Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/135803
Title: GENERALIZED PREDICTIVE PLANNING FOR AUTONOMOUS DRIVING IN DYNAMIC ENVIRONMENTS
Authors: SCOTT DREW PENDLETON
Keywords: autonomous vehicle, motion planning, dynamic environment modeling, behavior planning, planning framework design, reachability guidance
Issue Date: 19-Jan-2017
Source: SCOTT DREW PENDLETON (2017-01-19). GENERALIZED PREDICTIVE PLANNING FOR AUTONOMOUS DRIVING IN DYNAMIC ENVIRONMENTS. ScholarBank@NUS Repository.
Abstract: This thesis presents a generalized framework for real-time predictive planning in space-time to improve autonomous driving performance in dynamic environments. Predictive planning refers to planning around predicted obstacle trajectories, where robot velocity profiles are solved in an integrated manner along with spatial paths, which is contrasted against traditional motion planning approaches which decouple the velocity and path planning problems. Autonomous vehicle deployments are still limited with respect to environmental complexity and operating speed, however the real world experimental results show that the proposed predictive planning framework can push the bounds of planning capabilities in both aspects. The planning methods are demonstrated onboard three classes of vehicles, a road car, buggy and scooter, in both unstructured pedestrian environments and on-road environments. Test scenarios include pedestrian crowd navigation, T-junction navigation, defensive driving, and overtaking.
URI: http://scholarbank.nus.edu.sg/handle/10635/135803
Appears in Collections:Ph.D Theses (Open)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
PendletonSD.pdf26.82 MBAdobe PDF

OPEN

NoneView/Download

Page view(s)

57
checked on Jan 14, 2018

Download(s)

97
checked on Jan 14, 2018

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.