Robot Navigation in Cluttered Environments with Deep Reinforcement Learning
The application of robotics in cluttered and dynamic environments provides a wealth of challenges. This thesis proposes a deep reinforcement learning based system that determines collision free navigation robot velocities directly from a sequence of depth images and a desired direction of travel. Th...
| Main Author: | |
|---|---|
| Format: | Others |
| Published: |
DigitalCommons@CalPoly
2019
|
| Subjects: | |
| Online Access: | https://digitalcommons.calpoly.edu/theses/2011 https://digitalcommons.calpoly.edu/cgi/viewcontent.cgi?article=3413&context=theses |