Autonomous Navigation in Complex Environments
Robotics
2024-01-09 v1 Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Systems and Control
Systems and Control
Abstract
This paper explores the application of CNN-DNN network fusion to construct a robot navigation controller within a simulated environment. The simulated environment is constructed to model a subterranean rescue situation, such that an autonomous agent is tasked with finding a goal within an unknown cavernous system. Imitation learning is used to train the control algorithm to use LiDAR and camera data to navigate the space and find the goal. The trained model is then tested for robustness using Monte-Carlo.
Cite
@article{arxiv.2401.03267,
title = {Autonomous Navigation in Complex Environments},
author = {Andrew Gerstenslager and Jomol Lewis and Liam McKenna and Poorva Patel},
journal= {arXiv preprint arXiv:2401.03267},
year = {2024}
}
Comments
7 pages, 3 figures, independent paper