Roadmap Learning for Probabilistic Occupancy Maps With Topology-Informed Growing Neural Gas
Roadmap Learning for Probabilistic Occupancy Maps With Topology-Informed Growing Neural Gas
复制标题
具有拓扑信息的生长神经气体的概率占用图的路线图学习
DOI:
10.1109/lra.2021.3068886
复制
发表时间:
2021
影响因子:
5.2
通讯作者:
Hollinger, Geoffrey A.
中科院分区:
文献类型:
--
作者:
Saroya, Manish;Best, Graeme;Hollinger, Geoffrey A.
We address the problem of generating navigation roadmaps for uncertain and cluttered environments represented with probabilistic occupancy maps. A key challenge is to generate roadmaps that provide connectivity through tight passages and paths around uncertain obstacles. We propose the topology-informed growing neural gas algorithm that leverages estimates of probabilistic topological structures computed using persistent homology theory. These topological structure estimates inform the random sampling distribution to focus the roadmap learning on challenging regions of the environment that have not yet been learned correctly. We present experiments for three real-world indoor point-cloud datasets represented as Hilbert maps. Our method outperforms baseline methods in terms of graph connectivity, path solution quality, and search efficiency. Compared to a much denser PRM*, our method achieves similar performance while enabling a 27× faster query time for shortest-path searches.
DOI:
--
发表时间:
2016
期刊:
IEEE International Conference on Robotics and Automation
影响因子:
--
作者:
Florian T. Pokorny;Ken Goldberg;D. Kragic
通讯作者:
D. Kragic
DOI:
10.1109/iros45743.2020.9341040
发表时间:
2020
期刊:
IEEE International Conference on Intelligent Robots and Systems
影响因子:
--
作者:
McCammon, Seth;Jones, Dylan;Hollinger, Geoffrey A.
通讯作者:
Hollinger, Geoffrey A.
影响因子:
8.3
作者:
Reid, William;Fitch, Robert;Sukkarieh, Salah
通讯作者:
Sukkarieh, Salah