LTS-NET: End-to-end Unsupervised Learning of Long-Term 3D Stable objects

no code implementations • 9 Jan 2023 • Ibrahim Hroob, Sergi Molina, Riccardo Polvara, Grzegorz Cielniak, Marc Hanheide

In this research, we present an end-to-end data-driven pipeline for determining the long-term stability status of objects within a given environment, specifically distinguishing between static and dynamic objects.

Classification regression

Collection and Evaluation of a Long-Term 4D Agri-Robotic Dataset

no code implementations • 25 Nov 2022 • Riccardo Polvara, Sergi Molina Mellado, Ibrahim Hroob, Grzegorz Cielniak, Marc Hanheide

Long-term autonomy is one of the most demanded capabilities looked into a robot.

Autonomous Quadrotor Landing using Deep Reinforcement Learning

no code implementations • 11 Sep 2017 • Riccardo Polvara, Massimiliano Patacchiola, Sanjay Sharma, Jian Wan, Andrew Manning, Robert Sutton, Angelo Cangelosi

Landing an unmanned aerial vehicle (UAV) on a ground marker is an open problem despite the effort of the research community.

reinforcement-learning Reinforcement Learning (RL)

Monocular Visual Odometry for an Unmanned Sea-Surface Vehicle

no code implementations • 14 Jul 2017 • George Terzakis, Riccardo Polvara, Sanjay Sharma, Phil Culverhouse, Robert Sutton

We tackle the problem of localizing an autonomous sea-surface vehicle in river estuarine areas using monocular camera and angular velocity input from an inertial sensor.

Monocular Visual Odometry Simultaneous Localization and Mapping +1