Stochastic Occupancy Grid Map Prediction in Dynamic Scenes

Zhanteng Xie, Philip Dames
Proceedings of The 7th Conference on Robot Learning, PMLR 229:1686-1705, 2023.

Abstract

This paper presents two variations of a novel stochastic prediction algorithm that enables mobile robots to accurately and robustly predict the future state of complex dynamic scenes. The proposed algorithm uses a variational autoencoder to predict a range of possible future states of the environment. The algorithm takes full advantage of the motion of the robot itself, the motion of dynamic objects, and the geometry of static objects in the scene to improve prediction accuracy. Three simulated and real-world datasets collected by different robot models are used to demonstrate that the proposed algorithm is able to achieve more accurate and robust prediction performance than other prediction algorithms. Furthermore, a predictive uncertainty-aware planner is proposed to demonstrate the effectiveness of the proposed predictor in simulation and real-world navigation experiments. Implementations are open source at https://github.com/TempleRAIL/SOGMP.

Cite this Paper

BibTeX
@InProceedings{pmlr-v229-xie23a, title = {Stochastic Occupancy Grid Map Prediction in Dynamic Scenes}, author = {Xie, Zhanteng and Dames, Philip}, booktitle = {Proceedings of The 7th Conference on Robot Learning}, pages = {1686--1705}, year = {2023}, editor = {Tan, Jie and Toussaint, Marc and Darvish, Kourosh}, volume = {229}, series = {Proceedings of Machine Learning Research}, month = {06--09 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v229/xie23a/xie23a.pdf}, url = {https://proceedings.mlr.press/v229/xie23a.html}, abstract = {This paper presents two variations of a novel stochastic prediction algorithm that enables mobile robots to accurately and robustly predict the future state of complex dynamic scenes. The proposed algorithm uses a variational autoencoder to predict a range of possible future states of the environment. The algorithm takes full advantage of the motion of the robot itself, the motion of dynamic objects, and the geometry of static objects in the scene to improve prediction accuracy. Three simulated and real-world datasets collected by different robot models are used to demonstrate that the proposed algorithm is able to achieve more accurate and robust prediction performance than other prediction algorithms. Furthermore, a predictive uncertainty-aware planner is proposed to demonstrate the effectiveness of the proposed predictor in simulation and real-world navigation experiments. Implementations are open source at https://github.com/TempleRAIL/SOGMP.} }
Endnote
%0 Conference Paper %T Stochastic Occupancy Grid Map Prediction in Dynamic Scenes %A Zhanteng Xie %A Philip Dames %B Proceedings of The 7th Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2023 %E Jie Tan %E Marc Toussaint %E Kourosh Darvish %F pmlr-v229-xie23a %I PMLR %P 1686--1705 %U https://proceedings.mlr.press/v229/xie23a.html %V 229 %X This paper presents two variations of a novel stochastic prediction algorithm that enables mobile robots to accurately and robustly predict the future state of complex dynamic scenes. The proposed algorithm uses a variational autoencoder to predict a range of possible future states of the environment. The algorithm takes full advantage of the motion of the robot itself, the motion of dynamic objects, and the geometry of static objects in the scene to improve prediction accuracy. Three simulated and real-world datasets collected by different robot models are used to demonstrate that the proposed algorithm is able to achieve more accurate and robust prediction performance than other prediction algorithms. Furthermore, a predictive uncertainty-aware planner is proposed to demonstrate the effectiveness of the proposed predictor in simulation and real-world navigation experiments. Implementations are open source at https://github.com/TempleRAIL/SOGMP.
APA
Xie, Z. & Dames, P.. (2023). Stochastic Occupancy Grid Map Prediction in Dynamic Scenes. Proceedings of The 7th Conference on Robot Learning, in Proceedings of Machine Learning Research 229:1686-1705 Available from https://proceedings.mlr.press/v229/xie23a.html.

Related Material