# Fast Human Attention Prediction for Fixation-guided Active Perception in Autonomous Navigation

arXiv: https://arxiv.org/abs/2606.20491 · HTML: https://mlsanity.com/paper/2606.20491/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 43 references that are in the map.
- First posted on arXiv 18 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures](https://mlsanity.com/paper/1802.01561/) (2018)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [Liquid Time-constant Networks](https://mlsanity.com/paper/2006.04439/) (2020)
- [Revisiting Active Perception](https://mlsanity.com/paper/1603.02729/) (2016)
- [Sample Factory: Egocentric 3D Control from Pixels at 100000 FPS with Asynchronous Reinforcement Learning](https://mlsanity.com/paper/2006.11751/) (2020)
- [Closed-form Continuous-time Neural Models](https://mlsanity.com/paper/2106.13898/) (2021)
- [DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling](https://mlsanity.com/paper/2105.12441/) (2021)
- [Gazeformer: Scalable, Effective and Fast Prediction of Goal-Directed Human Attention](https://mlsanity.com/paper/2303.15274/) (2023)
- [Unifying Top-down and Bottom-up Scanpath Prediction Using Transformers](https://mlsanity.com/paper/2303.09383/) (2023)
- [Aerial Gym Simulator: A Framework for Highly Parallelized Simulation of Aerial Robots](https://mlsanity.com/paper/2503.01471/) (2025)
- [ViSaRL: Visual Reinforcement Learning Guided by Human Saliency](https://mlsanity.com/paper/2403.10940/) (2024)
- [SUM: Saliency Unification through Mamba for Visual Attention Modeling](https://mlsanity.com/paper/2406.17815/) (2024)
- [Attention-based Active Visual Search for Mobile Robots](https://mlsanity.com/paper/1807.10744/) (2018)
- [Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agents](https://mlsanity.com/paper/2201.02569/) (2022)
- [Task-driven Compression for Collision Encoding based on Depth Images](https://mlsanity.com/paper/2309.05289/) (2023)
- [Semantically-driven Deep Reinforcement Learning for Inspection Path Planning](https://mlsanity.com/paper/2505.14443/) (2025)
- [Reinforcement Learning for Active Perception in Autonomous Navigation](https://mlsanity.com/paper/2602.01266/) (2026)
- [Integrating Three Mechanisms of Visual Attention for Active Visual Search](https://mlsanity.com/paper/1702.04292/) (2017)
- [Unified Attention Modeling for Efficient Free-Viewing and Visual Search via Shared Representations](https://mlsanity.com/paper/2506.02764/) (2025)

## Abstract (arXiv)

Human visual attention relies on structured scanpaths to efficiently process scenes, yet instilling this behavior into robot autonomy is in its infancy and hindered by the high,computational costs of existing predictive models. To address this, we introduce GazeLNN, a computationally lightweight,scanpath prediction model that leverages Liquid Neural Networks as its recurrent engine and employs MobileNetV3 for feature extraction. Operating auto-regressively, the architecture predicts sequential fixation heatmaps conditioned on the current visual stimulus and fixation history. Despite requiring only 0.61 GFLOPs, GazeLNN achieves state-of-the-art performance on the MIT Low Resolution dataset achieving 0.47 ScanMatch score. It outperforms existing recurrent baselines across diverse evaluation metrics, while reducing computational costs by 99.40% and accelerating inference by up to six times. To investigate the role of human attention modeling in robot autonomy and demonstrate the practical utility of this highly efficient architecture, we integrate GazeLNN into an active camera-robot control policy trained via Reinforcement Learning. This integration enables human-fixation-guided perception during autonomous navigation, validated through successful real-world deployments on an aerial robot.