Filters








493 Hits in 7.3 sec

Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task [article]

Stephen James, Andrew J. Davison, Edward Johns
<span title="2017-10-17">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we show how two simple techniques can lead to end-to-end (image to velocity) execution of a multi-stage task, which is analogous to a simple tidying routine, without having seen a single  ...  To achieve this, robot trajectories are computed in a simulator, to collect a series of control velocities which accomplish the task.  ...  We thank the reviewers for their valuable feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.02267v2">arXiv:1707.02267v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hh3337mjxnej5nkzgyzzqrbuby">fatcat:hh3337mjxnej5nkzgyzzqrbuby</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200827152538/https://arxiv.org/pdf/1707.02267v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/45/8c/458c3a17de9282076487d4500e05792365d1afe0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1707.02267v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Reinforcement and Imitation Learning for Diverse Visuomotor Skills [article]

Yuke Zhu, Ziyu Wang, Josh Merel, Andrei Rusu, Tom Erez, Serkan Cabi, Saran Tunyasuvunakool, János Kramár, Raia Hadsell, Nando de Freitas, Nicolas Heess
<span title="2018-05-27">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities.  ...  We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious.  ...  ACKNOWLEDGMENT The authors would like to thank Yuval Tassa, Jonathan Scholz, Thomas Rothörl, Jonathan Hunt, and many other colleagues at DeepMind for the helpful discussion and feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.09564v2">arXiv:1802.09564v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7vwziswy25blbdgmb6gklibl5m">fatcat:7vwziswy25blbdgmb6gklibl5m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191020130739/https://arxiv.org/pdf/1802.09564v1.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/56/f7/56f73c1d42501dd5f5d559f8649781e6f95b9bba.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1802.09564v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Reinforcement and Imitation Learning for Diverse Visuomotor Skills

Yuke Zhu, Ziyu Wang, Josh Merel, Andrei Rusu, Tom Erez, Serkan Cabi, Saran Tunyasuvunakool, János Kramár, Raia Hadsell, Nando de Freitas, Nicolas Heess
<span title="2018-06-26">2018</span> <i title="Robotics: Science and Systems Foundation"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/gjhqqq6dgnaupkvp2ckhefvv6i" style="color: black;">Robotics: Science and Systems XIV</a> </i> &nbsp;
We apply this approach to robotic manipulation tasks and train end-to-end visuomotor policies that map directly from RGB camera inputs to joint velocities.  ...  We demonstrate that our approach can solve a wide variety of visuomotor tasks, for which engineering a scripted controller would be laborious.  ...  ACKNOWLEDGMENT The authors would like to thank Yuval Tassa, Jonathan Scholz, Thomas Rothörl, Jonathan Hunt, and many other colleagues at DeepMind for the helpful discussion and feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15607/rss.2018.xiv.009">doi:10.15607/rss.2018.xiv.009</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/rss/Zhu0MRECTKHFH18.html">dblp:conf/rss/Zhu0MRECTKHFH18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u6pt5wi6lvgchhezcsn6qntid4">fatcat:u6pt5wi6lvgchhezcsn6qntid4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190225131533/http://pdfs.semanticscholar.org/6318/ffe9649e4c4d683da2336f57c1a45189a692.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/63/18/6318ffe9649e4c4d683da2336f57c1a45189a692.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.15607/rss.2018.xiv.009"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Multi-Modal Fusion in Contact-Rich Precise Tasks via Hierarchical Policy Learning [article]

