My Account Log in

1 option

Implementation and Validation of Behavior Cloning using Scaled Vehicles Clemson University

SAE Technical Papers (1906-current) Available online

View online
Format:
Book
Conference/Event
Author/Creator:
Verma, Ankit, author.
Contributor:
Allam, Naga Venkata SaiTeja
Bagkar, Siddhesh
Krovi, Venkat N.
Raman, Adhiti
Schmid, Matthias
Conference Name:
SAE WCX Digital Summit (2021-04-13 : Live Online, Pennsylvania, United States)
Language:
English
Physical Description:
1 online resource cm
Place of Publication:
Warrendale, PA SAE International 2021
Summary:
Over the last decade, a tremendous amount of research and progress has been made towards developing smart technologies and strategies to implement the lane-keeping assist, lane following algorithms. One of the fundamental objectives for the development of such technologies is to enable vehicles to maneuver autonomously with the capability to avoid obstacles, keeping lanes, and thereby maintain safety. Driving is one of the riskiest activities we might choose to do during one's lifetime. The autonomous market is currently growing at an existential rate and many driverless vehicles are expected to be on our roads this year and in large numbers. Implementing the new autonomy strategies straight away on the full-scaled vehicles increases the complexity concerning the cost incurred and safety of the environment. The alternate approaches to test the strategy include simulation which was ruled out as many real-life instances are difficult to recreate and incorporate. Therefore, in this paper, we explored another alternate approach to deploy the algorithms on F1-tenth scaled vehicles equipped with a camera. Implementing the Deep Reinforcement Learning to process the camera feed, train them on the neural networks, and deploy on the Scaled Vehicles. This approach contains a great potential for educational and research-bed deployments with a short development and deployment time that can fit neatly in one semester
Notes:
Vendor supplied data
Publisher Number:
2021-01-0248
Access Restriction:
Restricted for use by site license

The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.

My Account

Shelf Request an item Bookmarks Fines and fees Settings

Guides

Using the Library Catalog Using Articles+ Library Account