Meno:Tomá¹
Priezvisko:Belák
Názov:Training and analysis of robot NICO in virtual environment
Vedúci:Mgr. ©tefan Póco¹, PhD.
Rok:2026
Kµúèové slová:reinforcement learning, NICO robot, virtual environment, robotic control, explainability
Abstrakt:This thesis studies how the NICO humanoid robot can learn useful behavior in a virtual Unity environment. The robot is trained with reinforcement learning through the ML-Agents toolkit. We first explore gaze control through a task where NICO learns to look at a selected object while ignoring distractors. Then we study pushing in a tabletop task where the robot moves cubes into target zones. The experiments show that strong policies require careful design of observations, rewards, exploration and curricula. The thesis also proposes a custom self-attention-based policy architecture for the pushing task, which learns the task successfully. The learned policies are then analyzed through ablations, counterfactual tests, local explanations, and attention weights in the self-attention-based policy.

Súbory diplomovej práce:

diplomova_praca.pdf
e-priloha.zip

Súbory prezentácie na obhajobe:

Upravi»