A significant barrier to the combined use of simulation and AI techniques such as Machine Learning (ML) are that developers have differing backgrounds and use different tools. In particular simulation model developers may lack expertise in the software tools and coding abilities needed for the development of ML algorithms. In order to bridge this gap this article presents a discrete-event simulation (DES) that incorporates the use of a reinforcement learning (RL) algorithm which determines an approximate best route for robots in a factory moving from one physical location to another whilst avoiding collisions with fixed barriers. The study shows how the object modelling and graphical facilities of the Simio commercial off-the-shelf (COTS) DES software package enables an RL capability without the need to use program code or require an interface with external RL software.
This paper reports on the co-simulation of a team of robots deployed in an exploration task, coordinated by a bio-inspired exploration algorithm. The co-simulation integrates the high-level exploration algorithm with detailed implementations of the robot controllers and kinematic models. Co-simulation results are used to find and correct mismatches between submodels.
This paper proposes a three-dimensional (3D) communication channel model for an indoor environment considering the effect of the Hypersurface. The Hypersurface is a software controlled intelligent metasurface, which can be used to manipulate electromagnetic waves, as for example for nonspecular reflection and full absorption. Thus it can control the impinging rays from a transmitter towards a receiver location in both LOS and NLOS paths, e.g. to combat distance and improve wireless connectivity. We focus on the 60 GHz mmWave frequency band due to its increasing significance in 5G/6G networks and evaluate the effect of Hypersurface in an indoor environment in terms of attenuation coefficients related to the Hypersurface reflection and absorption functionalities, using CST simulation, a 3D electromagnetic simulator of high frequency components. To highlight the benefits of Hypersurface coated walls versus plain walls, we use the derived Hypersurface 3D channel model and a custom 3D ray-tracing simulator for plain walls considering a typical indoor scenario for different Tx-Rx location and separation distances.
In this paper, we simulated a distributed, cooperative path planning technique for multiple drones (~200) to explore an unknown region (~10,000 connected units) in the presence of obstacles. The map of an unknown region is dynamically created based on the information obtained from sensors and other drones. The unknown area is considered a connected region made up of hexagonal unit cells. These cells are grouped to form larger cells called sub-areas. We use long range and short range communication. The short-range communication within drones in smaller proximity helps avoid re-exploration of cells already explored by companion drones located in the same subarea. The long-range communication helps drones identify next subarea to be targeted based on weighted RNN (Reverse nearest neighbor). Simulation results show that weighted RNN in a hexagonal representation makes exploration more efficient, scalable and resilient to communication failures.
As a basic element of organisms, motivation shapes the action pattern. There are abundant biological and social systems that originate from motivations, which have attracted widespread attention. To pave the technical foundation of relevant researches, this paper presents an effective model to simulate the spatial distribution of motivation within complex environments, which is named as the quasi-potential field. Our modelling process includes three steps. First, we suggest an original algorithm for structure reduction, which can preserve all the topological properties of a given environment. Second, we define the quasi-potential value on the reduced structure, which works as the root of the whole field. Third, we extend the field from the root to all the available spaces. Thus, the motivation distribution in the real environment can be finally generated. In our paper, several simulation experiments are carried out to verify the effectiveness of our model, whose results are proved to be promising.
