- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- UBC Theses and Dissertations /
- ROS-X-Habitat : bridging the ROS ecosystem with embodied...
Open Collections
UBC Theses and Dissertations
UBC Theses and Dissertations
ROS-X-Habitat : bridging the ROS ecosystem with embodied AI Yang, Haoyu
Abstract
We introduce ROS-X-Habitat, a software interface that bridges the AI Habitat plat- form for embodied reinforcement learning agents with other robotics resources via ROS. This interface not only offers standardized communication protocols between embodied agents and simulators, but also enables physics-based simulation. With this interface, roboticists are able to train their own Habitat RL agents in another simulation environment or to develop their own robotic algorithms inside Habitat Sim. Through in silico experiments, we demonstrate that ROS-X-Habitat has minimal impact on the navigation performance and simulation speed of Habitat agents; that a standard set of ROS mapping, planning and navigation tools can run in the Habitat simulator, and that a Habitat agent can run in the standard ROS simulator Gazebo. Furthermore, to show how ROS-X-Habitat can be used in data collection and RL training, we present the training and evaluation of an agent we train to perform a multiple point goal navigation task we define.
Item Metadata
Title |
ROS-X-Habitat : bridging the ROS ecosystem with embodied AI
|
Creator | |
Supervisor | |
Publisher |
University of British Columbia
|
Date Issued |
2022
|
Description |
We introduce ROS-X-Habitat, a software interface that bridges the AI Habitat plat-
form for embodied reinforcement learning agents with other robotics resources via
ROS. This interface not only offers standardized communication protocols between
embodied agents and simulators, but also enables physics-based simulation. With
this interface, roboticists are able to train their own Habitat RL agents in another
simulation environment or to develop their own robotic algorithms inside Habitat
Sim. Through in silico experiments, we demonstrate that ROS-X-Habitat has minimal impact on the navigation performance and simulation speed of Habitat agents;
that a standard set of ROS mapping, planning and navigation tools can run in the
Habitat simulator, and that a Habitat agent can run in the standard ROS simulator
Gazebo. Furthermore, to show how ROS-X-Habitat can be used in data collection
and RL training, we present the training and evaluation of an agent we train to
perform a multiple point goal navigation task we define.
|
Genre | |
Type | |
Language |
eng
|
Date Available |
2022-04-07
|
Provider |
Vancouver : University of British Columbia Library
|
Rights |
Attribution-NonCommercial-NoDerivatives 4.0 International
|
DOI |
10.14288/1.0412641
|
URI | |
Degree | |
Program | |
Affiliation | |
Degree Grantor |
University of British Columbia
|
Graduation Date |
2022-05
|
Campus | |
Scholarly Level |
Graduate
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International