Piaopiao Jin, Yinjie Lin, Yanchao Tan, Tiefeng Li, Wei Yang
<span title="2022-02-17">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
A key challenge is to achieve an effective multi-modal and generalized control scheme to novel objects with precision.  ...  To begin with, we use a self-supervised encoder that extracts multi-view visual features and a hybrid motion/force controller that regulates force behaviors.  ...  Moreover, the controller shows weak generalization ability when transferred from simulation to reality.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.08401v1">arXiv:2202.08401v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5pbamntwovcv5fxxbv66pwma2u">fatcat:5pbamntwovcv5fxxbv66pwma2u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220223010534/https://arxiv.org/pdf/2202.08401v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3b/73/3b7303d8f56c976617f0b4330cade03290616661.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2202.08401v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Adaptive Curriculum Generation from Demonstrations for Sim-to-Real Visuomotor Control [article]

Lukas Hermann, Max Argus, Andreas Eitel, Artemij Amiranashvili, Wolfram Burgard, Thomas Brox
<span title="2020-07-08">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show that training vision-based control policies in simulation while gradually increasing the difficulty of the task via ACGD improves the policy transfer to the real world.  ...  Rather than designing shaped reward functions, ACGD adaptively sets the appropriate task difficulty for the learner by controlling where to sample from the demonstration trajectories and which set of simulation  ...  Learning continuous visuomotor controllers from raw images circumvents the need for manually designing multi-stage manipulation and computer vision pipelines [1] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.07972v3">arXiv:1910.07972v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dexm2xv3jzfn7ihrqkyixkeb2u">fatcat:dexm2xv3jzfn7ihrqkyixkeb2u</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710070948/https://arxiv.org/pdf/1910.07972v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1910.07972v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Composable Instructions and Prospection Guided Visuomotor Control for Robotic Manipulation

Quanquan Shao, Jie Hu, Weiming Wang, Yi Fang, Mingshuo Han, Jin Qi, Jin Ma
<span title="">2019</span> <i title="Atlantis Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/wjdkfhqywrdefeqoyzjz3os76i" style="color: black;">International Journal of Computational Intelligence Systems</a> </i> &nbsp;
A B S T R A C T Deep neural network-based end-to-end visuomotor control for robotic manipulation is becoming a hot issue of robotics field recently.  ...  This paper proposes a framework by combining composable instructions with visuomotor control for multi-task problems.  ...  , 51975360, 51975350) and the Cross Fund for medical and Engineering of Shanghai Jiao Tong University (YG2017QN61).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2991/ijcis.d.191017.001">doi:10.2991/ijcis.d.191017.001</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pwv2yzqgpndhjjn4i5t6klzq74">fatcat:pwv2yzqgpndhjjn4i5t6klzq74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200215091825/https://download.atlantis-press.com/article/125921091.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fd/1a/fd1af3d63432713f57361c92b51c370ff321fdf3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.2991/ijcis.d.191017.001"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Adapting Deep Visuomotor Representations with Weak Pairwise Constraints [article]

Eric Tzeng, Coline Devin, Judy Hoffman, Chelsea Finn, Pieter Abbeel, Sergey Levine, Kate Saenko, Trevor Darrell
<span title="2017-05-25">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
For many robotic control tasks, real world experience is expensive to obtain, but data is easy to collect in either an instrumented environment or in simulation.  ...  Focusing on adapting from simulation to real world data using a PR2 robot, we evaluate our approach on a manipulation task and show that by using weakly paired images, our method compensates for domain  ...  Recently proposed endto-end visuomotor networks [1] can learn both image representations and the control policy for a particular task directly from visual data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.07111v5">arXiv:1511.07111v5</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/53ouc3i5irbynhfuslqzvfimzm">fatcat:53ouc3i5irbynhfuslqzvfimzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930190030/https://arxiv.org/pdf/1511.07111v5.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9f/ad/9fad27c687ba1820fd25d41427e0af2a68c4153b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1511.07111v5" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Object Detection-Based One-Shot Imitation Learning with an RGB-D Camera

