Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383108510> ?p ?o ?g. }
- W4383108510 abstract "Safety is one of the main challenges when applying learning-based motion controllers to practical robotic systems, especially when the dynamics of the robots and their surrounding dynamic environments are unknown. This issue is further exacerbated when the learned information is unreliable and inaccurate. In this paper, we aim to enhance the safety of learning-enabled mobile robots in dynamic environments from the perspective of distributionally robust optimization (DRO) and the unscented transform (UT). Our method infers the unknown dynamics of both the robot and the environment by adopting Gaussian process regression with an uncertainty propagation scheme based on UT to improve prediction accuracy. This leads to a novel learning-based model predictive control (MPC) method in which state information about both the robot and the environment is propagated via UT. The proposed method uses DRO to proactively limit the risk of collisions or other unsafe events in the presence of learning errors. However, the distributionally robust risk constraint is intractable because it involves a separate infinite-dimensional optimization problem. To overcome this challenge, we exploit UT with modern DRO techniques to replace the risk constraint with its simple upper bound. The performance and the utility of our method are demonstrated through simulations in autonomous driving scenarios, showing its capability to enhance safety and computational efficiency." @default.
- W4383108510 created "2023-07-05" @default.
- W4383108510 creator A5063507594 @default.
- W4383108510 creator A5082502066 @default.
- W4383108510 date "2023-05-29" @default.
- W4383108510 modified "2023-10-16" @default.
- W4383108510 title "Distributionally Robust Optimization with Unscented Transform for Learning-Based Motion Control in Dynamic Environments" @default.
- W4383108510 cites W1591375184 @default.
- W4383108510 cites W1749494163 @default.
- W4383108510 cites W1988994102 @default.
- W4383108510 cites W2019291268 @default.
- W4383108510 cites W2020426055 @default.
- W4383108510 cites W2020934227 @default.
- W4383108510 cites W2052190322 @default.
- W4383108510 cites W2105945651 @default.
- W4383108510 cites W2107802551 @default.
- W4383108510 cites W2125417745 @default.
- W4383108510 cites W2885972001 @default.
- W4383108510 cites W2897861898 @default.
- W4383108510 cites W2905838893 @default.
- W4383108510 cites W2954115742 @default.
- W4383108510 cites W2963167203 @default.
- W4383108510 cites W2963450292 @default.
- W4383108510 cites W2963732412 @default.
- W4383108510 cites W2963762522 @default.
- W4383108510 cites W2963945659 @default.
- W4383108510 cites W2969738732 @default.
- W4383108510 cites W2972428093 @default.
- W4383108510 cites W3021487874 @default.
- W4383108510 cites W3044582844 @default.
- W4383108510 cites W3047198505 @default.
- W4383108510 cites W3089935474 @default.
- W4383108510 cites W3105252106 @default.
- W4383108510 cites W3111862348 @default.
- W4383108510 cites W3129986830 @default.
- W4383108510 cites W3132905665 @default.
- W4383108510 cites W3166231878 @default.
- W4383108510 cites W3185684906 @default.
- W4383108510 cites W3195968524 @default.
- W4383108510 cites W3217053727 @default.
- W4383108510 cites W4205837603 @default.
- W4383108510 cites W4206101152 @default.
- W4383108510 cites W4293775970 @default.
- W4383108510 cites W3129641903 @default.
- W4383108510 doi "https://doi.org/10.1109/icra48891.2023.10161246" @default.
- W4383108510 hasPublicationYear "2023" @default.
- W4383108510 type Work @default.
- W4383108510 citedByCount "0" @default.
- W4383108510 crossrefType "proceedings-article" @default.
- W4383108510 hasAuthorship W4383108510A5063507594 @default.
- W4383108510 hasAuthorship W4383108510A5082502066 @default.
- W4383108510 hasConcept C11413529 @default.
- W4383108510 hasConcept C119857082 @default.
- W4383108510 hasConcept C121332964 @default.
- W4383108510 hasConcept C126255220 @default.
- W4383108510 hasConcept C127413603 @default.
- W4383108510 hasConcept C137836250 @default.
- W4383108510 hasConcept C154945302 @default.
- W4383108510 hasConcept C163716315 @default.
- W4383108510 hasConcept C165696696 @default.
- W4383108510 hasConcept C193254401 @default.
- W4383108510 hasConcept C2776036281 @default.
- W4383108510 hasConcept C33923547 @default.
- W4383108510 hasConcept C38652104 @default.
- W4383108510 hasConcept C41008148 @default.
- W4383108510 hasConcept C61326573 @default.
- W4383108510 hasConcept C62520636 @default.
- W4383108510 hasConcept C78519656 @default.
- W4383108510 hasConcept C90509273 @default.
- W4383108510 hasConcept C97541855 @default.
- W4383108510 hasConceptScore W4383108510C11413529 @default.
- W4383108510 hasConceptScore W4383108510C119857082 @default.
- W4383108510 hasConceptScore W4383108510C121332964 @default.
- W4383108510 hasConceptScore W4383108510C126255220 @default.
- W4383108510 hasConceptScore W4383108510C127413603 @default.
- W4383108510 hasConceptScore W4383108510C137836250 @default.
- W4383108510 hasConceptScore W4383108510C154945302 @default.
- W4383108510 hasConceptScore W4383108510C163716315 @default.
- W4383108510 hasConceptScore W4383108510C165696696 @default.
- W4383108510 hasConceptScore W4383108510C193254401 @default.
- W4383108510 hasConceptScore W4383108510C2776036281 @default.
- W4383108510 hasConceptScore W4383108510C33923547 @default.
- W4383108510 hasConceptScore W4383108510C38652104 @default.
- W4383108510 hasConceptScore W4383108510C41008148 @default.
- W4383108510 hasConceptScore W4383108510C61326573 @default.
- W4383108510 hasConceptScore W4383108510C62520636 @default.
- W4383108510 hasConceptScore W4383108510C78519656 @default.
- W4383108510 hasConceptScore W4383108510C90509273 @default.
- W4383108510 hasConceptScore W4383108510C97541855 @default.
- W4383108510 hasLocation W43831085101 @default.
- W4383108510 hasOpenAccess W4383108510 @default.
- W4383108510 hasPrimaryLocation W43831085101 @default.
- W4383108510 hasRelatedWork W2251221343 @default.
- W4383108510 hasRelatedWork W2800812001 @default.
- W4383108510 hasRelatedWork W3015523332 @default.
- W4383108510 hasRelatedWork W3022038857 @default.
- W4383108510 hasRelatedWork W3035069654 @default.
- W4383108510 hasRelatedWork W3149055374 @default.
- W4383108510 hasRelatedWork W3159863825 @default.
- W4383108510 hasRelatedWork W3167657283 @default.