilateral imitation learning framework that explicitly models lighting variations using transformers, significantly improving robustness and adaptability in underwater robot manipulation tasks.

Contribution

It is the first to incorporate lighting-aware modeling into bilateral imitation learning for underwater robots, enhancing performance under variable lighting conditions.

Findings

Outperforms baseline without lighting modeling.

Robust under seen, unseen, and changing lighting conditions.

Effective in long-horizon, contact-rich tasks.

Abstract

Underwater robotic manipulation remains challenging because lighting variation, color attenuation, scattering, and reduced visibility can severely degrade visuomotor policies. We present Bi-AQUA, the first underwater bilateral control-based imitation learning framework for robot arms that explicitly models lighting within the policy. Bi-AQUA integrates transformer-based bilateral action chunking with a hierarchical lighting-aware design composed of a label-free Lighting Encoder, FiLM-based visual feature modulation, and a lighting token for action conditioning. This design enables adaptation to static and dynamically changing underwater illumination while preserving the force-sensitive advantages of bilateral control, which are particularly important in long-horizon and contact-rich manipulation. Real-world experiments on underwater pick-and-place, drawer closing, and peg extraction tasks show that Bi-AQUA outperforms a bilateral baseline without lighting modeling and achieves robust performance under seen, unseen, and changing lighting conditions. These results highlight the importance of combining explicit lighting modeling with force-aware bilateral imitation learning for reliable underwater manipulation. For additional material, please check: https://mertcookimg.github.io/bi-aqua