English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Two current methods used to train autonomous cars are reinforcement learningand imitation learning. This research develops a new learning methodology andsystematic approach in both a simulated and a smaller real world environment byintegrating supervised imitation learning into reinforcement learning to makethe RL training data collection process more effective and efficient. Bycombining the two methods, the proposed research successfully leverages theadvantages of both RL and IL methods. First, a real mini-scale robot car wasassembled and trained on a 6 feet by 9 feet real world track using imitationlearning. During the process, a handle controller was used to control themini-scale robot car to drive on the track by imitating a human expert driverand manually recorded the actions using Microsoft AirSim's API. 331 accuratehuman-like reward training samples were able to be generated and collected.Then, an agent was trained in the Microsoft AirSim simulator usingreinforcement learning for 6 hours with the initial 331 reward data inputtedfrom imitation learning training. After a 6-hour training period, themini-scale robot car was able to successfully drive full laps around the 6 feetby 9 feet track autonomously while the mini-scale robot car was unable tocomplete one full lap round the track even after 30 hour training pure RLtraining. With 80% less training time, the new methodology producedsignificantly more average rewards per hour. Thus, the new methodology was ableto save a significant amount of training time and can be used to accelerate theadoption of RL in autonomous driving, which would help produce more efficientand better results in the long run when applied to real life scenarios.  Key Words: Reinforcement Learning (RL), Imitation Learning (IL), AutonomousDriving, Human Driving Data, CNN

Integrating Imitation Learning with Human Driving Data into Reinforcement Learning to Improve Training Efficiency for Autonomous Driving