<div dir="ltr"><div>Hello!</div><div><br></div><div>I am Sakshay. I am currently working on the project:Robotics Academy under Google Summer of Code. <a href="https://github.com/TheRoboticsClub/colab-gsoc2020-Sakshay_Mahna" target="_blank">My project</a>
is on developing an exercise for students on the topic Evolutionary
Robotics. The exercise is supposed to offer a Gazebo simulation of the
robot, and we have to train the parameters of it's Neural Network by
means of a Genetic Algorithm for obstacle avoidance. However, the problem is with
the repeatability of the simulations. Every time we run the simulation,
the robot takes a slightly different course of action, which should not
be the case. The robot should behave the same way every time we run it.<br></div><div><br></div><div>It would be really great if I could get a little guidance on how to implement this.<br></div><div><br></div><div>Thanks & Regards</div><div>Sakshay Mahna<br></div></div>