# Motion Estimation in Occupancy Grid Maps in Stationary Settings Using Recurrent Neural Networks

arXiv: https://arxiv.org/abs/1909.11387 · HTML: https://mlsanity.com/paper/1909.11387/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [PillarSegNet: Pillar-based Semantic Grid Map Estimation using Sparse LiDAR Data](https://mlsanity.com/paper/2105.04169/) (2021)
- [Unsupervised 4D LiDAR Moving Object Segmentation in Stationary Settings with Multivariate Occupancy Time Series](https://mlsanity.com/paper/2212.14750/) (2022)
- [Allo-centric Occupancy Grid Prediction for Urban Traffic Scene Using Video Prediction Networks](https://mlsanity.com/paper/2301.04454/) (2023)
- [Gesture Recognition with Keypoint and Radar Stream Fusion for Automated Vehicles](https://mlsanity.com/paper/2302.09998/) (2023)
- [Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Time](https://mlsanity.com/paper/2306.06126/) (2023)
- [ROSA-RL: Uncertainty-Aware Roundabout Optimized Speed Advisory with Reinforcement Learning](https://mlsanity.com/paper/2606.16558/) (2026)

## Abstract (arXiv)

In this work, we tackle the problem of modeling the vehicle environment as dynamic occupancy grid map in complex urban scenarios using recurrent neural networks. Dynamic occupancy grid maps represent the scene in a bird's eye view, where each grid cell contains the occupancy probability and the two dimensional velocity. As input data, our approach relies on measurement grid maps, which contain occupancy probabilities, generated with lidar measurements. Given this configuration, we propose a recurrent neural network architecture to predict a dynamic occupancy grid map, i.e. filtered occupancy and velocity of each cell, by using a sequence of measurement grid maps. Our network architecture contains convolutional long-short term memories in order to sequentially process the input, makes use of spatial context, and captures motion. In the evaluation, we quantify improvements in estimating the velocity of braking and turning vehicles compared to the state-of-the-art. Additionally, we demonstrate that our approach provides more consistent velocity estimates for dynamic objects, as well as, less erroneous velocity estimates in static area.