In the field of robotics, forward kinematics is an activity that allows finding a mathematical model for the resulting position in the final effector based on the robot joints position, a popular alternative for determining this model is defined by the Denavit Hartenberg convention, nevertheless, this method requires knowledge about linear algebra and three-dimensional spatial kinematics. Machine learning uses specific computational methodologies to solving similar problems in several areas, so it could be a viable answer for automatic determining of forwarding kinematics. In this work we propose the use of genetic programming as a machine learning algorithm for finding the forward kinematics of a 2 degrees of freedom robot, getting a satisfactory outcome obtaining a satisfactory result with blocks that describe the expected solution, validating the capacity of the genetic programming in order to validate this algorithm for later work with more complex robots.

Advanced driver assistance systems (ADAS) are important to prevent road accidents, one of those are lane invasions. Nowadays optical and control systems are applied in new cars to maintain vehicles centered in a lane, nevertheless old vehicles cannot access to these new assistant systems. In this paper we present a position steering wheel control (SWC) in a lane detection prototype designed for its implementation in cars that do not have installed this system. The proposed technique uses a self-tuning PID controller connected to a DC motor for SWC that uses orientation of lines on the road. Lines are detected by applying Sobel filter convolution and Hough transform, which are image processing techniques that allow obtaining orientation. The PID controller is automatically tuned since this assistant would be installed in different cars. GA is used since it has shown good results parametrizing well known structured problems without requiring mathematical models or techniques that demand control experts. The main contributions of this research are a SCW alternative capable of been installed in any old vehicle and the algorithm implemented for using orientation as input data as the control reference with a self-tuning PID controller.