Environmental-aware Reinforcement Learning-based Scheduler for Trustworthy 6G in the Factory Floor

6G networks will play a crucial role in Industry 4.0 advancing further smart manufacturing and trustworthy communication. This paper introduces a reinforcement learning scheduler that considers environmental knowledge designed to improve reliability and security aspects of trustworthiness by favoring to serve nodes when in line-of-sight. We evaluate the performance in a factory floor scenario for two different heights of remote-radio heads and various blockage densities. The results show that the proposed method outperforms traditional schedulers such as round robin and proportional fair in terms of reliability, availability and fairness enhancing thus reliability and security aspects of trustworthiness when the environment is prone to a mixture of line-of-sight and non-line-of-sight.