Design and analysis of an E-Puck2 robot plug-in for the ARGoS simulator
Daniel H. Stolfi, Grégoire Danoy
- 发表年份
- 2023
- 引用次数
- 6
摘要
In this article we present a new plug-in for the ARGoS swarm robotic simulator to implement the E-Puck2 robot model, including its graphical representation, sensors and actuators. We have based our development on the former E-Puck robot model (version 1) by upgrading the existing sensors (proximity, light, ground, camera, and battery) and adding new ones (time of flight and simulated encoders) implemented from scratch. We have adapted the values produced by the proximity, light and ground sensors, including the E-Puck2’s onboard camera according to its resolution, and proposed four new discharge models for the battery. We have evaluated this new plug-in in terms of accuracy and efficiency through comparisons with real robots and extensive simulations. In all our experiments the proposed plug-in has worked well showing high levels of accuracy. The observed increment of execution times when using the studied sensors varies according to the number of robots and types of sensors included in the simulation, ranging from a negligible impact to 53% longer simulations in the most demanding cases.
关键词
相关论文
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002