Integrating Deep Reinforcement and Supervised Learning to Expedite Indoor Mapping

no code implementations • 17 Sep 2021 • Elchanan Zwecher, Eran Iceland, Sean R. Levy, Shmuel Y. Hayoun, Oren Gal, Ariel Barel

Each one helps to improve the decision making through use of the learned structural statistics of the environment, and both, being realized as neural networks, ensure a constant calculation time.

Decision Making Motion Planning

Deep-Learning-Aided Path Planning and Map Construction for Expediting Indoor Mapping

no code implementations • 3 Nov 2020 • Elchanan Zwecher, Eran Iceland, Shmuel Y. Hayoun, Ahavatya Revivo, Sean R. Levy, Ariel Barel

When the prediction is integrated in both path planning and map construction processes it is shown that the mapping time may in some cases be cut by over 50%.

Motion Planning