Simultaneous Localization and Mapping (SLAM) is a powerful method for autonomously exploring new environments, which has never been applied to humanoid robots. This project implemented SLAM on the Atlas humanoid robot, allowing it to interact with and explore novel environments. The Atlas robot was programmed to create 3 dimensional maps of environments and localize itself within them. Due to constraints in time and safety the project was conducted mostly in simulation. Both stereo cameras and LiDAR were used in experiments to identify the robot’s surroundings and avoid obstacles. These sensors paired with the robot’s locomotion allowed the Atlas robot to search and navigate unknown areas.

• This report represents the work of one or more WPI undergraduate students submitted to the faculty as evidence of completion of a degree requirement. WPI routinely publishes these reports on its website without editorial or peer review.

Creator

• Staknis, Emily L.
• Parmanand, Amrit
• Carnemolla, Ryan F.
• Mukherjee, Anirban

Publisher

• Worcester Polytechnic Institute

Identifier

• 22811
• E-project-050621-111552

Keyword

• ATLAS
• TOUGH
• Octomap
• LiDAR
• SLAM

Advisor

• Gennert, Michael A.

Year

• 2021

Sponsor

• No Sponsor

Date created

• 2021-05-06

Resource type

• Major Qualifying Project

Major

• Computer Science
• Robotics Engineering

Rights statement

• In Copyright