Machine Learning for Modeling Spatiotemporal Uncertainty in Urban Environments

While advancing robots towards full autonomy, it is important to minimize deleterious effects on human and infrastructure. To achieve this, it is essential for robots to understand their surrounding. The surrounding can be represented as a metric map. However, if the environment is assumed to be static and deterministic, it is challenging for the decision-making algorithms to effectively account for the changing and unpredictable nature of the real-world urban environments with pedestrians and vehicles. Therefore, it is essential to model uncertainties in dynamic environments. In this talk, various machine learning techniques for mapping environments that change in both space and time are discussed. Since these maps represent uncertainty, they can then be used for risk-aware decision-making.

June 27, 2019 (Thursday)
Room 205, Building E, Karlovo nám. 13


Ransalu Senanayake

Ransalu is a postdoctoral scholar at the Stanford Intelligent Systems Laboratory (SISL), working with Prof. Mykel Kochenderfer. He completed his PhD in Robot Learning and Machine Learning in Prof. Fabio Ramos' group at the School of Computer Science in the University of Sydney. In his research Ransalu has been developing data-efficient robotic mapping techniques that capture uncertainty in dynamic environment.