# Visuospatial navigation from the bottom-up: without vestibular integration, distance prediction, or maps

arXiv: https://arxiv.org/abs/2407.13535 · HTML: https://mlsanity.com/paper/2407.13535/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 104 references that are in the map.
- First posted on arXiv 18 Jul 2024.

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

- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Transformers in Vision: A Survey](https://mlsanity.com/paper/2101.01169/) (2021)
- [ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders](https://mlsanity.com/paper/2301.00808/) (2023)
- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)
- [Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuning](https://mlsanity.com/paper/1708.02596/) (2017)
- [Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future](https://mlsanity.com/paper/2001.07092/) (2020)
- [Emergence of grid-like representations by training recurrent neural networks to perform spatial localization](https://mlsanity.com/paper/1803.07770/) (2018)
- [Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey](https://mlsanity.com/paper/2110.01411/) (2021)
- [ClipUp: A Simple and Powerful Optimizer for Distribution-based Policy Evolution](https://mlsanity.com/paper/2008.02387/) (2020)
- [Robots as Powerful Allies for the Study of Embodied Cognition from the Bottom Up](https://mlsanity.com/paper/1801.04819/) (2018)
- [Geometrical Structure of Bifurcations during Spatial Decision-Making](https://mlsanity.com/paper/2307.05837/) (2023)

## Abstract (arXiv)

Navigation is believed to be controlled by at least two partially dissociable systems in the brain. The cognitive map informs an organism of its location and bearing, updated by integrating vestibular self-motion or predicting distances to landmarks. Route-based navigation, on the other hand, directly evaluate sequential movement decisions from immediate percepts. Here we demonstrate the sufficiency of visual route-based decision-making in a classic open field navigation task often assumed to require a cognitive map. Three distinct strategies emerge to robustly navigate to a hidden goal, each conferring contextual tradeoffs analyzed at both neural and behavioral scales, as well as qualitatively aligning with behavior observed across the biological spectrum. We propose reframing navigation from the bottom-up, through an egocentric episodic perspective without assuming online access to computationally expensive top-down representations, to better explain behavior under energetic or attentional constraints.