2026-09-19T17:17:34Zhttps://dspace.mit.edu/server/oai/request

oai:dspace.mit.edu:1721.1/1526622023-11-03T03:21:27Zcom_1721.1_7582com_1721.1_7581col_1721.1_131023

Carlone, Luca Muriga, Veronica Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science 2023-11-02T20:06:42Z 2023-11-02T20:06:42Z 2023-09 2023-10-03T18:21:01.032Z https://hdl.handle.net/1721.1/152662 Applying Reinforcement Learning (RL) for autonomous navigation has enormous potential in several robotics applications, including search and rescue operations. RL circumvents the need to manually specify a control policy for navigation and allows capturing aspects that are difficult to describe without relying on learning, e.g., that survivors or objects of interest are more likely to be found in specific regions of the environment. This is relevant for navigation policies guiding autonomous exploration and object search. To improve the performance of RL models guiding autonomous agents, we use 3D Scene Graphs (3DSGs) as a map representation. Previous work has shown that RL policies based on offline 3DSGs produce promising results in simulation, and this work takes initial steps towards extending these findings to 3DSGs produced online by Hydra, a new spatial perception system that builds 3DSGs in real-time. The work also provides an initial integration of the RL policies previously trained and evaluated in simulation [1] on a Unitree A1 quadruped robot. While the results are too preliminary to be conclusive, the thesis takes several integration steps towards deploying scene-graph-based RL policies for navigation on real robots. M.Eng. Massachusetts Institute of Technology In Copyright - Educational Use Permitted Copyright retained by author(s) https://rightsstatements.org/page/InC-EDU/1.0/ Towards Reinforcement-Learning-based Robot Navigation with 3D Scene Graphs Thesis application/pdf Master Master of Engineering in Electrical Engineering and Computer Science Publication unknown unknown <Publication xmlns="https://www.openaire.eu/cerif-profile/1.1/" id="b4f28818-8ad3-4e67-ab31-f8482586c89c"> <Type xmlns="https://www.openaire.eu/cerif-profile/vocab/COAR_Publication_Types">http://purl.org/coar/resource_type/c_1843</Type> <Title>Towards Reinforcement-Learning-based Robot Navigation with 3D Scene Graphs</Title> <PublishedIn> <Publication> </Publication> </PublishedIn> <PublicationDate>2023-09</PublicationDate> <Authors> <Author> <DisplayName>Muriga, Veronica</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>Applying Reinforcement Learning (RL) for autonomous navigation has enormous potential in several robotics applications, including search and rescue operations. RL circumvents the need to manually specify a control policy for navigation and allows capturing aspects that are difficult to describe without relying on learning, e.g., that survivors or objects of interest are more likely to be found in specific regions of the environment. This is relevant for navigation policies guiding autonomous exploration and object search. To improve the performance of RL models guiding autonomous agents, we use 3D Scene Graphs (3DSGs) as a map representation. Previous work has shown that RL policies based on offline 3DSGs produce promising results in simulation, and this work takes initial steps towards extending these findings to 3DSGs produced online by Hydra, a new spatial perception system that builds 3DSGs in real-time. The work also provides an initial integration of the RL policies previously trained and evaluated in simulation [1] on a Unitree A1 quadruped robot. While the results are too preliminary to be conclusive, the thesis takes several integration steps towards deploying scene-graph-based RL policies for navigation on real robots.</Abstract> <Access xmlns="http://purl.org/coar/access_right" > </Access> </Publication>