# DR-SPAAM: A Spatial-Attention and Auto-regressive Model for Person Detection in 2D Range Data

arXiv: https://arxiv.org/abs/2004.14079 · HTML: https://mlsanity.com/paper/2004.14079/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Apr 2020.

## Built on by (most cited first, 19 of 19)

- [Intention Aware Robot Crowd Navigation with Attention-Based Interaction Graph](https://mlsanity.com/paper/2203.01821/) (2022)
- [Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation](https://mlsanity.com/paper/2401.12275/) (2024)
- [SoNIC: Safe Social Navigation with Adaptive Conformal Inference and Constrained Reinforcement Learning](https://mlsanity.com/paper/2407.17460/) (2024)
- [HEIGHT: Heterogeneous Interaction Graph Transformer for Robot Navigation in Crowded and Constrained Environments](https://mlsanity.com/paper/2411.12150/) (2024)
- [2D vs. 3D LiDAR-based Person Detection on Mobile Robots](https://mlsanity.com/paper/2106.11239/) (2021)
- [GSON: A Group-based Social Navigation Framework with Large Multimodal Model](https://mlsanity.com/paper/2409.18084/) (2024)
- [Towards Generalizable Safety in Crowd Navigation via Conformal Uncertainty Handling](https://mlsanity.com/paper/2508.05634/) (2025)
- [Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Study](https://mlsanity.com/paper/2108.01495/) (2021)
- [Pedestrian-Robot Interactions on Autonomous Crowd Navigation: Reactive Control Methods and Evaluation Metrics](https://mlsanity.com/paper/2208.02121/) (2022)
- [COLSON: Controllable Learning-Based Social Navigation via Diffusion-Based Reinforcement Learning](https://mlsanity.com/paper/2503.13934/) (2025)
- [The Un-Kidnappable Robot: Acoustic Localization of Sneaking People](https://mlsanity.com/paper/2310.03743/) (2023)
- [What we see and What we don't see: Imputing Occluded Crowd Structures from Robot Sensing](https://mlsanity.com/paper/2109.08494/) (2021)
- [Incremental Residual Reinforcement Learning Toward Real-World Learning for Social Navigation](https://mlsanity.com/paper/2604.07945/) (2026)
- [Belief Aided Navigation using Bayesian Reinforcement Learning for Avoiding Humans in Blind Spots](https://mlsanity.com/paper/2403.10105/) (2024)
- [Structured Graph Network for Constrained Robot Crowd Navigation with Low Fidelity Simulation](https://mlsanity.com/paper/2405.16830/) (2024)
- [Person Segmentation and Action Classification for Multi-Channel Hemisphere Field of View LiDAR Sensors](https://mlsanity.com/paper/2411.11151/) (2024)
- [Real-Time 2D LiDAR Object Detection Using Three-Frame RGB Scan Encoding](https://mlsanity.com/paper/2602.02167/) (2026)
- [KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic Feasibility](https://mlsanity.com/paper/2606.12042/) (2026)
- [Navigating the Proximity-Safety Balance: Constraint Decomposition for Human Following in Pedestrian Crowds](https://mlsanity.com/paper/2608.10056/) (2026)

## Abstract (arXiv)

Detecting persons using a 2D LiDAR is a challenging task due to the low information content of 2D range data. To alleviate the problem caused by the sparsity of the LiDAR points, current state-of-the-art methods fuse multiple previous scans and perform detection using the combined scans. The downside of such a backward looking fusion is that all the scans need to be aligned explicitly, and the necessary alignment operation makes the whole pipeline more expensive -- often too expensive for real-world applications. In this paper, we propose a person detection network which uses an alternative strategy to combine scans obtained at different times. Our method, Distance Robust SPatial Attention and Auto-regressive Model (DR-SPAAM), follows a forward looking paradigm. It keeps the intermediate features from the backbone network as a template and recurrently updates the template when a new scan becomes available. The updated feature template is in turn used for detecting persons currently in the scene. On the DROW dataset, our method outperforms the existing state-of-the-art, while being approximately four times faster, running at 87.2 FPS on a laptop with a dedicated GPU and at 22.6 FPS on an NVIDIA Jetson AGX embedded GPU. We release our code in PyTorch and a ROS node including pre-trained models.