Matches in SemOpenAlex for { <https://semopenalex.org/work/W4380994003> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4380994003 abstract "In recent years, Deep Reinforcement Learning (DRL) has emerged as a promising method for robot collision avoidance. However, such DRL models often come with limitations, such as adapting effectively to structured environments containing various pedestrians. In order to solve this difficulty, previous research has attempted a few approaches, including training an end-to-end solution by integrating a waypoint planner with DRL and developing a multimodal solution to mitigate the drawbacks of the DRL model. However, these approaches have encountered several issues, including slow training times, scalability challenges, and poor coordination among different models. To address these challenges, this paper introduces a novel approach called evolutionary curriculum training to tackle these challenges. The primary goal of evolutionary curriculum training is to evaluate the collision avoidance model's competency in various scenarios and create curricula to enhance its insufficient skills. The paper introduces an innovative evaluation technique to assess the DRL model's performance in navigating structured maps and avoiding dynamic obstacles. Additionally, an evolutionary training environment generates all the curriculum to improve the DRL model's inadequate skills tested in the previous evaluation. We benchmark the performance of our model across five structured environments to validate the hypothesis that this evolutionary training environment leads to a higher success rate and a lower average number of collisions. Further details and results at our project website." @default.
- W4380994003 created "2023-06-17" @default.
- W4380994003 creator A5000889755 @default.
- W4380994003 creator A5014213647 @default.
- W4380994003 creator A5028834865 @default.
- W4380994003 creator A5080052891 @default.
- W4380994003 date "2023-06-15" @default.
- W4380994003 modified "2023-09-26" @default.
- W4380994003 title "Evolutionary Curriculum Training for DRL-Based Navigation Systems" @default.
- W4380994003 doi "https://doi.org/10.48550/arxiv.2306.08870" @default.
- W4380994003 hasPublicationYear "2023" @default.
- W4380994003 type Work @default.
- W4380994003 citedByCount "0" @default.
- W4380994003 crossrefType "posted-content" @default.
- W4380994003 hasAuthorship W4380994003A5000889755 @default.
- W4380994003 hasAuthorship W4380994003A5014213647 @default.
- W4380994003 hasAuthorship W4380994003A5028834865 @default.
- W4380994003 hasAuthorship W4380994003A5080052891 @default.
- W4380994003 hasBestOaLocation W43809940031 @default.
- W4380994003 hasConcept C119857082 @default.
- W4380994003 hasConcept C121332964 @default.
- W4380994003 hasConcept C13280743 @default.
- W4380994003 hasConcept C153294291 @default.
- W4380994003 hasConcept C154945302 @default.
- W4380994003 hasConcept C15744967 @default.
- W4380994003 hasConcept C185798385 @default.
- W4380994003 hasConcept C19417346 @default.
- W4380994003 hasConcept C205649164 @default.
- W4380994003 hasConcept C2776999362 @default.
- W4380994003 hasConcept C2777211547 @default.
- W4380994003 hasConcept C2781271823 @default.
- W4380994003 hasConcept C41008148 @default.
- W4380994003 hasConcept C47177190 @default.
- W4380994003 hasConcept C48044578 @default.
- W4380994003 hasConcept C77088390 @default.
- W4380994003 hasConcept C79403827 @default.
- W4380994003 hasConcept C97541855 @default.
- W4380994003 hasConceptScore W4380994003C119857082 @default.
- W4380994003 hasConceptScore W4380994003C121332964 @default.
- W4380994003 hasConceptScore W4380994003C13280743 @default.
- W4380994003 hasConceptScore W4380994003C153294291 @default.
- W4380994003 hasConceptScore W4380994003C154945302 @default.
- W4380994003 hasConceptScore W4380994003C15744967 @default.
- W4380994003 hasConceptScore W4380994003C185798385 @default.
- W4380994003 hasConceptScore W4380994003C19417346 @default.
- W4380994003 hasConceptScore W4380994003C205649164 @default.
- W4380994003 hasConceptScore W4380994003C2776999362 @default.
- W4380994003 hasConceptScore W4380994003C2777211547 @default.
- W4380994003 hasConceptScore W4380994003C2781271823 @default.
- W4380994003 hasConceptScore W4380994003C41008148 @default.
- W4380994003 hasConceptScore W4380994003C47177190 @default.
- W4380994003 hasConceptScore W4380994003C48044578 @default.
- W4380994003 hasConceptScore W4380994003C77088390 @default.
- W4380994003 hasConceptScore W4380994003C79403827 @default.
- W4380994003 hasConceptScore W4380994003C97541855 @default.
- W4380994003 hasLocation W43809940031 @default.
- W4380994003 hasOpenAccess W4380994003 @default.
- W4380994003 hasPrimaryLocation W43809940031 @default.
- W4380994003 hasRelatedWork W112744582 @default.
- W4380994003 hasRelatedWork W1992807924 @default.
- W4380994003 hasRelatedWork W2740695633 @default.
- W4380994003 hasRelatedWork W2789601449 @default.
- W4380994003 hasRelatedWork W3022038857 @default.
- W4380994003 hasRelatedWork W3034514558 @default.
- W4380994003 hasRelatedWork W3132110306 @default.
- W4380994003 hasRelatedWork W3217340113 @default.
- W4380994003 hasRelatedWork W4313484441 @default.
- W4380994003 hasRelatedWork W4319083788 @default.
- W4380994003 isParatext "false" @default.
- W4380994003 isRetracted "false" @default.
- W4380994003 workType "article" @default.