A3RNN: Bi-directional Fusion of Bottom-up and Top-down Process for Developmental Visual Attention in Robots
Preprint
Abstract
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 $A^3 RNN$ 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.
Keywords
All Related Versions
This publication has 14 references indexed in Scilit:
- The Cascading Development of Visual Attention in Infancy: Learning to Look and Looking to LearnCurrent Directions in Psychological Science, 2023
- Lightweight object detection algorithm for robots with improved YOLOv5Engineering Applications of Artificial Intelligence, 2023
- Deep Active Visual Attention for Real-Time Robot Motion Generation: Emergence of Tool-Body Assimilation and Adaptive Tool-UseIEEE Robotics and Automation Letters, 2022
- PQ-Transformer: Jointly Parsing 3D Objects and Layouts From Point CloudsIEEE Robotics and Automation Letters, 2022
- Image Segmentation Using Deep Learning: A SurveyIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Active Inference: A Process TheoryNeural Computation, 2017
- Whatever next? Predictive brains, situated agents, and the future of cognitive scienceBehavioral and Brain Sciences, 2013
- The free-energy principle: a unified brain theory?Nature Reviews Neuroscience, 2010
- Emergence of Functional Hierarchy in a Multiple Timescale Neural Network Model: A Humanoid Robot ExperimentPLOS Computational Biology, 2008
- A model of saliency-based visual attention for rapid scene analysisIEEE Transactions on Pattern Analysis and Machine Intelligence, 1998