# Emergence of Maps in the Memories of Blind Navigation Agents

arXiv: https://arxiv.org/abs/2301.13261 · HTML: https://mlsanity.com/paper/2301.13261/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 80 references that are in the map.
- First posted on arXiv 30 Jan 2023.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [Matterport3D: Learning from RGB-D Data in Indoor Environments](https://mlsanity.com/paper/1709.06158/) (2017)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Habitat: A Platform for Embodied AI Research](https://mlsanity.com/paper/1904.01201/) (2019)
- [The Replica Dataset: A Digital Replica of Indoor Spaces](https://mlsanity.com/paper/1906.05797/) (2019)
- [A Generalist Agent](https://mlsanity.com/paper/2205.06175/) (2022)
- [Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI](https://mlsanity.com/paper/2109.08238/) (2021)
- [On Evaluation of Embodied Navigation Agents](https://mlsanity.com/paper/1807.06757/) (2018)
- [Habitat 2.0: Training Home Assistants to Rearrange their Habitat](https://mlsanity.com/paper/2106.14405/) (2021)
- [Gibson Env: Real-World Perception for Embodied Agents](https://mlsanity.com/paper/1808.10654/) (2018)
- [DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Frames](https://mlsanity.com/paper/1911.00357/) (2019)
- [Emergent Tool Use From Multi-Agent Autocurricula](https://mlsanity.com/paper/1909.07528/) (2019)
- [An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution](https://mlsanity.com/paper/1807.03247/) (2018)
- [Efficient Object Localization Using Convolutional Networks](https://mlsanity.com/paper/1411.4280/) (2014)
- [Simple but Effective: CLIP Embeddings for Embodied AI](https://mlsanity.com/paper/2111.09888/) (2021)
- [Rearrangement: A Challenge for Embodied AI](https://mlsanity.com/paper/2011.01975/) (2020)
- [The Surprising Creativity of Digital Evolution: A Collection of Anecdotes from the Evolutionary Computation and Artificial Life Research Communities](https://mlsanity.com/paper/1803.03453/) (2018)
- [RobustNav: Towards Benchmarking Robustness in Embodied Navigation](https://mlsanity.com/paper/2106.04531/) (2021)
- [Emergence of grid-like representations by training recurrent neural networks to perform spatial localization](https://mlsanity.com/paper/1803.07770/) (2018)
- [Is Mapping Necessary for Realistic PointGoal Navigation?](https://mlsanity.com/paper/2206.00997/) (2022)
- [No Training Required: Exploring Random Encoders for Sentence Classification](https://mlsanity.com/paper/1901.10444/) (2019)
- [Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?](https://mlsanity.com/paper/1912.06321/) (2019)
- [Estimating Uncertain Spatial Relationships in Robotics](https://mlsanity.com/paper/1304.3111/) (2013)
- [Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal](https://mlsanity.com/paper/1807.05211/) (2018)
- [What do navigation agents learn about their environment?](https://mlsanity.com/paper/2206.08500/) (2022)

