Matches in SemOpenAlex for { <https://semopenalex.org/work/W3121095832> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W3121095832 abstract "Navigating through unsignalized intersections is one of the most challenging problems in urban environments for autonomous vehicles. Existing methods need to train specific policy models to deal with different tasks including going straight, turning left and turning right. In this paper we formulate intersection navigation as a multi-task reinforcement learning problem and propose a unified learning framework for all three navigation tasks at the intersections. We propose to represent multiple tasks with a unified four-dimensional vector, which elements mean a common sub-task and three specific target sub-tasks respectively. Meanwhile, we design a vectorized reward function combining with deep Q-networks (DQN) to learn to handle multiple intersection navigation tasks concurrently. We train the agent to navigate through intersections by adjusting the speed of the ego vehicle under given route. Experimental results in both simulation and realworld vehicle test demonstrate that the proposed multi-task DQN algorithm outperforms baselines for all three navigation tasks in several different intersection scenarios." @default.
- W3121095832 created "2021-01-18" @default.
- W3121095832 creator A5001330715 @default.
- W3121095832 creator A5023899707 @default.
- W3121095832 creator A5036527488 @default.
- W3121095832 creator A5047509839 @default.
- W3121095832 creator A5059794693 @default.
- W3121095832 creator A5090567275 @default.
- W3121095832 date "2020-10-19" @default.
- W3121095832 modified "2023-10-17" @default.
- W3121095832 title "A Multi-Task Reinforcement Learning Approach for Navigating Unsignalized Intersections" @default.
- W3121095832 cites W2092187344 @default.
- W3121095832 cites W2257979135 @default.
- W3121095832 cites W2344396459 @default.
- W3121095832 cites W2575705757 @default.
- W3121095832 cites W2604216058 @default.
- W3121095832 cites W2903683378 @default.
- W3121095832 cites W2903709398 @default.
- W3121095832 cites W2963625099 @default.
- W3121095832 cites W2963804019 @default.
- W3121095832 cites W2970787054 @default.
- W3121095832 cites W2991276938 @default.
- W3121095832 doi "https://doi.org/10.1109/iv47402.2020.9304542" @default.
- W3121095832 hasPublicationYear "2020" @default.
- W3121095832 type Work @default.
- W3121095832 sameAs 3121095832 @default.
- W3121095832 citedByCount "14" @default.
- W3121095832 countsByYear W31210958322021 @default.
- W3121095832 countsByYear W31210958322022 @default.
- W3121095832 countsByYear W31210958322023 @default.
- W3121095832 crossrefType "proceedings-article" @default.
- W3121095832 hasAuthorship W3121095832A5001330715 @default.
- W3121095832 hasAuthorship W3121095832A5023899707 @default.
- W3121095832 hasAuthorship W3121095832A5036527488 @default.
- W3121095832 hasAuthorship W3121095832A5047509839 @default.
- W3121095832 hasAuthorship W3121095832A5059794693 @default.
- W3121095832 hasAuthorship W3121095832A5090567275 @default.
- W3121095832 hasConcept C107457646 @default.
- W3121095832 hasConcept C119857082 @default.
- W3121095832 hasConcept C127413603 @default.
- W3121095832 hasConcept C14036430 @default.
- W3121095832 hasConcept C154945302 @default.
- W3121095832 hasConcept C175154964 @default.
- W3121095832 hasConcept C201995342 @default.
- W3121095832 hasConcept C22212356 @default.
- W3121095832 hasConcept C2780451532 @default.
- W3121095832 hasConcept C41008148 @default.
- W3121095832 hasConcept C64543145 @default.
- W3121095832 hasConcept C78458016 @default.
- W3121095832 hasConcept C86803240 @default.
- W3121095832 hasConcept C97541855 @default.
- W3121095832 hasConceptScore W3121095832C107457646 @default.
- W3121095832 hasConceptScore W3121095832C119857082 @default.
- W3121095832 hasConceptScore W3121095832C127413603 @default.
- W3121095832 hasConceptScore W3121095832C14036430 @default.
- W3121095832 hasConceptScore W3121095832C154945302 @default.
- W3121095832 hasConceptScore W3121095832C175154964 @default.
- W3121095832 hasConceptScore W3121095832C201995342 @default.
- W3121095832 hasConceptScore W3121095832C22212356 @default.
- W3121095832 hasConceptScore W3121095832C2780451532 @default.
- W3121095832 hasConceptScore W3121095832C41008148 @default.
- W3121095832 hasConceptScore W3121095832C64543145 @default.
- W3121095832 hasConceptScore W3121095832C78458016 @default.
- W3121095832 hasConceptScore W3121095832C86803240 @default.
- W3121095832 hasConceptScore W3121095832C97541855 @default.
- W3121095832 hasLocation W31210958321 @default.
- W3121095832 hasOpenAccess W3121095832 @default.
- W3121095832 hasPrimaryLocation W31210958321 @default.
- W3121095832 hasRelatedWork W2734912394 @default.
- W3121095832 hasRelatedWork W2774891019 @default.
- W3121095832 hasRelatedWork W3022038857 @default.
- W3121095832 hasRelatedWork W3121095832 @default.
- W3121095832 hasRelatedWork W4200580761 @default.
- W3121095832 hasRelatedWork W4226170924 @default.
- W3121095832 hasRelatedWork W4287626175 @default.
- W3121095832 hasRelatedWork W4291288511 @default.
- W3121095832 hasRelatedWork W4319083788 @default.
- W3121095832 hasRelatedWork W3128776981 @default.
- W3121095832 isParatext "false" @default.
- W3121095832 isRetracted "false" @default.
- W3121095832 magId "3121095832" @default.
- W3121095832 workType "article" @default.