29,244 Hits in 4.8 sec

Active learning from demonstration for robust autonomous navigation

David Silver, J. Andrew Bagnell, Anthony Stentz
2012 2012 IEEE International Conference on Robotics and Automation  
This work proposes two approaches for active learning from demonstration, in which the learning system requests specific demonstrations from the expert.  ...  Building robust and reliable autonomous navigation systems that generalize across environments and operating scenarios remains a core challenge in robotics.  ...  This work investigates the application of active learning to learning from demonstration, specifically in the context of autonomous navigation. The next section describes related work in both fields.  ... 
doi:10.1109/icra.2012.6224757 dblp:conf/icra/SilverBS12 fatcat:jsjodv3ovbdf7pf4xoj3k3taxa

Guest Editorial: Autonomous systems: Navigation, learning, and control

Yu Zhang, Fei Gao, Yuxiang Sun, Naira Hovakimyan, Zheng Fang
2021 IET Cyber-Systems and Robotics  
However, navigation, learning, and control are critical for realizing true autonomy, which are still left for research.  ...  This is the IET Cyber-systems and Robotics special issue of Autonomous systems: Navigation, learning, and control.  ...  ACKNOWLEDGEMENTS The Guest Editors wish to express their gratitude to IET Cyber-systems and Robotics Editors-in-Chief Rob Buckingham, Jian Chu, and Max Meng for their constant support.  ... 
doi:10.1049/csy2.12038 fatcat:6oydu3mdufcmlgqnqa774cctmq

Adaptive and intelligent navigation of autonomous planetary rovers — A survey

Cuebong Wong, Erfu Yang, Xiu-Tian Yan, Dongbing Gu
2017 2017 NASA/ESA Conference on Adaptive Hardware and Systems (AHS)  
This paper surveys a representative selection of work applicable to autonomous planetary rover navigation, discussing some ongoing challenges and promising future research directions from the perspectives  ...  The development of a truly autonomous rover system with the capability to be effectively navigated in such environments requires intelligent and adaptive methods fitting for a system with limited resources  ...  The success of these missions were considerable feats that demonstrate the benefits that can be derived from the deployment of autonomous wheeled mobile robots to assist and support human activities.  ... 
doi:10.1109/ahs.2017.8046384 dblp:conf/ahs/WongYYG17 fatcat:iwlth237anf7dhrbpy3seuul3q

Do Not Make the Same Mistakes Again and Again: Learning Local Recovery Policies for Navigation From Human Demonstrations

Francesco Del Duchetto, Ayse Kucukyilmaz, Luca Iocchi, Marc Hanheide
2018 IEEE Robotics and Automation Letters  
Employing a learning by demonstration (LbD) approach, our framework can incrementally learn to autonomously recover from situations it initially needs humans to help with.  ...  In this paper, we present a human-in-the-loop learning framework for mobile robots to generate effective local policies in order to recover from navigation failures in longterm autonomy.  ...  Our experiments indicate the utility of the technique to learn active local navigation recovery policies from human demonstrations.  ... 
doi:10.1109/lra.2018.2861080 dblp:journals/ral/DuchettoKIH18 fatcat:wz6agti2krag5o6wzbh4fym54a

Using rat navigation models to learn orientation from visual input on a mobile robot

Brett Browning
2001 Proceedings of the fifth international conference on Autonomous agents - AGENTS '01  
This paper describes research that is part of a larger project aimed at developing a robot navigation system that is capable of robust autonomous navigation in real-time by using biologically plausible  ...  constructs inspired from the many neurological and behavioral studies conducted on freely navigating rats.  ...  The robust, proficient nature of the rat navigation system suggests that robotics could gain from robotic implementation of rat navigation models.  ... 
doi:10.1145/375735.375829 dblp:conf/agents/Browning01 fatcat:ap5p7w3zs5au5muzt4vtxm2nvu

Artificial Intelligence for Long-Term Robot Autonomy: A Survey [article]

