# EgoMap: Projective mapping and structured egocentric memory for Deep RL

arXiv: https://arxiv.org/abs/2002.02286 · HTML: https://mlsanity.com/paper/2002.02286/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jan 2020.

## Built on by (most cited first, 23 of 23)

- [GridMM: Grid Memory Map for Vision-and-Language Navigation](https://mlsanity.com/paper/2307.12907/) (2023)
- [Memory-Augmented Reinforcement Learning for Image-Goal Navigation](https://mlsanity.com/paper/2101.05181/) (2021)
- [Multi-Object Navigation with dynamically learned neural implicit representations](https://mlsanity.com/paper/2210.05129/) (2022)
- [Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents](https://mlsanity.com/paper/2110.05769/) (2021)
- [NavAgent: Multi-scale Urban Street View Fusion For UAV Embodied Vision-and-Language Navigation](https://mlsanity.com/paper/2411.08579/) (2024)
- [Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation](https://mlsanity.com/paper/2107.06011/) (2021)
- [End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon](https://mlsanity.com/paper/2309.16634/) (2023)
- [Deep KKL: Data-driven Output Prediction for Non-Linear Systems](https://mlsanity.com/paper/2103.12443/) (2021)
- [Flow Equivariant World Models: Memory for Partially Observed Dynamic Environments](https://mlsanity.com/paper/2601.01075/) (2026)
- [An in-depth experimental study of sensor usage and visual reasoning of robots navigating in real environments](https://mlsanity.com/paper/2111.14666/) (2021)
- [Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction](https://mlsanity.com/paper/2306.03857/) (2023)
- [Graph augmented Deep Reinforcement Learning in the GameRLand3D environment](https://mlsanity.com/paper/2112.11731/) (2021)
- [Learning to navigate efficiently and precisely in real environments](https://mlsanity.com/paper/2401.14349/) (2024)
- [Godot Reinforcement Learning Agents](https://mlsanity.com/paper/2112.03636/) (2021)
- [Feudal Networks for Visual Navigation](https://mlsanity.com/paper/2402.12498/) (2024)
- [Reasoning in visual navigation of end-to-end trained agents: a dynamical systems approach](https://mlsanity.com/paper/2503.08306/) (2025)
- [RANa: Retrieval-Augmented Navigation](https://mlsanity.com/paper/2504.03524/) (2025)
- [What does really matter in image goal navigation?](https://mlsanity.com/paper/2507.01667/) (2025)
- [Kinaema: a recurrent sequence model for memory and pose in motion](https://mlsanity.com/paper/2510.20261/) (2025)
- [Symmetry-aware Neural Architecture for Embodied Visual Navigation](https://mlsanity.com/paper/2112.09515/) (2021)
- [Zero-BEV: Zero-shot Projection of Any First-Person Modality to BEV Maps](https://mlsanity.com/paper/2402.13848/) (2024)
- [FeudalNav: A Simple Framework for Visual Navigation](https://mlsanity.com/paper/2602.06974/) (2026)
- [MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance](https://mlsanity.com/paper/2602.17930/) (2026)

## Abstract (arXiv)

Tasks involving localization, memorization and planning in partially observable 3D environments are an ongoing challenge in Deep Reinforcement Learning. We present EgoMap, a spatially structured neural memory architecture. EgoMap augments a deep reinforcement learning agent's performance in 3D environments on challenging tasks with multi-step objectives. The EgoMap architecture incorporates several inductive biases including a differentiable inverse projection of CNN feature vectors onto a top-down spatially structured map. The map is updated with ego-motion measurements through a differentiable affine transform. We show this architecture outperforms both standard recurrent agents and state of the art agents with structured memory. We demonstrate that incorporating these inductive biases into an agent's architecture allows for stable training with reward alone, circumventing the expense of acquiring and labelling expert trajectories. A detailed ablation study demonstrates the impact of key aspects of the architecture and through extensive qualitative analysis, we show how the agent exploits its structured internal memory to achieve higher performance.