# HouseExpo: A Large-scale 2D Indoor Layout Dataset for Learning-based Algorithms on Mobile Robots

arXiv: https://arxiv.org/abs/1903.09845 · HTML: https://mlsanity.com/paper/1903.09845/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2019.

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

- [FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations](https://mlsanity.com/paper/2507.07644/) (2025)
- [Joint Learning of Reward Machines and Policies in Environments with Partially Known Semantics](https://mlsanity.com/paper/2204.11833/) (2022)
- [PathBench: A Benchmarking Platform for Classical and Learned Path Planning Algorithms](https://mlsanity.com/paper/2105.01777/) (2021)
- [Map completion from partial observation using the global structure of multiple environmental maps](https://mlsanity.com/paper/2103.09071/) (2021)
- [Waypoint Planning Networks](https://mlsanity.com/paper/2105.00312/) (2021)
- [Integrating Deep Reinforcement and Supervised Learning to Expedite Indoor Mapping](https://mlsanity.com/paper/2109.08490/) (2021)
- [Tracking and Planning with Spatial World Models](https://mlsanity.com/paper/2201.10335/) (2022)
- [Toward an Idiomatic Framework for Cognitive Robotics](https://mlsanity.com/paper/2111.13027/) (2021)
- [FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interests](https://mlsanity.com/paper/2309.03100/) (2023)
- [Contrastive Diffusion Guidance for Spatial Inverse Problems](https://mlsanity.com/paper/2509.26489/) (2025)
- [MATT-Diff: Multimodal Active Target Tracking by Diffusion Policy](https://mlsanity.com/paper/2511.11931/) (2025)
- [UPath: Universal Planner Across Topological Heterogeneity For Grid-Based Pathfinding](https://mlsanity.com/paper/2602.23789/) (2026)
- [A Probabilistic Programming Idiom for Active Knowledge Search](https://mlsanity.com/paper/2202.09555/) (2022)
- [Systematic Comparison of Path Planning Algorithms using PathBench](https://mlsanity.com/paper/2203.03092/) (2022)
- [2D Floor Plan Segmentation Based on Down-sampling](https://mlsanity.com/paper/2303.13798/) (2023)
- [SenseExpo: Spatial Exploration and Navigation via Scene Estimation from Expeditious Predictive Operators](https://mlsanity.com/paper/2503.16000/) (2025)
- [Mapping at First Sense: A Lightweight Neural Network-Based Indoor Structures Prediction Method for Robot Autonomous Exploration](https://mlsanity.com/paper/2504.04061/) (2025)
- [GAN-SLAM: Real-Time GAN Aided Floor Plan Creation Through SLAM](https://mlsanity.com/paper/2504.19653/) (2025)
- [Transformation & Translation Occupancy Grid Mapping: 2-Dimensional Deep Learning Refined SLAM](https://mlsanity.com/paper/2504.19654/) (2025)
- [Verbalized Algorithms: Classical Algorithms are All You Need (Mostly)](https://mlsanity.com/paper/2509.08150/) (2025)
- [Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking](https://mlsanity.com/paper/2604.03404/) (2026)
- [Discrete Langevin-Inspired Posterior Sampling](https://mlsanity.com/paper/2605.09302/) (2026)
- [Neural Navigation Functions for Zero-Shot Generalizable Motion Planning](https://mlsanity.com/paper/2606.03756/) (2026)

## Abstract (arXiv)

As one of the most promising areas, mobile robots draw much attention these years. Current work in this field is often evaluated in a few manually designed scenarios, due to the lack of a common experimental platform. Meanwhile, with the recent development of deep learning techniques, some researchers attempt to apply learning-based methods to mobile robot tasks, which requires a substantial amount of data. To satisfy the underlying demand, in this paper we build HouseExpo, a large-scale indoor layout dataset containing 35,126 2D floor plans including 252,550 rooms in total. Together we develop Pseudo-SLAM, a lightweight and efficient simulation platform to accelerate the data generation procedure, thereby speeding up the training process. In our experiments, we build models to tackle obstacle avoidance and autonomous exploration from a learning perspective in simulation as well as real-world experiments to verify the effectiveness of our simulator and dataset. All the data and codes are available online and we hope HouseExpo and Pseudo-SLAM can feed the need for data and benefits the whole community.