Shao, Qi, Ma, Fang, Wang, Hu
<span title="2020-01-23">2020</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/smrngspzhzce7dy6ofycrfxbim" style="color: black;">Applied Sciences</a> </i> &nbsp;
To evaluate this proposed pipeline, a series of experiments are conducted on typical placing tasks in different simulation scenarios and, additionally, the learned policy is transferred from simulation  ...  to the real world without any fine-tuning.  ...  James et al. trained a visuomotor skill for pick-and-place task in simulation with domain randomization and transferred the visuomotor skill to the real world without any fine-tuning [3] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10030803">doi:10.3390/app10030803</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m54bsnac2ncbja3fy6x2oiptoe">fatcat:m54bsnac2ncbja3fy6x2oiptoe</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200212063537/https://res.mdpi.com/d_attachment/applsci/applsci-10-00803/article_deploy/applsci-10-00803-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d1/b9/d1b96b3ce803c3b2f687876e276954668bc8cc78.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app10030803"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Transferring Visuomotor Learning from Simulation to the Real World for Robotics Manipulation Tasks

Phuong D.H. Nguyen, Tobias Fischer, Hyung Jin Chang, Ugo Pattacini, Giorgio Metta, Yiannis Demiris
<span title="">2018</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/dmucnarmarh2fj6syg5jyqs7ny" style="color: black;">2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)</a> </i> &nbsp;
Nguyen was supported by a Marie Curie Early Stage Researcher Fellowship (H2020-MSCA-ITA, SECURE 642667).  ...  We would like to thank Alessandro Roncone for the initial figure of the simplified iCub's head-eyes joints.  ...  CONCLUSIONS Transferring Visuomotor Learning from Simulation to the Real World for Robotics Manipulation Tasks Phuong D.H.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iros.2018.8594519">doi:10.1109/iros.2018.8594519</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iros/Nguyen0CPMD18.html">dblp:conf/iros/Nguyen0CPMD18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t743kbfmvrdsvozf2oyba6vhei">fatcat:t743kbfmvrdsvozf2oyba6vhei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200506005747/http://pure-oai.bham.ac.uk/ws/files/54069769/Transferring_Visuomotor.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/83/5c/835c4fb987a8babaab4bd29ab0958290c3029c67.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iros.2018.8594519"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Adversarial Discriminative Sim-to-real Transfer of Visuo-motor Policies [article]

Fangyi Zhang, Jürgen Leitner, Zongyuan Ge, Michael Milford, Peter Corke
<span title="2018-05-31">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Various approaches have been proposed to learn visuo-motor policies for real-world robotic applications. One solution is first learning in simulation then transferring to the real world.  ...  The effectiveness of the approach is demonstrated with modular networks in a table-top object reaching task where a 7 DoF arm is controlled in velocity mode to reach a blue cuboid in clutter through visual  ...  Acknowledgement This research was conducted by the Australian Research Council Centre of Excellence for Robotic Vision (project number CE140100016).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.05746v2">arXiv:1709.05746v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qaauxfe2ozabzl6uimqxf6mlkm">fatcat:qaauxfe2ozabzl6uimqxf6mlkm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901204614/https://arxiv.org/pdf/1709.05746v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/bb/27/bb270997495efa5a36eabb5b666f32cf0d6001ce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1709.05746v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Location Instruction-based Motion Generation for Sequential Robotic Manipulation

Quanquan Shao, Jie Hu, Weiming Wang, Yi Fang, Teng Xue, Jin Qi
<span title="">2020</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Deep learning-based visuomotor control for manipulation are studied recently, which uses a neural network to learn the mapping from images to robotic actions directly.  ...  When multiple target objects are present, they are normally regarded as multi-task problems. One-hot vectors are often used to denote different tasks in the visuomotor framework.  ...  Domain randomization was used in visuomotor learning for a pickand-place task in simulation and the visuomotor skill was transferred from a simulated environment to the real world [28] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2971570">doi:10.1109/access.2020.2971570</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n2ji76pjxbbvdg65dniuvuygce">fatcat:n2ji76pjxbbvdg65dniuvuygce</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201107112026/https://ieeexplore.ieee.org/ielx7/6287639/8948470/08981898.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/3f/72/3f7299d8e91efb1b3b345aafc67448cf19c8260f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2971570"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Adversarial Feature Training for Generalizable Robotic Visuomotor Control [article]

