Noise and the Reality Gap: The Use of Simulation in Evolutionary Robotics
Proceedings of the Third European Conference on Advances in Artificial Life
Inverse Problem Theory and Methods for Model Parameter Estimation
Inverse Problem Theory and Methods for Model Parameter Estimation
Hi-index | 0.00 |
This paper presents a platform- and hardware-in-the-loop simulator (PHILS), which was developed for the evaluation of cooperative performance of multiple autonomous robots and their testing in virtual environments. The simulator consists of computers each with a graphics processing unit (GPU), monitors, a network switch that links the computers, and a server-client simulation software system installed on the computers. The cooperative performance of multiple autonomous robots can be evaluated by linking computers each to be mounted on a robot to the network and running and testing autonomous robots in a virtual environment. Unlike the conventional hardware-in-the-loop simulators or multi-robot simulators, the primary advantage of the PHILS is that it can test cooperative autonomous robots and analyze their cooperative performance as well as hardware performance in a real-time virtual environment, enabling the implementation of synchronous and asynchronous communication strategies and the control of communication delay and loss.