Lars Kunze, Nick Hawes, Tom Duckett, Marc Hanheide, Tomáš Krajník
2018 arXiv   pre-print
Some of these have been investigated by sub-disciplines of Artificial Intelligence (AI) including navigation & mapping, perception, knowledge representation & reasoning, planning, interaction, and learning  ...  and opportunities for AI in long-term autonomy.  ...  Its autonomous capabilities come from a mixedinitiative task planner, and an autonomous navigation system.  ... 
arXiv:1807.05196v1 fatcat:5hi5seffdbhlbilbgoxb3ejmjm

Artificial Intelligence for Long-Term Robot Autonomy: A Survey

Lars Kunze, Nick Hawes, Tom Duckett, Marc Hanheide, Tomas Krajnik
2018 IEEE Robotics and Automation Letters  
Some of these have been investigated by sub-disciplines of Artificial Intelligence (AI) including navigation & mapping, perception, knowledge representation & reasoning, planning, interaction, and learning  ...  and opportunities for AI in long-term autonomy.  ...  Valgren & Lilienthal [45] demonstrated the robustness of local image features for localisation across seasons.  ... 
doi:10.1109/lra.2018.2860628 dblp:journals/ral/KunzeHDHK18 fatcat:7unhzdtaiffsdpkgywhl4c63oq

CoBots: Collaborative robots servicing multi-floor buildings

Manuela Veloso, Joydeep Biswas, Brian Coltin, Stephanie Rosenthal, Tom Kollar, Cetin Mericli, Mehdi Samadi, Susana Brandao, Rodrigo Ventura
2012 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems  
We further investigate robust execution monitoring, and active learning for learning of the environment and effective factored humanrobot interaction plans.  ...  We are currently focusing on several research directions: multi-modal speech interaction, interactions among our multiple robots, learning from human demonstration, human observation, and human correction  ...  We further investigate robust execution monitoring, and active learning for learning of the environment and effective factored humanrobot interaction plans. II.  ... 
doi:10.1109/iros.2012.6386300 dblp:conf/iros/VelosoBCRKMSBV12 fatcat:viovsntyfrggll7e5xcydrscjy

Guest editorial: special issue on long-term autonomy in marine robotics

Francesco Maurelli, Marc Carreras, Kanna Rajan, David Lane
2016 Autonomous Robots  
In recent years, persistent autonomous operations have become a key area of interest for marine robotics researchers.  ...  Over and beyond making time-series measurements marine robots have demonstrated their capability to respond to episodic events, perform targeted sample collection, track dynamic phenomenon in rough coastal  ...  planning to robust control, from reliable navigation to bio-inspired approaches.  ... 
doi:10.1007/s10514-016-9606-9 fatcat:d6hqneezkrhvnkmftjpauqi7sm

Vision for Autonomous Vehicles and Probes (Dagstuhl Seminar 15461)

André Bruhn, Atsushi Imiya, Ales Leonardis, Tomas Pajdla, Marc Herbstritt
2016 Dagstuhl Reports  
as the central component for autonomous driving and navigation and remote exploration.  ...  Continuing topics of interest in computer vision are scene and environmental understanding using singleand multiple-camera systems, which are fundamental techniques for autonomous driving, navigation in  ...  In this talk, I will give an overview of my research activities on visual inertial navigation of quadrotors, from slow navigation (using standard frame-based cameras) to agile flight (using event-based  ... 
doi:10.4230/dagrep.5.11.36 dblp:journals/dagstuhl-reports/BruhnILP15 fatcat:l2nqd45tnrabpdqmwex6enkxei

