Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313854493> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W4313854493 abstract "There has been a recent interest in employing reinforcement learning for training end-to-end goal-driven robot navigation policies. However, implementing reinforcement learning in end-to-end navigation may result in inefficient policies that exhibit redundant turning actions when attempting to avoid obstacles. This work proposes a two branches network to learn efficient policies with less turning action when robots cross the obstacles. We first employ supervised learning to train a robot action classification network with optical flow. We then combine this classifier with an RGBD optical encoder to develop an action-decision network. Ultimately, we evaluate our approach in a visually realistic simulation environment. The results show that our method can reduce unnecessary steering actions and improve efficiency while ensuring navigation capabilities. We further show that our approach can reduce energy consumption during navigation and extend the robot's work time. Experiment results in the iGibson® simulator over hand-made paths reveal that our method can reduce 13.1% of the action number in the training set and 12.9% in the testing set compared with the baseline approaches. It also can reduce 8.3% energy consumption in the training set and 9.6% in the testing set and only has a 4.2% and 8.1% difference compared with the human path." @default.
- W4313854493 created "2023-01-10" @default.
- W4313854493 creator A5015998155 @default.
- W4313854493 creator A5032580266 @default.
- W4313854493 date "2022-12-10" @default.
- W4313854493 modified "2023-10-14" @default.
- W4313854493 title "End-to-End Efficient Indoor Navigation with Optical Flow" @default.
- W4313854493 cites W1530958058 @default.
- W4313854493 cites W1979266466 @default.
- W4313854493 cites W2143864104 @default.
- W4313854493 cites W2146203184 @default.
- W4313854493 cites W2342662179 @default.
- W4313854493 cites W2432964524 @default.
- W4313854493 cites W2768523414 @default.
- W4313854493 cites W2792887144 @default.
- W4313854493 cites W2905683736 @default.
- W4313854493 cites W2912063360 @default.
- W4313854493 cites W2962887844 @default.
- W4313854493 cites W2963428623 @default.
- W4313854493 cites W2963523627 @default.
- W4313854493 cites W2963775820 @default.
- W4313854493 cites W2964156315 @default.
- W4313854493 cites W2999770866 @default.
- W4313854493 cites W3009928773 @default.
- W4313854493 cites W3102327032 @default.
- W4313854493 cites W3103648783 @default.
- W4313854493 cites W3130821023 @default.
- W4313854493 cites W3192162805 @default.
- W4313854493 cites W764651262 @default.
- W4313854493 doi "https://doi.org/10.1109/icsai57119.2022.10005455" @default.
- W4313854493 hasPublicationYear "2022" @default.
- W4313854493 type Work @default.
- W4313854493 citedByCount "0" @default.
- W4313854493 crossrefType "proceedings-article" @default.
- W4313854493 hasAuthorship W4313854493A5015998155 @default.
- W4313854493 hasAuthorship W4313854493A5032580266 @default.
- W4313854493 hasConcept C111919701 @default.
- W4313854493 hasConcept C115961682 @default.
- W4313854493 hasConcept C118505674 @default.
- W4313854493 hasConcept C119599485 @default.
- W4313854493 hasConcept C127413603 @default.
- W4313854493 hasConcept C154945302 @default.
- W4313854493 hasConcept C155542232 @default.
- W4313854493 hasConcept C177264268 @default.
- W4313854493 hasConcept C199360897 @default.
- W4313854493 hasConcept C2777735758 @default.
- W4313854493 hasConcept C2780165032 @default.
- W4313854493 hasConcept C31258907 @default.
- W4313854493 hasConcept C41008148 @default.
- W4313854493 hasConcept C74296488 @default.
- W4313854493 hasConcept C79403827 @default.
- W4313854493 hasConcept C90509273 @default.
- W4313854493 hasConcept C95623464 @default.
- W4313854493 hasConcept C97541855 @default.
- W4313854493 hasConceptScore W4313854493C111919701 @default.
- W4313854493 hasConceptScore W4313854493C115961682 @default.
- W4313854493 hasConceptScore W4313854493C118505674 @default.
- W4313854493 hasConceptScore W4313854493C119599485 @default.
- W4313854493 hasConceptScore W4313854493C127413603 @default.
- W4313854493 hasConceptScore W4313854493C154945302 @default.
- W4313854493 hasConceptScore W4313854493C155542232 @default.
- W4313854493 hasConceptScore W4313854493C177264268 @default.
- W4313854493 hasConceptScore W4313854493C199360897 @default.
- W4313854493 hasConceptScore W4313854493C2777735758 @default.
- W4313854493 hasConceptScore W4313854493C2780165032 @default.
- W4313854493 hasConceptScore W4313854493C31258907 @default.
- W4313854493 hasConceptScore W4313854493C41008148 @default.
- W4313854493 hasConceptScore W4313854493C74296488 @default.
- W4313854493 hasConceptScore W4313854493C79403827 @default.
- W4313854493 hasConceptScore W4313854493C90509273 @default.
- W4313854493 hasConceptScore W4313854493C95623464 @default.
- W4313854493 hasConceptScore W4313854493C97541855 @default.
- W4313854493 hasLocation W43138544931 @default.
- W4313854493 hasOpenAccess W4313854493 @default.
- W4313854493 hasPrimaryLocation W43138544931 @default.
- W4313854493 hasRelatedWork W1561867011 @default.
- W4313854493 hasRelatedWork W1562959674 @default.
- W4313854493 hasRelatedWork W2056851291 @default.
- W4313854493 hasRelatedWork W2066023933 @default.
- W4313854493 hasRelatedWork W2169276416 @default.
- W4313854493 hasRelatedWork W2356875448 @default.
- W4313854493 hasRelatedWork W2923653485 @default.
- W4313854493 hasRelatedWork W3084370450 @default.
- W4313854493 hasRelatedWork W3149716236 @default.
- W4313854493 hasRelatedWork W4311427762 @default.
- W4313854493 isParatext "false" @default.
- W4313854493 isRetracted "false" @default.
- W4313854493 workType "article" @default.