The goal of LEARNER is to expand the applicability of mobile robotic platforms and provide a hybrid solution between model-based and AI-based approaches for addressing current challenges in mobile SLAM and Path Planning, specifically targeting dynamic conditions and constantly changing environments populated by humans
Introducing social skills in Path Planning by considering the humans' presence, dynamics, actions, and emotional states in the robot's internal map representation.
Developing robust SLAM and Path Planning modules that will enhance the existing techniques for coping with structural and conditional changes in the environment, as well as handling the human's dynamic presence.
Developing robust SLAM and Path Planning modules that will enhance the existing techniques for coping with structural and conditional changes in the environment, as well as handling the human's dynamic presence.
Integrating and assessing the developed framework on a mobile robot under challenging conditions that resemble a physical environment defined by user requirements.
LEARNER will offer three main services that combined will conclude a complete middleware package that can be effectively deployed, with minimum reconfiguration, in various challenging areas, such as industrial, mining, or construction sites
Automating data extraction for self-supervised learning
Combining deep learning and model-based approaches
Navigating under social constrains in dynamic environmental conditions
The research for developing LEARNER is conducted at Mechatronics and Systems Automation Lab, Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece