Matches in SemOpenAlex for { <https://semopenalex.org/work/W2924895351> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2924895351 abstract "Robot navigation in mapless environment is one of the essential problems and challenges in mobile robots. Deep reinforcement learning is a promising technique to tackle the task of mapless navigation. Since reinforcement learning requires a lot of explorations, it is usually necessary to train the agent in the simulator and then migrate to the real environment. The big reality gap makes RGB image, the most common visual sensor, rarely used. In this paper we present a learning-based mapless motion planner by taking RGB images as visual inputs. Many parameters in end-to-end navigation network taking RGB images as visual input are used to extract visual features. Therefore, we decouple visual features extracted module from the reinforcement learning network to reduce the need of interactions between agent and environment. We use Variational Autoencoder (VAE) to encode the image, and input the obtained latent vector as low-dimensional visual features into the network together with the target and motion information, so that the sampling efficiency of the agent is greatly improved. We built simulation environment as robot navigation environment for algorithm comparison. In the test environment, the proposed method was compared with the end-to-end network, which proved its effectiveness and efficiency. The source code is available: https://github.com/marooncn/navbot." @default.
- W2924895351 created "2019-04-01" @default.
- W2924895351 creator A5000987583 @default.
- W2924895351 creator A5062679565 @default.
- W2924895351 creator A5076479076 @default.
- W2924895351 date "2019-03-24" @default.
- W2924895351 modified "2023-10-08" @default.
- W2924895351 title "Using RGB Image as Visual Input for Mapless Robot Navigation" @default.
- W2924895351 cites W1771410628 @default.
- W2924895351 cites W1959608418 @default.
- W2924895351 cites W2061562262 @default.
- W2924895351 cites W2121863487 @default.
- W2924895351 cites W2141125852 @default.
- W2924895351 cites W2145339207 @default.
- W2924895351 cites W2155968351 @default.
- W2924895351 cites W2156737235 @default.
- W2924895351 cites W2165150801 @default.
- W2924895351 cites W2173564293 @default.
- W2924895351 cites W2227909145 @default.
- W2924895351 cites W2290354866 @default.
- W2924895351 cites W2565555125 @default.
- W2924895351 cites W2766447205 @default.
- W2924895351 cites W2796447411 @default.
- W2924895351 cites W2884565639 @default.
- W2924895351 cites W2901136733 @default.
- W2924895351 cites W2962887844 @default.
- W2924895351 cites W2962954724 @default.
- W2924895351 cites W2963277051 @default.
- W2924895351 cites W2963403593 @default.
- W2924895351 cites W2963428623 @default.
- W2924895351 cites W2963523627 @default.
- W2924895351 cites W2963946945 @default.
- W2924895351 cites W2964043796 @default.
- W2924895351 cites W2964343197 @default.
- W2924895351 cites W2981954954 @default.
- W2924895351 cites W3124420883 @default.
- W2924895351 doi "https://doi.org/10.48550/arxiv.1903.09927" @default.
- W2924895351 hasPublicationYear "2019" @default.
- W2924895351 type Work @default.
- W2924895351 sameAs 2924895351 @default.
- W2924895351 citedByCount "3" @default.
- W2924895351 countsByYear W29248953512019 @default.
- W2924895351 countsByYear W29248953512020 @default.
- W2924895351 crossrefType "posted-content" @default.
- W2924895351 hasAuthorship W2924895351A5000987583 @default.
- W2924895351 hasAuthorship W2924895351A5062679565 @default.
- W2924895351 hasAuthorship W2924895351A5076479076 @default.
- W2924895351 hasBestOaLocation W29248953511 @default.
- W2924895351 hasConcept C101738243 @default.
- W2924895351 hasConcept C108583219 @default.
- W2924895351 hasConcept C115961682 @default.
- W2924895351 hasConcept C127413603 @default.
- W2924895351 hasConcept C154945302 @default.
- W2924895351 hasConcept C19966478 @default.
- W2924895351 hasConcept C201995342 @default.
- W2924895351 hasConcept C2777708103 @default.
- W2924895351 hasConcept C2780451532 @default.
- W2924895351 hasConcept C31972630 @default.
- W2924895351 hasConcept C41008148 @default.
- W2924895351 hasConcept C82990744 @default.
- W2924895351 hasConcept C90509273 @default.
- W2924895351 hasConcept C97541855 @default.
- W2924895351 hasConceptScore W2924895351C101738243 @default.
- W2924895351 hasConceptScore W2924895351C108583219 @default.
- W2924895351 hasConceptScore W2924895351C115961682 @default.
- W2924895351 hasConceptScore W2924895351C127413603 @default.
- W2924895351 hasConceptScore W2924895351C154945302 @default.
- W2924895351 hasConceptScore W2924895351C19966478 @default.
- W2924895351 hasConceptScore W2924895351C201995342 @default.
- W2924895351 hasConceptScore W2924895351C2777708103 @default.
- W2924895351 hasConceptScore W2924895351C2780451532 @default.
- W2924895351 hasConceptScore W2924895351C31972630 @default.
- W2924895351 hasConceptScore W2924895351C41008148 @default.
- W2924895351 hasConceptScore W2924895351C82990744 @default.
- W2924895351 hasConceptScore W2924895351C90509273 @default.
- W2924895351 hasConceptScore W2924895351C97541855 @default.
- W2924895351 hasLocation W29248953511 @default.
- W2924895351 hasOpenAccess W2924895351 @default.
- W2924895351 hasPrimaryLocation W29248953511 @default.
- W2924895351 hasRelatedWork W1941772210 @default.
- W2924895351 hasRelatedWork W2056979260 @default.
- W2924895351 hasRelatedWork W2096344081 @default.
- W2924895351 hasRelatedWork W2132132164 @default.
- W2924895351 hasRelatedWork W2892004916 @default.
- W2924895351 hasRelatedWork W2980357211 @default.
- W2924895351 hasRelatedWork W2980506548 @default.
- W2924895351 hasRelatedWork W2981828152 @default.
- W2924895351 hasRelatedWork W3158522902 @default.
- W2924895351 hasRelatedWork W4313023825 @default.
- W2924895351 isParatext "false" @default.
- W2924895351 isRetracted "false" @default.
- W2924895351 magId "2924895351" @default.
- W2924895351 workType "article" @default.