Visual Place Recognition Pre-Training for End-to-End Trained Autonomous Driving Agent

Visual Place Recognition Pre-Training for End-to-End Trained Autonomous Driving Agent

End-to-end autonomous driving often relies on the concept of learning to imitate from expert demonstrations. Since those demonstrations cannot cover all possible variations in data, there always are situations where the trained agents encounter unseen conditions, which results in a shift in the data...

Full description

Bibliographic Details
Main Authors: Shubham Juneja, Povilas Daniusis, Virginijus Marcinkevicius
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Imitation learning
autonomous driving
agents
self-driving cars
deep learning
pre-training
Online Access:https://ieeexplore.ieee.org/document/10313277/

Internet

https://ieeexplore.ieee.org/document/10313277/

Similar Items