Bayesian Generalized Kernel Inference for Terrain Traversability Mapping

Tixiao Shan, Jinkun Wang, Brendan Englot, Kevin Doherty
Proceedings of The 2nd Conference on Robot Learning, PMLR 87:829-838, 2018.

Abstract

We propose a new approach for traversability mapping with sparse lidar scans collected by ground vehicles, which leverages probabilistic inference to build descriptive terrain maps. Enabled by recent developments in sparse kernels, Bayesian generalized kernel inference is applied sequentially to the related problems of terrain elevation and traversability inference. The first inference step allows sparse data to support descriptive terrain modeling, and the second inference step relieves the burden typically associated with traversability computation. We explore the capabilities of the approach over a variety of data and terrain, demonstrating its suitability for online use in real-world applications.

Cite this Paper


BibTeX
@InProceedings{pmlr-v87-shan18a, title = {Bayesian Generalized Kernel Inference for Terrain Traversability Mapping}, author = {Shan, Tixiao and Wang, Jinkun and Englot, Brendan and Doherty, Kevin}, booktitle = {Proceedings of The 2nd Conference on Robot Learning}, pages = {829--838}, year = {2018}, editor = {Billard, Aude and Dragan, Anca and Peters, Jan and Morimoto, Jun}, volume = {87}, series = {Proceedings of Machine Learning Research}, month = {29--31 Oct}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v87/shan18a/shan18a.pdf}, url = {https://proceedings.mlr.press/v87/shan18a.html}, abstract = {We propose a new approach for traversability mapping with sparse lidar scans collected by ground vehicles, which leverages probabilistic inference to build descriptive terrain maps. Enabled by recent developments in sparse kernels, Bayesian generalized kernel inference is applied sequentially to the related problems of terrain elevation and traversability inference. The first inference step allows sparse data to support descriptive terrain modeling, and the second inference step relieves the burden typically associated with traversability computation. We explore the capabilities of the approach over a variety of data and terrain, demonstrating its suitability for online use in real-world applications. } }
Endnote
%0 Conference Paper %T Bayesian Generalized Kernel Inference for Terrain Traversability Mapping %A Tixiao Shan %A Jinkun Wang %A Brendan Englot %A Kevin Doherty %B Proceedings of The 2nd Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2018 %E Aude Billard %E Anca Dragan %E Jan Peters %E Jun Morimoto %F pmlr-v87-shan18a %I PMLR %P 829--838 %U https://proceedings.mlr.press/v87/shan18a.html %V 87 %X We propose a new approach for traversability mapping with sparse lidar scans collected by ground vehicles, which leverages probabilistic inference to build descriptive terrain maps. Enabled by recent developments in sparse kernels, Bayesian generalized kernel inference is applied sequentially to the related problems of terrain elevation and traversability inference. The first inference step allows sparse data to support descriptive terrain modeling, and the second inference step relieves the burden typically associated with traversability computation. We explore the capabilities of the approach over a variety of data and terrain, demonstrating its suitability for online use in real-world applications.
APA
Shan, T., Wang, J., Englot, B. & Doherty, K.. (2018). Bayesian Generalized Kernel Inference for Terrain Traversability Mapping. Proceedings of The 2nd Conference on Robot Learning, in Proceedings of Machine Learning Research 87:829-838 Available from https://proceedings.mlr.press/v87/shan18a.html.

Related Material