# A3RNN: Bi-directional Fusion of Bottom-up and Top-down Process for Developmental Visual Attention in Robots

arXiv: https://arxiv.org/abs/2510.10221 · HTML: https://mlsanity.com/paper/2510.10221/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 11 Oct 2025.

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [End-to-End Training of Deep Visuomotor Policies](https://mlsanity.com/paper/1504.00702/) (2015)
- [Image Segmentation Using Deep Learning: A Survey](https://mlsanity.com/paper/2001.05566/) (2020)
- [robosuite: A Modular Simulation Framework and Benchmark for Robot Learning](https://mlsanity.com/paper/2009.12293/) (2020)
- [Learning to Rearrange Deformable Cables, Fabrics, and Bags with Goal-Conditioned Transporter Networks](https://mlsanity.com/paper/2012.03385/) (2020)
- [3D Human Pose Estimation in RGBD Images for Robotic Task Learning](https://mlsanity.com/paper/1803.02622/) (2018)
- [Bi-ACT: Bilateral Control-Based Imitation Learning via Action Chunking with Transformer](https://mlsanity.com/paper/2401.17698/) (2024)
- [PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds](https://mlsanity.com/paper/2109.05566/) (2021)
- [Deep Predictive Learning: Motion Learning Concept inspired by Cognitive Robotics](https://mlsanity.com/paper/2306.14714/) (2023)
- [Spatial Attention Point Network for Deep-learning-based Robust Autonomous Robot Motion Generation](https://mlsanity.com/paper/2103.01598/) (2021)
- [Deep Active Visual Attention for Real-time Robot Motion Generation: Emergence of Tool-body Assimilation and Adaptive Tool-use](https://mlsanity.com/paper/2206.14530/) (2022)

## Abstract (arXiv)

This study investigates the developmental interaction between top-down (TD) and bottom-up (BU) visual attention in robotic learning. Our goal is to understand how structured, human-like attentional behavior emerges through the mutual adaptation of TD and BU mechanisms over time. To this end, we propose a novel attention model A3 RNN that integrates predictive TD signals and saliency-based BU cues through a bi-directional attention architecture. We evaluate our model in robotic manipulation tasks using imitation learning. Experimental results show that attention behaviors evolve throughout training, from saliency-driven exploration to prediction-driven direction. Initially, BU attention highlights visually salient regions, which guide TD processes, while as learning progresses, TD attention stabilizes and begins to reshape what is perceived as salient. This trajectory reflects principles from cognitive science and the free-energy framework, suggesting the importance of self-organizing attention through interaction between perception and internal prediction. Although not explicitly optimized for stability, our model exhibits more coherent and interpretable attention patterns than baselines, supporting the idea that developmental mechanisms contribute to robust attention formation.