The STRANDS Project: Long-Term Autonomy in Everyday Environments

Nick Hawes, Christopher Burbridge, Ferdian Jovan, Lars Kunze, Bruno Lacerda, Lenka Mudrova, Jay Young, Jeremy Wyatt, Denise Hebesberger, Tobias Kortner, Rares Ambrus, Nils Bore (+21 others)
2017 IEEE robotics & automation magazine  
There is also an increasing demand from end-users for autonomous service robots that can operate in real environments for extended periods.  ...  Over four deployments, our robots have been operational for a combined duration of 104 days autonomously performing end-user defined tasks, covering 116km in the process.  ...  Acknowledgments We wish to thank our project reviewers and project officers for their contributions to our research: Luc De Raedt, James Ferryman, Horst-Michael Gross, Olivier Da Costa, and Juha Heikkilä  ... 
doi:10.1109/mra.2016.2636359 fatcat:vplh3crenvhytea5ej7mrjwbde

IoT Driven Ambient Intelligence Architecture for Indoor Intelligent Mobility

Varuna De Silva, Jamie Roche, Xiyu Shi, Ahmet Kondoz
2018 2018 IEEE 16th Intl Conf on Dependable, Autonomic and Secure Computing, 16th Intl Conf on Pervasive Intelligence and Computing, 4th Intl Conf on Big Data Intelligence and Computing and Cyber Science and Technology Congress(DASC/PiCom/DataCom/CyberSciTech)  
The paper takes a semi-survey approach to presenting and illustrating preliminary results from our in-house built fully autonomous electric quadbike.  ...  Indoor environments are extremely challenging from a robot perception and navigation point of view, because of the ever-changing decorations, internal organizations and clutter.  ...  Among these challenges is the requirement for robust navigation of robots in indoor environments.  ... 
doi:10.1109/dasc/picom/datacom/cyberscitec.2018.00090 dblp:conf/dasc/SilvaRSK18 fatcat:2bpu3u4owvg37h5rvflcakcitu

CrowdMove: Autonomous Mapless Navigation in Crowded Scenarios [article]

Tingxiang Fan, Xinjing Cheng, Jia Pan, Dinesh Manocha, Ruigang Yang
2018 arXiv   pre-print
We optimize a mapless navigation policy with a robust policy gradient algorithm.  ...  Navigation is an essential capability for mobile robots. In this paper, we propose a generalized yet effective 3M (i.e., multi-robot, multi-scenario, and multi-stage) training framework.  ...  The experiments demonstrate that the mapless navigation policy can achieve autonomous navigation for different mobile platforms in a large variety of crowd scenes with moving pedestrians.  ... 
arXiv:1807.07870v2 fatcat:thyeg47p2vf3lab7ool2xuxroe

Intentional Control for Planetary Rover SRR

Robert Kozma, Terry Huntsberger, Hrand Aghazarian, Eddie Tunstel, Roman Ilin, Walter J. Freeman
2008 Advanced Robotics  
The central issue of this work is to study how the developed control system builds associations between the sensory modalities to achieve robust autonomous action selection.  ...  Learning is based on Hebbian rule coupled with reinforcement.  ...  We implement the developed system for the autonomous control of SRR2K. The multi-sensory association is described in details, which leads to robust goal oriented navigation and obstacle avoidance.  ... 
doi:10.1163/156855308x344846 fatcat:25gphrxsf5eltk65vtvwxkgibq

Autonomous navigation and sign detector learning

L. Ellis, N. Pugeault, K. Ofjall, J. Hedborg, R. Bowden, M. Felsberg
2013 2013 IEEE Workshop on Robot Vision (WORV)  
For autonomous navigation, a mapping is learnt from holistic image features (GIST) onto control parameters using Random Forest regression. Additionally, visual entities (road signs e.g.  ...  This is achieved within a Learning from Demonstration (LfD) framework, where policies are derived from example state-to-action mappings.  ...  ACKNOWLEDGMENTS This research has received funding from the Swedish Government for: ELLIIT (Strategic Area for ICT research), ETT (VR Swedish Research Council) and CUAS (Swedish Foundation for Strategic  ... 
doi:10.1109/worv.2013.6521929 fatcat:oixyd2w4jbabnj3qe22nruyt5e
« Previous Showing results 1 — 15 out of 29,244 results