M
Mohamed El-Shamouty
Researcher at Fraunhofer Society
Publications - 5
Citations - 62
Mohamed El-Shamouty is an academic researcher from Fraunhofer Society. The author has contributed to research in topics: Reinforcement learning & Human–robot interaction. The author has an hindex of 3, co-authored 3 publications receiving 26 citations.
Papers
More filters
Journal ArticleDOI
Simulation-driven machine learning for robotics and automation
TL;DR: In this paper, the challenges of applying robot-based automation in a highly individualized production are highlighted and a framework is proposed that combines latest machine learning techniques, like deep learning, with high-end physics simulation environments.
Proceedings ArticleDOI
Towards Safe Human-Robot Collaboration Using Deep Reinforcement Learning
TL;DR: This paper proposes a framework that uses deep RL as an enabling technology to enhance intelligence and safety of the robots in HRC scenarios and, thus, reduce hazards incurred by the robots.
Journal ArticleDOI
Skill-based Programming of Force-controlled Assembly Tasks using Deep Reinforcement Learning
TL;DR: This paper proposes a framework, using state-of-the-art model-free algorithms and manipulation skills to learn force and position parameters in a simulation environment.
Proceedings ArticleDOI
GLIR: A Practical Global-local Integrated Reactive Planner towards Safe Human-Robot Collaboration
TL;DR: In this paper , an integrated global planner is proposed to generate sub-optimal trajectories in human-robot collaboration (HRC) scenarios, where robots need to exert a desired behavior that maximizes utility without sacrificing safety and responsiveness.
Proceedings ArticleDOI
Uncertainty-Guided Active Reinforcement Learning with Bayesian Neural Networks
TL;DR: In this paper , the authors proposed using the Bayesian Neural Networks (BNNs) to guide the agent exploring actively to enhance the learning efficiency in RL and investigate the potential of recognizing safety risks in working environments with uncertainty information.