Matches in SemOpenAlex for { <https://semopenalex.org/work/W3149383640> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3149383640 abstract "This paper presents a sensor-level mapless collision avoidance algorithm for use in mobile robots that map raw sensor data to linear and angular velocities and navigate in an unknown environment without a map. An efficient training strategy is proposed to allow a robot to learn from both human experience data and self-exploratory data. A game format simulation framework is designed to allow the human player to tele-operate the mobile robot to a goal and human action is also scored using the reward function. Both human player data and self-playing data are sampled using prioritized experience replay algorithm. The proposed algorithm and training strategy have been evaluated in two different experimental configurations: Environment 1, a simulated cluttered environment, and Environment 2, a simulated corridor environment, to investigate the performance. It was demonstrated that the proposed method achieved the same level of reward using only 16% of the training steps required by the standard Deep Deterministic Policy Gradient (DDPG) method in Environment 1 and 20% of that in Environment 2. In the evaluation of 20 random missions, the proposed method achieved no collision in less than 2 h and 2.5 h of training time in the two Gazebo environments respectively. The method also generated smoother trajectories than DDPG. The proposed method has also been implemented on a real robot in the real-world environment for performance evaluation. We can confirm that the trained model with the simulation software can be directly applied into the real-world scenario without further fine-tuning, further demonstrating its higher robustness than DDPG. The video and code are available: https://youtu.be/BmwxevgsdGc https://github.com/hanlinniu/turtlebot3_ddpg_collision_avoidance" @default.
- W3149383640 created "2021-04-13" @default.
- W3149383640 creator A5005614248 @default.
- W3149383640 creator A5010068577 @default.
- W3149383640 creator A5011590665 @default.
- W3149383640 creator A5024320684 @default.
- W3149383640 creator A5055149475 @default.
- W3149383640 creator A5068175770 @default.
- W3149383640 date "2021-01-11" @default.
- W3149383640 modified "2023-10-05" @default.
- W3149383640 title "Accelerated Sim-to-Real Deep Reinforcement Learning: Learning Collision Avoidance from Human Player" @default.
- W3149383640 cites W1923344279 @default.
- W3149383640 cites W2604216058 @default.
- W3149383640 cites W2890001928 @default.
- W3149383640 cites W2891234582 @default.
- W3149383640 cites W2908713228 @default.
- W3149383640 cites W2908846937 @default.
- W3149383640 cites W2909564046 @default.
- W3149383640 cites W2909710443 @default.
- W3149383640 cites W2910367420 @default.
- W3149383640 cites W2963019567 @default.
- W3149383640 cites W2963428623 @default.
- W3149383640 cites W2963821308 @default.
- W3149383640 cites W2964319688 @default.
- W3149383640 cites W2967847744 @default.
- W3149383640 doi "https://doi.org/10.1109/ieeeconf49454.2021.9382693" @default.
- W3149383640 hasPublicationYear "2021" @default.
- W3149383640 type Work @default.
- W3149383640 sameAs 3149383640 @default.
- W3149383640 citedByCount "15" @default.
- W3149383640 countsByYear W31493836402021 @default.
- W3149383640 countsByYear W31493836402022 @default.
- W3149383640 countsByYear W31493836402023 @default.
- W3149383640 crossrefType "proceedings-article" @default.
- W3149383640 hasAuthorship W3149383640A5005614248 @default.
- W3149383640 hasAuthorship W3149383640A5010068577 @default.
- W3149383640 hasAuthorship W3149383640A5011590665 @default.
- W3149383640 hasAuthorship W3149383640A5024320684 @default.
- W3149383640 hasAuthorship W3149383640A5055149475 @default.
- W3149383640 hasAuthorship W3149383640A5068175770 @default.
- W3149383640 hasBestOaLocation W31493836402 @default.
- W3149383640 hasConcept C121704057 @default.
- W3149383640 hasConcept C154945302 @default.
- W3149383640 hasConcept C19966478 @default.
- W3149383640 hasConcept C2780864053 @default.
- W3149383640 hasConcept C31972630 @default.
- W3149383640 hasConcept C38652104 @default.
- W3149383640 hasConcept C41008148 @default.
- W3149383640 hasConcept C44154836 @default.
- W3149383640 hasConcept C79403827 @default.
- W3149383640 hasConcept C90509273 @default.
- W3149383640 hasConcept C97541855 @default.
- W3149383640 hasConceptScore W3149383640C121704057 @default.
- W3149383640 hasConceptScore W3149383640C154945302 @default.
- W3149383640 hasConceptScore W3149383640C19966478 @default.
- W3149383640 hasConceptScore W3149383640C2780864053 @default.
- W3149383640 hasConceptScore W3149383640C31972630 @default.
- W3149383640 hasConceptScore W3149383640C38652104 @default.
- W3149383640 hasConceptScore W3149383640C41008148 @default.
- W3149383640 hasConceptScore W3149383640C44154836 @default.
- W3149383640 hasConceptScore W3149383640C79403827 @default.
- W3149383640 hasConceptScore W3149383640C90509273 @default.
- W3149383640 hasConceptScore W3149383640C97541855 @default.
- W3149383640 hasLocation W31493836401 @default.
- W3149383640 hasLocation W31493836402 @default.
- W3149383640 hasOpenAccess W3149383640 @default.
- W3149383640 hasPrimaryLocation W31493836401 @default.
- W3149383640 hasRelatedWork W2047788632 @default.
- W3149383640 hasRelatedWork W2118648141 @default.
- W3149383640 hasRelatedWork W2123436641 @default.
- W3149383640 hasRelatedWork W2123582700 @default.
- W3149383640 hasRelatedWork W2151698195 @default.
- W3149383640 hasRelatedWork W2742483371 @default.
- W3149383640 hasRelatedWork W2756881483 @default.
- W3149383640 hasRelatedWork W2963821308 @default.
- W3149383640 hasRelatedWork W2965672371 @default.
- W3149383640 hasRelatedWork W3108596256 @default.
- W3149383640 isParatext "false" @default.
- W3149383640 isRetracted "false" @default.
- W3149383640 magId "3149383640" @default.
- W3149383640 workType "article" @default.