Timezone: »

 
Poster
Spatio-Temporal Hilbert Maps for Continuous Occupancy Representation in Dynamic Environments
Ransalu Senanayake · Lionel Ott · Simon O'Callaghan · Fabio Ramos

Tue Dec 06 09:00 AM -- 12:30 PM (PST) @ Area 5+6+7+8 #153
in Tuesday Posters »

We consider the problem of building continuous occupancy representations in dynamic environments for robotics applications. The problem has hardly been discussed previously due to the complexity of patterns in urban environments, which have both spatial and temporal dependencies. We address the problem as learning a kernel classifier on an efficient feature space. The key novelty of our approach is the incorporation of variations in the time domain into the spatial domain. We propose a method to propagate motion uncertainty into the kernel using a hierarchical model. The main benefit of this approach is that it can directly predict the occupancy state of the map in the future from past observations, being a valuable tool for robot trajectory planning under uncertainty. Our approach preserves the main computational benefits of static Hilbert maps — using stochastic gradient descent for fast optimization of model parameters and incremental updates as new data are captured. Experiments conducted in road intersections of an urban environment demonstrated that spatio-temporal Hilbert maps can accurately model changes in the map while outperforming other techniques on various aspects.

Keywords: Kernel Methods · Online Learning · (Other) Classification · (Other) Applications · (Other) Machine Learning Topics · (Other) Robotics and Control

Author Information

Ransalu Senanayake (The University of Sydney)

I am a Computer Science PhD student at the University of Sydney specializing in Machine Learning and Robotics.

Lionel Ott (The University of Sydney)
Simon O'Callaghan (NICTA)
Fabio Ramos (The University of Sydney)

More from the Same Authors