Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383109639> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W4383109639 abstract "Deep learning-based grasp prediction models have become an industry standard for robotic bin-picking systems. To maximize pick success, production environments are often equipped with several end-effector tools that can be swapped on-the-fly, based on the target object. Tool-change, however, takes time. Choosing the order of grasps to perform, and corresponding tool-change actions, can improve system throughput; this is the topic of our work. The main challenge in planning tool change is uncertainty - we typically cannot see objects in the bin that are currently occluded. Inspired by queuing and admission control problems, we model the problem as a Markov Decision Process (MDP), where the goal is to maximize expected throughput, and we pursue an approximate solution based on model predictive control, where at each time step we plan based only on the currently visible objects. Special to our method is the idea of void zones, which are geometrical boundaries in which an unknown object will be present, and therefore cannot be accounted for during planning. Our planning problem can be solved using integer linear programming (ILP). However, we find that an approximate solution based on sparse tree search yields near optimal performance at a fraction of the time. Another question that we explore is how to measure the performance of tool-change planning: we find that throughput alone can fail to capture delicate and smooth behavior, and propose a principled alternative. Finally, we demonstrate our algorithms on both synthetic and real world bin picking tasks." @default.
- W4383109639 created "2023-07-05" @default.
- W4383109639 creator A5006403951 @default.
- W4383109639 creator A5020699288 @default.
- W4383109639 creator A5036450155 @default.
- W4383109639 creator A5037673735 @default.
- W4383109639 date "2023-05-29" @default.
- W4383109639 modified "2023-09-26" @default.
- W4383109639 title "Online Tool Selection with Learned Grasp Prediction Models" @default.
- W4383109639 cites W1999156278 @default.
- W4383109639 cites W2049287714 @default.
- W4383109639 cites W2158782408 @default.
- W4383109639 cites W2399100674 @default.
- W4383109639 cites W2565639579 @default.
- W4383109639 cites W2910474428 @default.
- W4383109639 cites W2962746398 @default.
- W4383109639 cites W3089842364 @default.
- W4383109639 cites W4383109639 @default.
- W4383109639 doi "https://doi.org/10.1109/icra48891.2023.10160952" @default.
- W4383109639 hasPublicationYear "2023" @default.
- W4383109639 type Work @default.
- W4383109639 citedByCount "1" @default.
- W4383109639 countsByYear W43831096392023 @default.
- W4383109639 crossrefType "proceedings-article" @default.
- W4383109639 hasAuthorship W4383109639A5006403951 @default.
- W4383109639 hasAuthorship W4383109639A5020699288 @default.
- W4383109639 hasAuthorship W4383109639A5036450155 @default.
- W4383109639 hasAuthorship W4383109639A5037673735 @default.
- W4383109639 hasConcept C105795698 @default.
- W4383109639 hasConcept C106189395 @default.
- W4383109639 hasConcept C11413529 @default.
- W4383109639 hasConcept C119857082 @default.
- W4383109639 hasConcept C126255220 @default.
- W4383109639 hasConcept C154945302 @default.
- W4383109639 hasConcept C156273044 @default.
- W4383109639 hasConcept C157764524 @default.
- W4383109639 hasConcept C159886148 @default.
- W4383109639 hasConcept C171268870 @default.
- W4383109639 hasConcept C199360897 @default.
- W4383109639 hasConcept C33923547 @default.
- W4383109639 hasConcept C41008148 @default.
- W4383109639 hasConcept C41045048 @default.
- W4383109639 hasConcept C555944384 @default.
- W4383109639 hasConcept C56086750 @default.
- W4383109639 hasConcept C76155785 @default.
- W4383109639 hasConceptScore W4383109639C105795698 @default.
- W4383109639 hasConceptScore W4383109639C106189395 @default.
- W4383109639 hasConceptScore W4383109639C11413529 @default.
- W4383109639 hasConceptScore W4383109639C119857082 @default.
- W4383109639 hasConceptScore W4383109639C126255220 @default.
- W4383109639 hasConceptScore W4383109639C154945302 @default.
- W4383109639 hasConceptScore W4383109639C156273044 @default.
- W4383109639 hasConceptScore W4383109639C157764524 @default.
- W4383109639 hasConceptScore W4383109639C159886148 @default.
- W4383109639 hasConceptScore W4383109639C171268870 @default.
- W4383109639 hasConceptScore W4383109639C199360897 @default.
- W4383109639 hasConceptScore W4383109639C33923547 @default.
- W4383109639 hasConceptScore W4383109639C41008148 @default.
- W4383109639 hasConceptScore W4383109639C41045048 @default.
- W4383109639 hasConceptScore W4383109639C555944384 @default.
- W4383109639 hasConceptScore W4383109639C56086750 @default.
- W4383109639 hasConceptScore W4383109639C76155785 @default.
- W4383109639 hasFunder F4320320300 @default.
- W4383109639 hasLocation W43831096391 @default.
- W4383109639 hasOpenAccess W4383109639 @default.
- W4383109639 hasPrimaryLocation W43831096391 @default.
- W4383109639 hasRelatedWork W1486656814 @default.
- W4383109639 hasRelatedWork W1583652181 @default.
- W4383109639 hasRelatedWork W1982719520 @default.
- W4383109639 hasRelatedWork W2004060844 @default.
- W4383109639 hasRelatedWork W2321338106 @default.
- W4383109639 hasRelatedWork W2369756650 @default.
- W4383109639 hasRelatedWork W2905055379 @default.
- W4383109639 hasRelatedWork W3172764889 @default.
- W4383109639 hasRelatedWork W4310470542 @default.
- W4383109639 hasRelatedWork W4321504798 @default.
- W4383109639 isParatext "false" @default.
- W4383109639 isRetracted "false" @default.
- W4383109639 workType "article" @default.