Ciencias Exactas y Ciencias de la Salud

Now showing 1 - 2 of 2

Reinforcement learning for an attitude control algorithm for racing quadcopters
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-06-15) Nakasone Nakamurakari, Shun Mauricio; BUSTAMANTE BELLO, MARTIN ROGELIO; 58810; Bustamante Bello, Martín Rogelio; puemcuervo; Navarro Durán, David; School of Engineering and Sciences; Campus Ciudad de México; Galuzzi Aguilera, Renato
From its first conception to its wide commercial distribution, Unmanned Aerial Vehicle (UAV)’s have always presented an interesting control problem as their dynamics are not as simple to model and present a non-linear behavior. These vehicles have improved as the technology in these devices has been developed reaching commercial and leisure use in everyday life. Out of the many applications for these vehicles, one that has been rising in popularity is drone racing. As technology improves, racing quadcopters have also improved reaching capabilities never seen before in flying vehicles. Though hardware and performance have improved throughout the drone racing industry, something that has been lacking, in a way, is better and more robust control algorithms. In this thesis, a new control strategy based on Reinforcment Learning (RL) is presented in order to achieve better performance in attitude control for racing quadcopters. For this process, two different plants were developed to fulfill, a) the training process needs with a simplified dynamics model and b) a higher fidelity Multibody model to validate the resulting controller. By using Proximal Policy Optimization (PPO), the agent is trained via a reward function and interaction with the environment. This dissertation presents a different approach on how to determine a reward function such that the agent trained learns in a more effective and faster way. The control algorithm obtained from the training process is simulated and tested against the most common attitude control algorithm used in drone races (Proportional Integral Derivative (PID) control), as well as its ability to reject noise in the state signals and external disturbances from the environment. Results from agents trained with and without these disturbances are also presented. The resulting control policies were comparable to the PID controller and even outperformed this control strategy in noise rejection and robustness to external disturbances.
Model predictive control for dynamics in autonomous cars
(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-05-29) Valdivieso Soto, Andrew; BUSTAMANTE BELLO, MARTIN ROGELIO; 58810; Bustamante Bello, Martín Rogelio; puelquio/mscuervo; Izquirdo Reyes, Javier; School of Engineering and Sciences; Campus Ciudad de México; Galluzzi Aguilera, Renato
Car accidents are quite common in several countries, most of these accidents are due to human error, these cover a wide range, from hitting a pole to hitting a pedestrian and this can lead to fatal accidents as well, also the high time in traffic is due to the lack of attention or expertise on the part of the driver. To reduce these accidents and this time lost in traffic, the investigation of autonomous vehicles is chosen, this thesis is focused on the control system for lateral, longitudinal, and yaw angle position using a predictive control model. This study analyzes the performance of the model predictive control (MPC) against PID by controlling the steering and acceleration of a vehicle, it was used Matlab to create the waypoints in the driving scenario and to make the simulations in linear MPC and adaptive MPC blocks, it was analyzed the performance in each control to see how well the position of the vehicle follows the reference line for a double change lane maneuver and compare the results against a PID to see which one performs better. The parameters used were measured from a golf cart. These results suggest that the MPC has a better performance when the tuning is done correctly also the data obtained from the simulation showed that speed was significant to lateral position and yaw angle when lane changes were made. We conclude that Model Predictive Control has better performance against PID also the MPC can be adjusted to work as we wanted it had a lot of maneuverability and is quite flexible.

Ciencias Exactas y Ciencias de la Salud

Browse

Filters

Settings

Sort By

Results per page

Search Results