Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034731205> ?p ?o ?g. }
- W3034731205 abstract "Complex object manipulation tasks often span over long sequences of operations. Task planning over long-time horizons is a challenging and open problem in robotics, and its complexity grows exponentially with an increasing number of subtasks. In this paper we present a deep learning network that learns dependencies and transitions across subtasks solely from a set of demonstration videos. We represent each subtask as an action symbol (e.g. move cup), and show that these symbols can be learned and predicted directly from image observations. Learning from demonstrations and visual observations are two main pillars of our approach. The former makes the learning tractable as it provides the network with information about the most frequent transitions and relevant dependency between subtasks (instead of exploring all possible combination), while the latter allows the network to continuously monitor the task progress and thus to interactively adapt to changes in the environment. We evaluate our framework on two long horizon tasks: (1) block stacking of puzzle pieces being executed by humans, and (2) a robot manipulation task involving pick and place of objects and sliding a cabinet door with a 7-DoF robot arm. We show that complex plans can be carried out when executing the robotic task and the robot can interactively adapt to changes in the environment and recover from failure cases." @default.
- W3034731205 created "2020-06-19" @default.
- W3034731205 creator A5022418359 @default.
- W3034731205 creator A5064265174 @default.
- W3034731205 creator A5065802887 @default.
- W3034731205 creator A5088777896 @default.
- W3034731205 date "2020-06-08" @default.
- W3034731205 modified "2023-09-27" @default.
- W3034731205 title "Modeling Long-horizon Tasks as Sequential Interaction Landscapes." @default.
- W3034731205 cites W1539716820 @default.
- W3034731205 cites W1570540164 @default.
- W3034731205 cites W1858576077 @default.
- W3034731205 cites W1920293286 @default.
- W3034731205 cites W1952489873 @default.
- W3034731205 cites W1988650444 @default.
- W3034731205 cites W1999167988 @default.
- W3034731205 cites W2020149918 @default.
- W3034731205 cites W2022760091 @default.
- W3034731205 cites W2038937121 @default.
- W3034731205 cites W2063471043 @default.
- W3034731205 cites W2064851185 @default.
- W3034731205 cites W2075577325 @default.
- W3034731205 cites W2097856935 @default.
- W3034731205 cites W2108579172 @default.
- W3034731205 cites W2111534926 @default.
- W3034731205 cites W2126574503 @default.
- W3034731205 cites W2129202194 @default.
- W3034731205 cites W2130942839 @default.
- W3034731205 cites W2132467020 @default.
- W3034731205 cites W2135319191 @default.
- W3034731205 cites W2135639338 @default.
- W3034731205 cites W2145339207 @default.
- W3034731205 cites W2148933384 @default.
- W3034731205 cites W2157331557 @default.
- W3034731205 cites W2194775991 @default.
- W3034731205 cites W2294748366 @default.
- W3034731205 cites W2308045930 @default.
- W3034731205 cites W2341108136 @default.
- W3034731205 cites W2400535959 @default.
- W3034731205 cites W2461871279 @default.
- W3034731205 cites W2462996230 @default.
- W3034731205 cites W2523124567 @default.
- W3034731205 cites W2527587652 @default.
- W3034731205 cites W2528489519 @default.
- W3034731205 cites W2555088548 @default.
- W3034731205 cites W2555722472 @default.
- W3034731205 cites W2565427121 @default.
- W3034731205 cites W2605016475 @default.
- W3034731205 cites W2735021678 @default.
- W3034731205 cites W2786122328 @default.
- W3034731205 cites W2796864868 @default.
- W3034731205 cites W2886982406 @default.
- W3034731205 cites W2895192407 @default.
- W3034731205 cites W2922429790 @default.
- W3034731205 cites W2952068267 @default.
- W3034731205 cites W2962887844 @default.
- W3034731205 cites W2963150697 @default.
- W3034731205 cites W2963221965 @default.
- W3034731205 cites W2963484919 @default.
- W3034731205 cites W2963617068 @default.
- W3034731205 cites W2963689319 @default.
- W3034731205 cites W2963940579 @default.
- W3034731205 cites W2964055695 @default.
- W3034731205 cites W2964308564 @default.
- W3034731205 cites W2964311356 @default.
- W3034731205 cites W2964317067 @default.
- W3034731205 cites W2965418143 @default.
- W3034731205 cites W2966193718 @default.
- W3034731205 cites W2985318390 @default.
- W3034731205 cites W2990747716 @default.
- W3034731205 cites W3089768235 @default.
- W3034731205 hasPublicationYear "2020" @default.
- W3034731205 type Work @default.
- W3034731205 sameAs 3034731205 @default.
- W3034731205 citedByCount "4" @default.
- W3034731205 countsByYear W30347312052021 @default.
- W3034731205 crossrefType "posted-content" @default.
- W3034731205 hasAuthorship W3034731205A5022418359 @default.
- W3034731205 hasAuthorship W3034731205A5064265174 @default.
- W3034731205 hasAuthorship W3034731205A5065802887 @default.
- W3034731205 hasAuthorship W3034731205A5088777896 @default.
- W3034731205 hasConcept C107457646 @default.
- W3034731205 hasConcept C127413603 @default.
- W3034731205 hasConcept C154945302 @default.
- W3034731205 hasConcept C177264268 @default.
- W3034731205 hasConcept C199360897 @default.
- W3034731205 hasConcept C201995342 @default.
- W3034731205 hasConcept C2524010 @default.
- W3034731205 hasConcept C2777210771 @default.
- W3034731205 hasConcept C2780451532 @default.
- W3034731205 hasConcept C33923547 @default.
- W3034731205 hasConcept C34413123 @default.
- W3034731205 hasConcept C41008148 @default.
- W3034731205 hasConcept C90509273 @default.
- W3034731205 hasConceptScore W3034731205C107457646 @default.
- W3034731205 hasConceptScore W3034731205C127413603 @default.
- W3034731205 hasConceptScore W3034731205C154945302 @default.
- W3034731205 hasConceptScore W3034731205C177264268 @default.
- W3034731205 hasConceptScore W3034731205C199360897 @default.
- W3034731205 hasConceptScore W3034731205C201995342 @default.