## Built on by (most cited first, 30 of 33)

- [Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes](https://mlsanity.com/paper/2408.03539/) (2024)
- [GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation](https://mlsanity.com/paper/2404.06609/) (2024)
- [Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion](https://mlsanity.com/paper/2401.17583/) (2024)
- [HI-TOM: A Benchmark for Evaluating Higher-Order Theory of Mind Reasoning in Large Language Models](https://mlsanity.com/paper/2310.16755/) (2023)
- [Learning Robust Autonomous Navigation and Locomotion for Wheeled-Legged Robots](https://mlsanity.com/paper/2405.01792/) (2024)
- [Resilient Legged Local Navigation: Learning to Traverse with Compromised Perception End-to-End](https://mlsanity.com/paper/2310.03581/) (2023)
- [Refining Minimax Regret for Unsupervised Environment Design](https://mlsanity.com/paper/2402.12284/) (2024)
- [Planning in a recurrent neural network that plays Sokoban](https://mlsanity.com/paper/2407.15421/) (2024)
- [Object Goal Navigation with Recursive Implicit Maps](https://mlsanity.com/paper/2308.05602/) (2023)
- [Navigates Like Me: Understanding How People Evaluate Human-Like AI in Video Games](https://mlsanity.com/paper/2303.02160/) (2023)
- [Spatially-Enhanced Recurrent Memory for Long-Range Mapless Navigation via End-to-End Reinforcement Learning](https://mlsanity.com/paper/2506.05997/) (2025)
- [MANGO: A Benchmark for Evaluating Mapping and Navigation Abilities of Large Language Models](https://mlsanity.com/paper/2403.19913/) (2024)
- [What Does it Mean for a Neural Network to Learn a "World Model"?](https://mlsanity.com/paper/2507.21513/) (2025)
- [Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction](https://mlsanity.com/paper/2306.03857/) (2023)
- [Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning](https://mlsanity.com/paper/2307.03486/) (2023)
- [Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets](https://mlsanity.com/paper/2410.01779/) (2024)
- [Emergent World Representations in OpenVLA](https://mlsanity.com/paper/2509.24559/) (2025)
- [Optimal foraging strategies can be learned](https://mlsanity.com/paper/2303.06050/) (2023)
- [Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)](https://mlsanity.com/paper/2505.17323/) (2025)
- [Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN](https://mlsanity.com/paper/2506.10138/) (2025)
- [Notes-to-Self: Scratchpad Augmented VLAs for Memory Dependent Manipulation Tasks](https://mlsanity.com/paper/2602.21013/) (2026)
- [Kinaema: a recurrent sequence model for memory and pose in motion](https://mlsanity.com/paper/2510.20261/) (2025)
- [Learning to Terminate in Object Navigation](https://mlsanity.com/paper/2309.16164/) (2023)
- [Prompt-responsive Object Retrieval with Memory-augmented Student-Teacher Learning](https://mlsanity.com/paper/2505.02232/) (2025)
- [Building spatial world models from sparse transitional episodic memories](https://mlsanity.com/paper/2505.13696/) (2025)
- [Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning](https://mlsanity.com/paper/2505.14806/) (2025)
- [ProDapt: Proprioceptive Adaptation using Long-term Memory Diffusion](https://mlsanity.com/paper/2503.00193/) (2025)
- [Shared Control of Holonomic Wheelchairs through Reinforcement Learning](https://mlsanity.com/paper/2507.17055/) (2025)
- [Remembering the Markov Property in Cooperative MARL](https://mlsanity.com/paper/2507.18333/) (2025)
- [Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial Reasoning](https://mlsanity.com/paper/2509.00465/) (2025)

## Abstract (arXiv)

Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial intelligence (AI) navigation agents -- also build implicit (or 'mental') maps. A positive answer to this question would (a) explain the surprising phenomenon in recent literature of ostensibly map-free neural-networks achieving strong performance, and (b) strengthen the evidence of mapping as a fundamental mechanism for navigation by intelligent embodied agents, whether they be biological or artificial. Unlike animal navigation, we can judiciously design the agent's perceptual system and control the learning paradigm to nullify alternative navigation mechanisms. Specifically, we train 'blind' agents -- with sensing limited to only egomotion and no other sensing of any kind -- to perform PointGoal navigation ('go to Delta x, Delta y') via reinforcement learning. Our agents are composed of navigation-agnostic components (fully-connected and recurrent neural networks), and our experimental setup provides no inductive bias towards mapping. Despite these harsh conditions, we find that blind agents are (1) surprisingly effective navigators in new environments (~95% success); (2) they utilize memory over long horizons (remembering ~1,000 steps of past experience in an episode); (3) this memory enables them to exhibit intelligent behavior (following walls, detecting collisions, taking shortcuts); (4) there is emergence of maps and collision detection neurons in the representations of the environment built by a blind agent as it navigates; and (5) the emergent maps are selective and task dependent (e.g. the agent 'forgets' exploratory detours). Overall, this paper presents no new techniques for the AI audience, but a surprising finding, an insight, and an explanation.