2026-09-19T06:15:24Zhttps://dspace.mit.edu/server/oai/requestoai:dspace.mit.edu:1721.1/1636942025-11-18T06:27:05Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023
Agrawal, Pulkit
Fey, Nolan
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
2025-11-17T19:07:48Z
2025-11-17T19:07:48Z
2025-05
2025-08-14T19:31:47.412Z
https://hdl.handle.net/1721.1/163694
Achieving athletic loco-manipulation on robots requires moving beyond traditional tracking rewards—which simply guide the robot along a reference trajectory—to task rewards that drive truly dynamic, goal-oriented behaviors. Commands such as “throw the ball as far as you can” or “lift the weight as quickly as possible” compel the robot to exhibit the agility and power inherent in athletic performance. However, training solely with task rewards introduces two major challenges: these rewards are prone to exploitation (reward hacking), and the exploration process can lack sufficient direction. To address these issues, we propose a two-stage training pipeline. First, we introduce the Unsupervised Actuator Net (UAN), which leverages real-world data to bridge the sim-to-real gap for complex actuation mechanisms without requiring access to torque sensing. UAN mitigates reward hacking by ensuring that the learned behaviors remain robust and transferable. Second, we use a pre-training and fine-tuning strategy that leverages reference trajectories as initial hints to guide exploration. With these innovations, our robot athlete learns to lift, throw, and drag with remarkable fidelity from simulation to reality.
S.M.
Massachusetts Institute of Technology
In Copyright - Educational Use Permitted
Copyright retained by author(s)
https://rightsstatements.org/page/InC-EDU/1.0/
Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation
Thesis
application/pdf
Master
Master of Science in Electrical Engineering and Computer Science
Publication
unknown
unknown
<Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="d965d567-1dd2-4cf9-a9d0-b1384db7e8ec">
<Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type>
<Title>Bridging the Sim-to-Real Gap for Athletic Loco-Manipulation</Title>
<PublishedIn>
<Publication>
</Publication>
</PublishedIn>
<PublicationDate>2025-05</PublicationDate>
<Authors>
<Author>
<DisplayName>Fey, Nolan</DisplayName>
<Affiliation>
<OrgUnit>
</OrgUnit>
</Affiliation>
</Author>
</Authors>
<Editors>
</Editors>
<Publishers>
<Publisher>
<DisplayName>Massachusetts Institute of Technology</DisplayName>
<OrgUnit />
</Publisher>
</Publishers>
<License>https://rightsstatements.org/page/InC-EDU/1.0/</License>
<Abstract>Achieving athletic loco-manipulation on robots requires moving beyond traditional tracking rewards—which simply guide the robot along a reference trajectory—to task rewards that drive truly dynamic, goal-oriented behaviors. Commands such as “throw the ball as far as you can” or “lift the weight as quickly as possible” compel the robot to exhibit the agility and power inherent in athletic performance. However, training solely with task rewards introduces two major challenges: these rewards are prone to exploitation (reward hacking), and the exploration process can lack sufficient direction. To address these issues, we propose a two-stage training pipeline. First, we introduce the Unsupervised Actuator Net (UAN), which leverages real-world data to bridge the sim-to-real gap for complex actuation mechanisms without requiring access to torque sensing. UAN mitigates reward hacking by ensuring that the learned behaviors remain robust and transferable. Second, we use a pre-training and fine-tuning strategy that leverages reference trajectories as initial hints to guide exploration. With these innovations, our robot athlete learns to lift, throw, and drag with remarkable fidelity from simulation to reality.</Abstract>
<Access xmlns="http://purl.org/coar/access_right"
>
</Access>
</Publication>