Combining Planning and Deep Reinforcement Learning in Tactical Decision Making for Autonomous Driving

Sökning: L773:2379 8858 > Combining Planning ...

Tactical decision making for autonomous driving is challenging due to the diversity of environments, the uncertainty in the sensor information, and the complex interaction with other road users. This article introduces a general framework for tactical decision making, which combines the concepts of planning and learning, in the form of Monte Carlo tree search and deep reinforcement learning. The method is based on the AlphaGo Zero algorithm, which is extended to a domain with a continuous state space where self-play cannot be used. The framework is applied to two different highway driving cases in a simulated environment and it is shown to perform better than a commonly used baseline method. The strength of combining planning and learning is also illustrated by a comparison to using the Monte Carlo tree search or the neural network policy separately.

Driggs-Campbell, KatherineUniversity of Illinois (författare)
Wolff, Krister,1969Chalmers tekniska högskola,Chalmers University of Technology(Swepub:cth)wolff (författare)
Laine, Leo,1972Volvo Cars(Swepub:cth)leo72 (författare)
Kochenderfer, Mykel J.Stanford University (författare)
Volvo CarsUniversity of Illinois (creator_code:org_t)

Av författaren/redakt...: Hoel, Carl-Johan ...; Driggs-Campbell, ...; Wolff, Krister, ...; Laine, Leo, 1972; Kochenderfer, My ...

Om ämnet

TEKNIK OCH TEKNOLOGIER: TEKNIK OCH TEKNO ...; och Maskinteknik; och Farkostteknik

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...; och Datorseende och ...

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.