Bayesian Hilbert Maps for Dynamic Continuous Occupancy Mapping

Ransalu Senanayake, Fabio Ramos
Proceedings of the 1st Annual Conference on Robot Learning, PMLR 78:458-471, 2017.

Abstract

Hilbert mapping is an efficient technique for building continuous occupancy maps from depth sensors such as LiDAR in static environments. However, to make the map adaptable to dynamic environments, its parameters need to be learned automatically. In this paper, we take a variational Bayesian approach to this problem, thus eliminating the regularization term typically adjusted heuristically. We extend the proposed model to learn long-term occupancy maps in dynamic environments in a sequential fashion, demonstrating the power of kernel methods to capture abstract nonlinear patterns and Bayesian learning to construct sophisticated models. Experiments conducted in environments with moving vehicles show that the proposed approach has a significant speed improvement over the state-of-the-art techniques and maintain a similar or better accuracy. We also discuss the robustness against occlusions and various theoretical and empirical aspects of building long-term dynamic occupancy maps.

Cite this Paper

BibTeX
@InProceedings{pmlr-v78-senanayake17a, title = {Bayesian Hilbert Maps for Dynamic Continuous Occupancy Mapping}, author = {Senanayake, Ransalu and Ramos, Fabio}, booktitle = {Proceedings of the 1st Annual Conference on Robot Learning}, pages = {458--471}, year = {2017}, editor = {Levine, Sergey and Vanhoucke, Vincent and Goldberg, Ken}, volume = {78}, series = {Proceedings of Machine Learning Research}, month = {13--15 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v78/senanayake17a/senanayake17a.pdf}, url = {https://proceedings.mlr.press/v78/senanayake17a.html}, abstract = {Hilbert mapping is an efficient technique for building continuous occupancy maps from depth sensors such as LiDAR in static environments. However, to make the map adaptable to dynamic environments, its parameters need to be learned automatically. In this paper, we take a variational Bayesian approach to this problem, thus eliminating the regularization term typically adjusted heuristically. We extend the proposed model to learn long-term occupancy maps in dynamic environments in a sequential fashion, demonstrating the power of kernel methods to capture abstract nonlinear patterns and Bayesian learning to construct sophisticated models. Experiments conducted in environments with moving vehicles show that the proposed approach has a significant speed improvement over the state-of-the-art techniques and maintain a similar or better accuracy. We also discuss the robustness against occlusions and various theoretical and empirical aspects of building long-term dynamic occupancy maps.} }
Endnote
%0 Conference Paper %T Bayesian Hilbert Maps for Dynamic Continuous Occupancy Mapping %A Ransalu Senanayake %A Fabio Ramos %B Proceedings of the 1st Annual Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2017 %E Sergey Levine %E Vincent Vanhoucke %E Ken Goldberg %F pmlr-v78-senanayake17a %I PMLR %P 458--471 %U https://proceedings.mlr.press/v78/senanayake17a.html %V 78 %X Hilbert mapping is an efficient technique for building continuous occupancy maps from depth sensors such as LiDAR in static environments. However, to make the map adaptable to dynamic environments, its parameters need to be learned automatically. In this paper, we take a variational Bayesian approach to this problem, thus eliminating the regularization term typically adjusted heuristically. We extend the proposed model to learn long-term occupancy maps in dynamic environments in a sequential fashion, demonstrating the power of kernel methods to capture abstract nonlinear patterns and Bayesian learning to construct sophisticated models. Experiments conducted in environments with moving vehicles show that the proposed approach has a significant speed improvement over the state-of-the-art techniques and maintain a similar or better accuracy. We also discuss the robustness against occlusions and various theoretical and empirical aspects of building long-term dynamic occupancy maps.
APA
Senanayake, R. & Ramos, F.. (2017). Bayesian Hilbert Maps for Dynamic Continuous Occupancy Mapping. Proceedings of the 1st Annual Conference on Robot Learning, in Proceedings of Machine Learning Research 78:458-471 Available from https://proceedings.mlr.press/v78/senanayake17a.html.

Related Material