FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289549727> ?p ?o ?g. }

• W4289549727 endingPage "111971" @default.
• W4289549727 startingPage "111971" @default.
• W4289549727 abstract "Autonomous underwater vehicle (AUV) is playing a more and more important role in marine scientific research and resource exploration due to its flexibility. Recently, deep reinforcement learning (DRL) has been used to improve the autonomy of AUV. However, it is very time-consuming and even unpractical to define efficient reward functions for DRL to learn control policies in various tasks. In this paper, we implemented the generative adversarial imitation learning (GAIL) algorithm learning from demonstrated trajectories and proposed GA2IL learning from demonstrations and additional human rewards for AUV path following. We evaluated GAIL and our GA2IL method in a straight line following task and a sinusoids curve following task on the Gazebo platform extended to simulated underwater environments with AUV simulator of our lab. Both methods were compared to PPO—a classic traditional deep reinforcement learning from a predefined reward function, and a well-tuned PID controller. In addition, to evaluate the generalization of GAIL and our GA2IL method, we tested the trained control policies of the previous two tasks via GAIL and GA2IL in a new complex comb scan following task and a different sinusoids curve following task respectively. Our simulation results show AUV path following with GA2IL and GAIL can obtain a performance at a similar level to PPO and PID controller in both tasks. Moreover, GA2IL can generalize as well as PPO, adapting better to complex and different tasks than traditional PID controller." @default.
• W4289549727 created "2022-08-03" @default.
• W4289549727 creator A5001995630 @default.
• W4289549727 creator A5027747438 @default.
• W4289549727 creator A5043701064 @default.
• W4289549727 creator A5048299480 @default.
• W4289549727 creator A5059886289 @default.
• W4289549727 creator A5068870413 @default.
• W4289549727 creator A5072031992 @default.
• W4289549727 date "2022-09-01" @default.
• W4289549727 modified "2023-10-01" @default.
• W4289549727 title "Generative adversarial interactive imitation learning for path following of autonomous underwater vehicle" @default.
• W4289549727 cites W1999874108 @default.
• W4289549727 cites W2140246545 @default.
• W4289549727 cites W2145339207 @default.
• W4289549727 cites W2156869222 @default.
• W4289549727 cites W2169498096 @default.
• W4289549727 cites W2205612522 @default.
• W4289549727 cites W2410619805 @default.
• W4289549727 cites W2586026999 @default.
• W4289549727 cites W2766447205 @default.
• W4289549727 cites W2808470116 @default.
• W4289549727 cites W2911922016 @default.
• W4289549727 cites W2944766483 @default.
• W4289549727 cites W2963917788 @default.
• W4289549727 cites W2990747716 @default.
• W4289549727 cites W3004006877 @default.
• W4289549727 cites W3008337835 @default.
• W4289549727 cites W3034598088 @default.
• W4289549727 cites W3181364828 @default.
• W4289549727 cites W3184311107 @default.
• W4289549727 cites W3206733623 @default.
• W4289549727 cites W4200534645 @default.
• W4289549727 cites W4205260620 @default.
• W4289549727 cites W4206032480 @default.
• W4289549727 doi "https://doi.org/10.1016/j.oceaneng.2022.111971" @default.
• W4289549727 hasPublicationYear "2022" @default.
• W4289549727 type Work @default.
• W4289549727 citedByCount "3" @default.
• W4289549727 countsByYear W42895497272022 @default.
• W4289549727 countsByYear W42895497272023 @default.
• W4289549727 crossrefType "journal-article" @default.
• W4289549727 hasAuthorship W4289549727A5001995630 @default.
• W4289549727 hasAuthorship W4289549727A5027747438 @default.
• W4289549727 hasAuthorship W4289549727A5043701064 @default.
• W4289549727 hasAuthorship W4289549727A5048299480 @default.
• W4289549727 hasAuthorship W4289549727A5059886289 @default.
• W4289549727 hasAuthorship W4289549727A5068870413 @default.
• W4289549727 hasAuthorship W4289549727A5072031992 @default.
• W4289549727 hasConcept C105795698 @default.
• W4289549727 hasConcept C111368507 @default.
• W4289549727 hasConcept C119857082 @default.
• W4289549727 hasConcept C126388530 @default.
• W4289549727 hasConcept C127313418 @default.
• W4289549727 hasConcept C127413603 @default.
• W4289549727 hasConcept C133731056 @default.
• W4289549727 hasConcept C134306372 @default.
• W4289549727 hasConcept C154945302 @default.
• W4289549727 hasConcept C15744967 @default.
• W4289549727 hasConcept C177148314 @default.
• W4289549727 hasConcept C199360897 @default.
• W4289549727 hasConcept C201995342 @default.
• W4289549727 hasConcept C203479927 @default.
• W4289549727 hasConcept C2777735758 @default.
• W4289549727 hasConcept C2780451532 @default.
• W4289549727 hasConcept C2780598303 @default.
• W4289549727 hasConcept C33923547 @default.
• W4289549727 hasConcept C39890363 @default.
• W4289549727 hasConcept C41008148 @default.
• W4289549727 hasConcept C47116090 @default.
• W4289549727 hasConcept C536315585 @default.
• W4289549727 hasConcept C6557445 @default.
• W4289549727 hasConcept C77805123 @default.
• W4289549727 hasConcept C86803240 @default.
• W4289549727 hasConcept C97541855 @default.
• W4289549727 hasConcept C98083399 @default.
• W4289549727 hasConceptScore W4289549727C105795698 @default.
• W4289549727 hasConceptScore W4289549727C111368507 @default.
• W4289549727 hasConceptScore W4289549727C119857082 @default.
• W4289549727 hasConceptScore W4289549727C126388530 @default.
• W4289549727 hasConceptScore W4289549727C127313418 @default.
• W4289549727 hasConceptScore W4289549727C127413603 @default.
• W4289549727 hasConceptScore W4289549727C133731056 @default.
• W4289549727 hasConceptScore W4289549727C134306372 @default.
• W4289549727 hasConceptScore W4289549727C154945302 @default.
• W4289549727 hasConceptScore W4289549727C15744967 @default.
• W4289549727 hasConceptScore W4289549727C177148314 @default.
• W4289549727 hasConceptScore W4289549727C199360897 @default.
• W4289549727 hasConceptScore W4289549727C201995342 @default.
• W4289549727 hasConceptScore W4289549727C203479927 @default.
• W4289549727 hasConceptScore W4289549727C2777735758 @default.
• W4289549727 hasConceptScore W4289549727C2780451532 @default.
• W4289549727 hasConceptScore W4289549727C2780598303 @default.
• W4289549727 hasConceptScore W4289549727C33923547 @default.
• W4289549727 hasConceptScore W4289549727C39890363 @default.
• W4289549727 hasConceptScore W4289549727C41008148 @default.
• W4289549727 hasConceptScore W4289549727C47116090 @default.
• W4289549727 hasConceptScore W4289549727C536315585 @default.

• next