Combining offline and online learning in developing an adaptive controller for a simulated car racing environment
This report presents the work done to develop an autonomous driver
for the Simulated Car Racing Championship (SCRC), a competition in
computational intelligence based on The Open Racing Car Simulator
(TORCS). Autonomous race driving based only on local sensory data
is a complex problem, and previous SCRC entries' work show a wide
variety of approaches taken to address it. We describe CRABCAR,
a controller that combines oine learning prior to the competition
with online learning during the competition to optimize its performance in the SCRC context. The presented approach extends and builds on track modelling and racing line optimization techniques introduced previously, addressing known problems said techniques have with noisy sensory input and non-perfect track information. CRABCAR's performance is compared to previous entries from the SCRC, with results showing CRABCAR at a performance level similar to the others. We conclude that a system for online adaption is essential when pre-learned strategies are applied to discretely segmented and non-perfect track models in the SCRC context.
Place, publisher, year, edition, pages
Institutt for datateknikk og informasjonsvitenskap , 2011. , 96 p.
ntnudaim:6179, MTDT datateknikk, Intelligente systemer
IdentifiersURN: urn:nbn:no:ntnu:diva-13640Local ID: ntnudaim:6179OAI: oai:DiVA.org:ntnu-13640DiVA: diva2:441339
Downing, Keith, Professor