Activity
Time:
Master’s Thesis Defense: Pedro Lucas Franca Albuquerque
Date:
9:00 am
Schorr Center
Room: 211
1100 T St
Lincoln NE 68588
Lincoln NE 68588
Additional Info: SHOR
Master’s Thesis Defense: Pedro Lucas Franca Albuquerque
Monday, December 2, 2019
9 a.m.
211 Schorr Center
Committee Members: Dr. Carrick Detweiler (Advisor), Dr. Justin Bradley and Dr. Stephen Scott
“Domain Adaptation in Unmanned Aerial Vehicles Landing Using Reinforcement Learning”
Abstract: Landing an unmanned aerial vehicle (UAV) on a moving platform is a challenging task that often requires exact models of the UAV dynamics, platform characteristics, and environmental conditions. In this thesis, we present and investigate three different machine learning approaches with varying levels of domain knowledge: dynamics randomization, universal policy with system identification, and reinforcement learning with no parameter variation. We first train the policies in simulation, then perform experiments both in simulation, making variations of the system dynamics with wind and friction coefficient, then perform experiments in a real robot system with wind variation. We initially expected that providing more information on environmental characteristics with system identification would improve the outcomes, however, we found that transferring a policy learned in simulation with domain randomization to the real robot system achieves the best result in the real robot and simulation. In this thesis, we compare the results of multiple deep reinforcement learning approaches trained in simulation and transferred in robot experiments with the presence of external disturbances. We were able to create a policy to control an Unmanned Aerial Vehicle completely trained in simulation and transfer it to a real system with the presence of external disturbances. In doing so, we evaluate the performance of dynamics randomization and universal policy with system identification.
Monday, December 2, 2019
9 a.m.
211 Schorr Center
Committee Members: Dr. Carrick Detweiler (Advisor), Dr. Justin Bradley and Dr. Stephen Scott
“Domain Adaptation in Unmanned Aerial Vehicles Landing Using Reinforcement Learning”
Abstract: Landing an unmanned aerial vehicle (UAV) on a moving platform is a challenging task that often requires exact models of the UAV dynamics, platform characteristics, and environmental conditions. In this thesis, we present and investigate three different machine learning approaches with varying levels of domain knowledge: dynamics randomization, universal policy with system identification, and reinforcement learning with no parameter variation. We first train the policies in simulation, then perform experiments both in simulation, making variations of the system dynamics with wind and friction coefficient, then perform experiments in a real robot system with wind variation. We initially expected that providing more information on environmental characteristics with system identification would improve the outcomes, however, we found that transferring a policy learned in simulation with domain randomization to the real robot system achieves the best result in the real robot and simulation. In this thesis, we compare the results of multiple deep reinforcement learning approaches trained in simulation and transferred in robot experiments with the presence of external disturbances. We were able to create a policy to control an Unmanned Aerial Vehicle completely trained in simulation and transfer it to a real system with the presence of external disturbances. In doing so, we evaluate the performance of dynamics randomization and universal policy with system identification.