{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:44:08Z","timestamp":1777128248824,"version":"3.51.4"},"reference-count":79,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icra46639.2022.9812179","type":"proceedings-article","created":{"date-parts":[[2022,7,12]],"date-time":"2022-07-12T19:36:40Z","timestamp":1657654600000},"page":"9272-9279","source":"Crossref","is-referenced-by-count":54,"title":["Hierarchical Representations and Explicit Memory: Learning Effective Navigation Policies on 3D Scene Graphs using Graph Neural Networks"],"prefix":"10.1109","author":[{"given":"Zachary","family":"Ravichandran","sequence":"first","affiliation":[{"name":"Massachusetts Institute of Technology,Lincoln Laboratory,USA"}]},{"given":"Lisa","family":"Peng","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Laboratory for Information & Decision Systems,USA"}]},{"given":"Nathan","family":"Hughes","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Laboratory for Information & Decision Systems,USA"}]},{"given":"J. Daniel","family":"Griffith","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Lincoln Laboratory,USA"}]},{"given":"Luca","family":"Carlone","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology,Laboratory for Information & Decision Systems,USA"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1147\/sj.41.0025"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.142"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref76","first-page":"1008","article-title":"Actor-critic algorithms","author":"konda","year":"2000","journal-title":"SIAM Journal on Control and Optimization"},{"key":"ref77","article-title":"Proximal policy optimization algorithms","volume":"abs 1707 6347","author":"schulman","year":"2017","journal-title":"CoRR"},{"key":"ref74","article-title":"Graph attention networks","author":"veli?kovi?","year":"2018","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920917755"},{"key":"ref75","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"0","journal-title":"NIPS"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968142"},{"key":"ref78","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"ref33","article-title":"Harvesting common-sense navigational knowledge for robotics from uncurated text corpora","author":"fulda","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref32","article-title":"Self-supervised learning of scene-graph representations to solve sequential manipulation problems","author":"nguyen","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref31","author":"zhu","year":"2020","journal-title":"Hierarchical planning for long-horizon manipulation with geometric and symbolic scene graphs"},{"key":"ref30","article-title":"Where are the keys? - learning object-centric navigation policies on semantic maps with graph convolutional networks","author":"sunderhauf","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref37","article-title":"Same object, different grasps: Data and semantic knowledge for task-oriented grasping","author":"murali","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref36","article-title":"Visual semantic navigation using scene priors","author":"yang","year":"0","journal-title":"Intl Conf on Machine Learning (ICML)"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794070"},{"key":"ref34","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11966","article-title":"Guiding exploratory behaviors for multi-modal grounding of linguistic descriptions","author":"thomason","year":"2018","journal-title":"Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18)"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00097"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093614"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_13"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1177\/02783649211056674"},{"key":"ref64","article-title":"Using scene graph context to improve image generation","volume":"abs 1901 3762","author":"tripathi","year":"2019","journal-title":"ArXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00576"},{"key":"ref65","article-title":"Generating natural language explanations for visual question answering using scene graphs and visual attention","volume":"abs 1902 5715","author":"ghosh","year":"2019","journal-title":"ArXiv"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00857"},{"key":"ref29","article-title":"Semantic and geometric modeling with neural message passing in 3d scene graphs for hierarchical mechanical search","author":"kurenkov","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref68","article-title":"Graph r-cnn for scene graph generation","author":"yang","year":"0","journal-title":"ECCV"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.352"},{"key":"ref2","article-title":"Playing atari with deep reinforcement learning","author":"mnih","year":"2013","journal-title":"ArXiv Preprint"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.29007\/xtgm"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989518"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR.2018.00024"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2923960"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00286"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2019.XV.010"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298990"},{"key":"ref58","article-title":"Nervenet: Learning structured policy with graph neural networks","author":"wang","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683135"},{"key":"ref56","article-title":"Graph policy network for transferable active learning on graphs","author":"hu","year":"0","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref55","article-title":"Graph convolutional reinforcement learning","author":"jiang","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341657"},{"key":"ref53","article-title":"Semi-parametric topological memory for navigation","author":"savinov","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref52","article-title":"Learning to plan with uncertain topological maps","author":"beeching","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref10","article-title":"Neural slam: Learning to explore with external memory","author":"zhang","year":"2017","journal-title":"ArXiv Preprint"},{"key":"ref11","article-title":"Neural topological slam for visual navigation","author":"chaplot","year":"0","journal-title":"IEEE Conf on Computer Vision and Pattern Recognition (CVPR)"},{"key":"ref40","article-title":"Learning object relation graph and tentative policy for visual navigation","author":"du","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.695"},{"key":"ref13","first-page":"246","article-title":"Vso: Visual semantic odometry","author":"lianos","year":"0","journal-title":"European Conf on Computer Vision (ECCV)"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.380"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989538"},{"key":"ref17","author":"zheng","year":"2019","journal-title":"Active scene understanding via online semantic reconstruction"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354011"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759111"},{"key":"ref4","article-title":"Robust policies via mid-level visual representations: An experimental study in manipulation and navigation","author":"chen","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref3","article-title":"Mid-level representations improve generalization and sample efficiency for learning visuomotor policies","author":"sax","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref6","article-title":"Driving policy transfer via modularity and abstraction","author":"muller","year":"0","journal-title":"Conference on Robot Learning (CoRL)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.aaw6661"},{"key":"ref8","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","author":"wu","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01236-7"},{"key":"ref9","article-title":"Playing doom with slam-augmented deep reinforcement learning","author":"bhatti","year":"2016","journal-title":"ArXiv Preprint"},{"key":"ref46","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref45","article-title":"Learning exploration policies for navigation","author":"chen","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref48","article-title":"Neural map: Structured memory for deep reinforcement learning","author":"wu","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref47","article-title":"Learning to explore using active neural slam","author":"chaplot","year":"0","journal-title":"International Conference on Learning Representations (ICLR)"},{"key":"ref42","article-title":"Object goal navigation using goal-oriented semantic exploration","author":"chaplot","year":"0","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967677"},{"key":"ref44","author":"krishna","year":"2016","journal-title":"Visual genome Connecting language and vision using crowdsourced dense image annotations"},{"key":"ref43","article-title":"Learning hierarchical relationships for object-goal navigation","author":"qiu","year":"0","journal-title":"Conference on Robot Learning (CoRL)"}],"event":{"name":"2022 IEEE International Conference on Robotics and Automation (ICRA)","location":"Philadelphia, PA, USA","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["2022 International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9811522\/9811357\/09812179.pdf?arnumber=9812179","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:07:27Z","timestamp":1727568447000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9812179\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/icra46639.2022.9812179","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}