Xi Chen, Ali Ghadirzadeh, Mårten Björkman, Patric Jensfelt
<span title="2019-09-17">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose to leverage the deep RL capabilities to learn complex visuomotor skills for uncomplicated task setups, and then exploit transfer learning to generalize to new task domains provided only still  ...  However, it is impractical for a robotic setup to sufficiently collect interactive samples in a RL framework to generalize well to novel aspects of a task.  ...  Visual representation learning for visuomotor control Levine et al., [13] proposed end-to-end training of perception and control networks for a number of robotic visuomotor tasks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.07745v1">arXiv:1909.07745v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/psa6rhr3sfh73ovdyhqlwdmera">fatcat:psa6rhr3sfh73ovdyhqlwdmera</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908065709/https://arxiv.org/pdf/1909.07745v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/7a/95/7a958af007db6ddc4b462eeb7603857c9239f137.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.07745v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

A Data-Efficient Framework for Training and Sim-to-Real Transfer of Navigation Policies [article]

Homanga Bharadhwaj, Zihan Wang, Yoshua Bengio, Liam Paull
<span title="2018-10-11">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We subsequently perform adversarial domain transfer on the encoder by using a bank of unlabelled but random images from the simulation and real environments to enable the encoder to map images from the  ...  In this work, we introduce a robust framework that plans in simulation and transfers well to the real environment.  ...  The authors show the ability to effectively transfer the learning of a visuomotor policies from a simulation environment to the real setup by the use of very few real expert demonstrations for fine-tuning  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.04871v1">arXiv:1810.04871v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gqpiaprz2zafrgxdz4q7i6u6tm">fatcat:gqpiaprz2zafrgxdz4q7i6u6tm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200930112700/https://arxiv.org/pdf/1810.04871v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/13/ac/13ac99447a8c47f97714ab2982940716bf9ea044.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1810.04871v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives [article]

Oliver Groth, Chia-Man Hung, Andrea Vedaldi, Ingmar Posner
<span title="2021-09-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Visuomotor control (VMC) is an effective means of achieving basic manipulation tasks such as pushing or pick-and-place from raw images.  ...  In this paper we propose a conditioning scheme which avoids these pitfalls by learning the controller and its conditioning in an end-to-end manner.  ...  End-to-end visuomotor controllers have demonstrated remarkable performance in real systems, e.g. learning to pick up a cube and place it in a basket [1] , [2] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.08854v3">arXiv:2003.08854v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/52rgnfqm6ff53jgsayscf3xkle">fatcat:52rgnfqm6ff53jgsayscf3xkle</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210928081549/https://arxiv.org/pdf/2003.08854v3.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/95/0e/950e0099a34851e5979553732fdc7512796ab9a1.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2003.08854v3" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Deep Object-Centric Policies for Autonomous Driving [article]

Dequan Wang, Coline Devin, Qi-Zhi Cai, Fisher Yu, Trevor Darrell
<span title="2019-03-01">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We describe a taxonomy of "object-centric" models which leverage both object instances and end-to-end learning.  ...  While learning visuomotor skills in an end-to-end manner is appealing, deep neural networks are often uninterpretable and fail in surprising ways.  ...  INTRODUCTION End-to-end approaches to visuomotor learning are appealing in their ability to discover which features of an observed environment are most relevant for a task, and to be able to exploit large  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.05432v2">arXiv:1811.05432v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/eejtsmk44babjhn7jkifuudr74">fatcat:eejtsmk44babjhn7jkifuudr74</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200907101640/https://arxiv.org/pdf/1811.05432v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/80/d7/80d7cd49ce400158ef56ea52df4338b4b12a025b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1811.05432v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 493 results