Virginia Tech
Deploying Reinforcement Learning in the Real World: A Case Study on Apptronik Apollo
Abstract
dc:description.abstractHumanoid robots pose significant challenges for modeling and control: their many degrees of freedom and complex contact dynamics force traditional controllers to rely on simplified physical models that limit agility and robustness. Deep reinforcement learning offers an alternative: policies represented by deep neural networks can discover dynamic behaviors directly through millions of trials in a high-fidelity simulator, eliminating the need for simplified models. This thesis develops and validates a sim-to-real pipeline for deploying such policies on a humanoid robot, demonstrating reliable transfer of dynamic balancing and teleoperation skills from simulation to the Apptronik Apollo robot in the real world.
Degree
thesis:*- Name thesis:degree_name
- Master of Science
- Level thesis:degree_level
- masters
- Discipline thesis:degree_discipline
- Electrical Engineering
- Department dc:contributor.department
- Electrical Engineering
- Grantor dc:publisher
- Virginia Tech
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Welch, Stephen Brian
- Chair dc:contributor.committeechair
-
- Stilwell, Daniel J.
- Committee members dc:contributor.committeemember
-
- Williams, Ryan K.
- Leonessa, Alexander
Subjects
dc:subject × 3Rights
dc:rights- Statement dc:rights
-
- In Copyright
- Licence dc:rights.uri
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Dc Identifier Other
- vt_gsexam:44175