Matches in SemOpenAlex for { <https://semopenalex.org/work/W2959091704> ?p ?o ?g. }
- W2959091704 endingPage "261" @default.
- W2959091704 startingPage "249" @default.
- W2959091704 abstract "It is vital for mobile robots to achieve safe autonomous steering in various changing environments. In this paper, a novel end-to-end network architecture is proposed for mobile robots to learn steering autonomously through deep reinforcement learning. Specifically, two sets of feature representations are first extracted from the depth inputs through two different input streams. The acquired features are then merged together to derive both linear and angular actions simultaneously. Moreover, a new action selection strategy is also introduced to achieve motion filtering by taking the consistency in angular velocity into account. Besides, in addition to the extrinsic rewards, the intrinsic bonuses are also adopted during training to improve the exploration capability. Furthermore, it is worth noting the proposed model is readily transferable from the simple virtual training environment to much more complicated real-world scenarios so that no further fine-tuning is required for real deployment. Compared to the existing methods, the proposed method demonstrates significant superiority in terms of average reward, convergence speed, success rate, and generalization capability. In addition, it exhibits outstanding performance in various cluttered real-world environments containing both static and dynamic obstacles. A video of our experiments can be found at https://youtu.be/19jrQGG1oCU." @default.
- W2959091704 created "2019-07-23" @default.
- W2959091704 creator A5026848789 @default.
- W2959091704 creator A5035767152 @default.
- W2959091704 creator A5038637903 @default.
- W2959091704 creator A5080876523 @default.
- W2959091704 date "2021-06-01" @default.
- W2959091704 modified "2023-10-04" @default.
- W2959091704 title "BND*-DDQN: Learn to Steer Autonomously Through Deep Reinforcement Learning" @default.
- W2959091704 cites W1522734439 @default.
- W2959091704 cites W157606319 @default.
- W2959091704 cites W2034806191 @default.
- W2959091704 cites W2091417852 @default.
- W2959091704 cites W2101524054 @default.
- W2959091704 cites W2111481694 @default.
- W2959091704 cites W2145339207 @default.
- W2959091704 cites W2146150411 @default.
- W2959091704 cites W2167340365 @default.
- W2959091704 cites W2344034899 @default.
- W2959091704 cites W2573311857 @default.
- W2959091704 cites W2595700172 @default.
- W2959091704 cites W2611290840 @default.
- W2959091704 cites W2737529802 @default.
- W2959091704 cites W2768393699 @default.
- W2959091704 cites W2795561664 @default.
- W2959091704 cites W2805965406 @default.
- W2959091704 cites W2811406095 @default.
- W2959091704 cites W2883429621 @default.
- W2959091704 cites W2893600742 @default.
- W2959091704 cites W2898417779 @default.
- W2959091704 cites W2898994065 @default.
- W2959091704 cites W2899529983 @default.
- W2959091704 cites W2944200650 @default.
- W2959091704 cites W2962887844 @default.
- W2959091704 cites W2962894046 @default.
- W2959091704 cites W2962954724 @default.
- W2959091704 cites W2962957005 @default.
- W2959091704 cites W2963019567 @default.
- W2959091704 cites W2963129648 @default.
- W2959091704 cites W2963155035 @default.
- W2959091704 cites W2963232050 @default.
- W2959091704 cites W2963428623 @default.
- W2959091704 cites W2963523627 @default.
- W2959091704 cites W2963524571 @default.
- W2959091704 cites W2963591054 @default.
- W2959091704 cites W2963821308 @default.
- W2959091704 cites W3098035776 @default.
- W2959091704 cites W3100995110 @default.
- W2959091704 doi "https://doi.org/10.1109/tcds.2019.2928820" @default.
- W2959091704 hasPublicationYear "2021" @default.
- W2959091704 type Work @default.
- W2959091704 sameAs 2959091704 @default.
- W2959091704 citedByCount "12" @default.
- W2959091704 countsByYear W29590917042020 @default.
- W2959091704 countsByYear W29590917042021 @default.
- W2959091704 countsByYear W29590917042022 @default.
- W2959091704 countsByYear W29590917042023 @default.
- W2959091704 crossrefType "journal-article" @default.
- W2959091704 hasAuthorship W2959091704A5026848789 @default.
- W2959091704 hasAuthorship W2959091704A5035767152 @default.
- W2959091704 hasAuthorship W2959091704A5038637903 @default.
- W2959091704 hasAuthorship W2959091704A5080876523 @default.
- W2959091704 hasBestOaLocation W29590917042 @default.
- W2959091704 hasConcept C105339364 @default.
- W2959091704 hasConcept C111919701 @default.
- W2959091704 hasConcept C134306372 @default.
- W2959091704 hasConcept C138885662 @default.
- W2959091704 hasConcept C154945302 @default.
- W2959091704 hasConcept C177148314 @default.
- W2959091704 hasConcept C19966478 @default.
- W2959091704 hasConcept C2776401178 @default.
- W2959091704 hasConcept C2776436953 @default.
- W2959091704 hasConcept C33923547 @default.
- W2959091704 hasConcept C41008148 @default.
- W2959091704 hasConcept C41895202 @default.
- W2959091704 hasConcept C90509273 @default.
- W2959091704 hasConcept C97541855 @default.
- W2959091704 hasConceptScore W2959091704C105339364 @default.
- W2959091704 hasConceptScore W2959091704C111919701 @default.
- W2959091704 hasConceptScore W2959091704C134306372 @default.
- W2959091704 hasConceptScore W2959091704C138885662 @default.
- W2959091704 hasConceptScore W2959091704C154945302 @default.
- W2959091704 hasConceptScore W2959091704C177148314 @default.
- W2959091704 hasConceptScore W2959091704C19966478 @default.
- W2959091704 hasConceptScore W2959091704C2776401178 @default.
- W2959091704 hasConceptScore W2959091704C2776436953 @default.
- W2959091704 hasConceptScore W2959091704C33923547 @default.
- W2959091704 hasConceptScore W2959091704C41008148 @default.
- W2959091704 hasConceptScore W2959091704C41895202 @default.
- W2959091704 hasConceptScore W2959091704C90509273 @default.
- W2959091704 hasConceptScore W2959091704C97541855 @default.
- W2959091704 hasFunder F4320320671 @default.
- W2959091704 hasIssue "2" @default.
- W2959091704 hasLocation W29590917041 @default.
- W2959091704 hasLocation W29590917042 @default.
- W2959091704 hasLocation W29590917043 @default.
- W2959091704 hasLocation W29590917044 @default.
- W2959091704 hasOpenAccess W2959091704 @default.