Filters








10 Hits in 5.3 sec

3DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Data [article]

Li Sun and Zhi Yan and Sergi Molina Mellado and Marc Hanheide and Tom Duckett
2017 arXiv   pre-print
This paper presents a novel 3DOF pedestrian trajectory prediction approach for autonomous mobile service robots.  ...  Our approach, T-Pose-LSTM (Temporal 3DOF-Pose Long-Short-Term Memory), is trained using long-term data from real-world robot deployments and aims to learn context-dependent (environment- and time-specific  ...  This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 732737 (ILIAD).  ... 
arXiv:1710.00126v1 fatcat:j5ft2lxzhnajnmvp37ynpssrhe

EPANer Team Description Paper for World Robot Challenge 2020 [article]

Zhi Yan, Nathan Crombez, Li Sun
2019 arXiv   pre-print
This paper presents the research focus and ideas incorporated in the EPANer robotics team, entering the World Robot Challenge 2020 - Partner Robot Challenge (Real Space).  ...  Tomás Krajník 18 for helpful suggestions regarding "time in robotics" and his team for sharing ideas and giving comments.  ...  We also developed a 3DOF pedestrian trajectory prediction approach learned from long-term autonomous mobile robot deployment data with deep neural networks [20] .  ... 
arXiv:1909.02355v1 fatcat:vjsx2hf4krbudpftxgzzez6abq

TinyOdom

Swapnil Sayan Saha, Sandeep Singh Sandha, Luis Antonio Garcia, Mani Srivastava
2022 Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies  
Deep inertial sequence learning has shown promising odometric resolution over model-based approaches for trajectory estimation in GPS-denied environments.  ...  Specifically, we consider four applications: pedestrian, animal, aerial, and underwater vehicle dead-reckoning.  ...  We also thank Jason Wu from the Networked and Embedded Systems Laboratory at the University of California -Los Angeles for aiding us in the data collection phase during the real-world setup.  ... 
doi:10.1145/3534594 fatcat:n2nbtuf73nbl3jg7qj2cmd36mq

Resource and Response Aware Path Planning for Long-term Autonomy of Ground Robots in Agriculture [article]

Stuart Eiffert, Nathan D. Wallace, He Kong, Navid Pirmarzdashti, Salah Sukkarieh
2021 arXiv   pre-print
Achieving long-term autonomy for mobile robots operating in real-world unstructured environments such as farms remains a significant challenge.  ...  This framework acts to achieve long-term autonomy through awareness of both dynamic responses of individuals to a robot's motion and the limited resources available.  ...  Acknowledgements The authors would like to thank everybody from the ACFR involved in the development of the Swagbot Robotic Platform, those who helped during the field trials conducted during this work-specifically  ... 
arXiv:2105.10690v1 fatcat:3mfraomfjfcvndw3q2bm7nr674

D2.1 Definition of Use Cases, Service Requirements and KPIs

Marco Quagliotti, Albert Rafel, Oscar Gonzales De Dios, Víctor López, Rafael López Da Silva, José Alberto Hernández, Manuel Urueña, David Larrabeiti, Ignacio Martín, Neelakandan Manihatty Bojan, Ftoeini Ntavou, Emilio Hugues Salas (+21 others)
2018 Zenodo  
deployment time, energy efficiency and mobility.  ...  Current mobile VR head-mounted display (HMD) systems support a 3DoF architecture, where the HMD detects the user's rotational movement, providing the main benefit of looking at the world from a fixed point  ... 
doi:10.5281/zenodo.1194063 fatcat:p7pu7rcpnndjlb6urdbzh6w4mi

QoS-oriented capacity planning for edge computing

Yu Xiao, Marius Noreikis, Antti Yla-Jaaiski
2017 2017 IEEE International Conference on Communications (ICC)  
Vision based localization systems originate from the field of robotics, where they have proved highly beneficial for guiding autonomous robots [53] .  ...  [80] have developed PoseNet, a CNN that employs transfer learning [132] and image plane regression to predict 6DoF image poses from a single query image.  ... 
doi:10.1109/icc.2017.7997387 dblp:conf/icc/XiaoNY17 fatcat:lki5wxgyufbtfmuowjqcoztqou

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
DAY 2 -Jan 13, 2021 Song, Yue; Bisagno, Niccolò; Hassan, Syed Zohaib; Conci, Nicola 2389 AG-GAN: An Attentive Group-Aware GAN for pedestrian trajectory prediction DAY 2 -Jan 13, 2021 Ouda, Osama  ...  Yulu; Fu, Kun; Wang, Zheng; Zhang, Changshui; Ye, Jieping 1024 Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting DAY 2 -Jan 13, 2021 Huang, Yen-Ting; Liao, Wen-Hung  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

1st TUM Research Alumni Conference: Living and Mobility in Smart Cities

Technische Universität München
2018
We will show how satellite images, aerial (especially UAV) images, terrestrial images and point clouds from laserscans can be used for model generation.  ...  project "FCL -Virtual Singapore". 83 Our results are expected to shed light on the spatial planning of transport infrastructure with implications on the strategies for promoting electric vehicles and e-mobility  ...  learning for all and from all.  ... 
doi:10.14459/2017md1429192 fatcat:wsfmk5sezff5nhxlcfahxvbsey

Connected autonomous electromobility: Visual navigation and charging analytic frameworks [article]

Kai Li Lim
2020
The BaMVO was evaluated on the TUM RGB-D dataset before it was implemented for trajectories captured on the mobile robot in a dynamic indoor environment with pedestrians.  ...  s [53] work whereby it produces a path guide for the autonomous navigation of a mobile robot.  ... 
doi:10.26182/5ea243762ca6c fatcat:sqpyp7i77fhp3oco5nzaswrwlm

International Conference on the Applications of Computer Science and Mathematics in Architecture and Civil Engineering : July 20 - 22 2015, Bauhaus-University Weimar

Klaus Gürlebeck, Tom Lahmer
2015
The 20th International Conference on the Applications of Computer Science and Mathematics in Architecture and Civil Engineering will be held at the Bauhaus University Weimar from 20th till 22nd July 2015  ...  Architects, computer scientists, mathematicians, and engineers from all over the world will meet in Weimar for an interdisciplinary exchange of experiences, to report on their results in research, development  ...  State-of-the-art sensor nodes, collecting structural and environmental data from civil infrastructure systems, are capable of processing and analyzing the data sets directly on-board the nodes.  ... 
doi:10.25643/bauhaus-universitaet.2451 fatcat:uy35r7npord7znzqfzg3spwyxu