{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:27:17Z","timestamp":1779294437306,"version":"3.51.4"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,19]],"date-time":"2025-05-19T00:00:00Z","timestamp":1747612800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["SLES-2331880,CAREER2045834"],"award-info":[{"award-number":["SLES-2331880,CAREER2045834"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,5,19]]},"DOI":"10.1109\/icra55743.2025.11128042","type":"proceedings-article","created":{"date-parts":[[2025,9,2]],"date-time":"2025-09-02T17:28:56Z","timestamp":1756834136000},"page":"1-8","source":"Crossref","is-referenced-by-count":13,"title":["Vision Transformers for End-to-End Vision-Based Quadrotor Obstacle Avoidance"],"prefix":"10.1109","author":[{"given":"Anish","family":"Bhattacharya","sequence":"first","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nishanth","family":"Rao","sequence":"additional","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhruv","family":"Parikh","sequence":"additional","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pratik","family":"Kunapuli","sequence":"additional","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwei","family":"Wu","sequence":"additional","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuezhan","family":"Tao","sequence":"additional","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nikolai","family":"Matni","sequence":"additional","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vijay","family":"Kumar","sequence":"additional","affiliation":[{"name":"The General Robotics, Automation, Sensing & Perception (GRASP) Lab, University of Pennsylvania,Philadelphia,PA,United States,19104"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2898117"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1126\/scirobotics.abg5810"},{"key":"ref3","author":"Song","year":"2022","journal-title":"DodgeDrone: Vision-based Agile Drone Flight (ICRA 2022 Competition)"},{"key":"ref4","article-title":"Handwritten digit recognition with a backpropagation network","volume":"2","author":"LeCun","year":"1989","journal-title":"Advances in neural information processing systems"},{"key":"ref5","first-page":"3288","article-title":"Convolutional neural networks applied to house numbers digit classification","volume-title":"Proceedings of the 21st international conference on pattern recognition (ICPR2012)","author":"Sermanet","year":"2012"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.02.017"},{"key":"ref8","author":"Bahdanau","year":"2014","journal-title":"Neural machine translation by jointly learning to align and translate"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref10","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160563"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2795643"},{"key":"ref13","first-page":"1","article-title":"Driving Policy Transfer via Modularity and Abstraction","volume":"87","author":"Mueller","year":"2018","journal-title":"Proceedings of The 2nd Conference on Robot Learning"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.04.020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2021.12.006"},{"key":"ref18","author":"Tao","year":"2022","journal-title":"Evaluating Vision Transformer Methods for Deep Reinforcement Learning from Pixels"},{"key":"ref19","first-page":"28358856","article-title":"A Survey on Transformers in Reinforcement Learning","author":"Li","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref20","first-page":"3680","article-title":"Stabilizing deep q-learning with convnets and vision transformers under data augmentation","volume":"34","author":"Hansen","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref21","author":"Ardalan Kalantari","year":"2022","journal-title":"Improving sample efficiency of value based models using attention and vision transformers"},{"key":"ref22","first-page":"1332","article-title":"Masked world models for visual control","author":"Seo","year":"2023","journal-title":"Conference on Robot Learning. PMLR"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/rs14030592"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2023.3241825"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2022.102675"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2927938"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-43089-4_20"},{"key":"ref28","article-title":"Monocular Event-Based Vision for Obstacle Avoidance with a Quadrotor","author":"Bhattacharya","year":"2024","journal-title":"8th Annual Conference on Robot Learning"},{"key":"ref29","article-title":"Flightmare: A Flexible Quadrotor Simulator","author":"Song","year":"2020","journal-title":"Conference on Robot Learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128042"},{"key":"ref31","article-title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","author":"Xie","year":"2021","journal-title":"Neural Information Processing Systems (NeurIPS)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.207"},{"key":"ref33","author":"Constable","year":"2020","journal-title":"TorchBench: A collection of open source benchmarks for PyTorch performance and usability evaluation"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160295"},{"key":"ref35","journal-title":"GitHub - KumarRobotics\/kr_mav_control: Code for quadrotor control - github.com"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7140074"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161097"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2019.2927938"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/icra48506.2021.9561585"},{"key":"ref40","author":"Wu","year":"2024","journal-title":"Fast-Planner"},{"key":"ref41","author":"Wu","year":"2024","journal-title":"Double Description"}],"event":{"name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","location":"Atlanta, GA, USA","start":{"date-parts":[[2025,5,19]]},"end":{"date-parts":[[2025,5,23]]}},"container-title":["2025 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11127273\/11127223\/11128042.pdf?arnumber=11128042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T06:06:41Z","timestamp":1756879601000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11128042\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,19]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/icra55743.2025.11128042","relation":{},"subject":[],"published":{"date-parts":[[2025,5,19]]}}}