5G New Radio (NR) network deployment in Non-Stand Alone (NSA) mode means that 5G networks rely on the control plane of existing Long Term Evolution (LTE) modules for control functions, while 5G modules are only dedicated to the user plane tasks, which could also be carried out by LTE modules simultaneously. The first deployments of 5G networks are essentially using this technology. These deployments enable what is known as E-UTRAN NR Dual Connectivity (ENDC), where a user establish a 5G connection simultaneously with a pre-existing LTE connection to boost their data rate. In this paper, a single Federated Deep Reinforcement Learning (FDRL) agent for the optimization of the event that triggers the dual connectivity between LTE and 5G is proposed. First, single Deep Reinforcement Learning (DRL) agents are trained in isolated cells. Later, these agents are merged into a unique global agent capable of optimizing the whole network with Federated Learning (FL). This scheme of training single agents and merging them also makes feasible the use of dynamic simulators for this type of learning algorithm and parameters related to mobility, by drastically reducing the number of possible combinations resulting in fewer simulations. The simulation results show that the final agent is capable of achieving a tradeoff between dropped calls and the user throughput to achieve global optimum without the need for interacting with all the cells for training.

A new technique for Simultaneous Localization and Mapping (SLAM) is introduced. This technique was developed as a real-time, distributed, scalable implementation for heterogeneous mobile robot teams. Update efficiency and performance under variable resources is enhanced using a new strategy called Lazy Belief Propagation. The formulations and algorithms behind the implementation are described and a simulation was used to compare several SLAM algorithms. Results demonstrate an 11% improvement in map coverage in the same amount of time compared to a traditional implementation.

An architecture for robotic hardware-in-the- loop simulation (RHILS) has been proposed as a design and simulation tool for serial-link robot manipulators. This paper evaluates the RHILS platform's capabilities when applied to the simulation of the 5-d.o.f. CRS CataLyst-5 industrial manipulator from Thermo Fisher Scientific Inc. The results demonstrate that the RHILS platform is able to accurately simulate the robot even under extreme operating conditions, and the platform shows significant potential as a design tool for both the robot and its control unit.

This paper details the design and development of a robotic hardware-in-the-loop simulation platform that can be used for rapid-prototyping industrial manipulators. The architecture of the proposed platform has been presented by Martin and Emami (2006). Potential benefits of such a platform include allowing concurrent development of hardware and control system components and providing a reusable platform for reconfigurable manipulators through a generic and modular structure. Some preliminary tests on the platform have also been discussed in the paper