Filters








270 Hits in 5.9 sec

A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation [article]

Rika Antonova, Jingyun Yang, Priya Sundaresan, Dieter Fox, Fabio Ramos, Jeannette Bohg
2021 arXiv   pre-print
Overall, our method addresses the real-to-sim problem probabilistically and helps to better represent the evolution of the state of deformable objects.  ...  Deformable object manipulation remains a challenging task in robotics research.  ...  A Bayesian Treatment of Real-to-Sim for Deformable Object  ... 
arXiv:2112.05068v1 fatcat:hy33didiafac7kxlntlrco7lyi

A Bayesian Treatment of Real-to-Sim for Deformable Object Manipulation

Rika Antonova, Jingyun Yang, Priya Sundaresan, Dieter Fox, Fabio Ramos, Jeannette Bohg
2022 IEEE Robotics and Automation Letters  
In this letter, we formulate the real-to-sim problem as probabilistic inference over simulation parameters of deformable objects.  ...  This real-to-sim problem is particularly challenging for deformable objects, where conventional techniques fall short as they often rely on precise state estimation and accurate dynamics models.  ...  Given these challenges, we advocate the Bayesian treatment and cast the real-to-sim problem as probabilistic inference over simulation parameters of real objects.  ... 
doi:10.1109/lra.2022.3157377 fatcat:iwvginpvuvb2lfwbjajxosr65e

Robot Learning From Randomized Simulations: A Review

Fabio Muratore, Fabio Ramos, Greg Turk, Wenhao Yu, Michael Gienger, Jan Peters
2022 Frontiers in Robotics and AI  
We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named "domain randomization" which is a method for learning from randomized simulations.  ...  Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real).  ...  Solving three variations of a tissue folding task, this work scales sim-to-real visuomotor manipulation to deformable objects.  ... 
doi:10.3389/frobt.2022.799893 pmid:35494543 pmcid:PMC9038844 fatcat:f7bytfvmgjfnllmnuy74ywnxau

Robot Learning from Randomized Simulations: A Review [article]

Fabio Muratore, Fabio Ramos, Greg Turk, Wenhao Yu, Michael Gienger, Jan Peters
2021 arXiv   pre-print
We provide a comprehensive review of sim-to-real research for robotics, focusing on a technique named 'domain randomization' which is a method for learning from randomized simulations.  ...  Therefore, state-of-the-art approaches learn in simulation where data generation is fast as well as inexpensive and subsequently transfer the knowledge to the real robot (sim-to-real).  ...  Solving three variations of a tissue folding task, this work scales sim-to-real visuomotor manipulation to deformable objects.  ... 
arXiv:2111.00956v1 fatcat:khywklph2jfkbd2at3fvnszf2e

Real-time target tracking of soft tissues in 3D ultrasound images based on robust visual information and mechanical simulation

Lucas Royer, Alexandre Krupa, Guillaume Dardenne, Anthony Le Bras, Eric Marchand, Maud Marchal
2017 Medical Image Analysis  
In this paper, we present a real-time approach that allows tracking deformable structures in 3D ultrasound sequences.  ...  We perform evaluation of our method through simulated data, phantom data, and real-data.  ...  Acknowledgments This research is currently supported by the Institute of Research and Technology (IRT) b-com.  ... 
doi:10.1016/j.media.2016.09.004 pmid:27689897 fatcat:n2rttjggmzbf7hgkheio2jwnve

2020 Index IEEE Robotics and Automation Letters Vol. 5

2020 IEEE Robotics and Automation Letters  
: Efficient Reinforcement Learning for Multi-Step Visual Tasks with Sim to Real Transfer.  ...  Sim-To-Real Transfer Learning Approach for Tracking Multi-DOF Ankle Motions Using Soft Strain Sensors.  ... 
doi:10.1109/lra.2020.3032821 fatcat:qrnouccm7jb47ipq6w3erf3cja

Training models of anatomic shape variability

Derek Merck, Gregg Tracton, Rohit Saboo, Joshua Levy, Edward Chaney, Stephen Pizer, Sarang Joshi
2008 Medical Physics (Lancaster)  
This article presents a set of general principles to guide such training.  ...  constraints in favor of the converging shape probabilities as the fitted objects converge to their target segmentations.  ...  For each i in I: 2.1.1. Find m i s.t. m i = Arg/ Min (sim trans of Rk) Energy(R k , i) 2.1.2. Find m i s.t. m i = Arg/ Min (globai deformations of Rk) Energy(R k , i) 2.1.3.  ... 
doi:10.1118/1.2940188 pmid:18777919 pmcid:PMC2809709 fatcat:tdvcmw7pdzdgxinulk7apipq6u

Haptic guided 3-D deformable image registration

Petter Risholm, Eigil Samset
2009 International Journal of Computer Assisted Radiology and Surgery  
I am grateful to the Center of Mathematics for Applications for giving me the opportunity to pursue a PhD and the Research Council of Norway for their financial support.  ...  I will be forever grateful to my co-supervisor William Wells for his excellent guidance, dedication and clarity of vision.  ...  Reported deformations of the brain-tissue due to brain-shift are up to 24mm [8, 9, 10] , and further deformations may be induced because of manipulation of tissue during the resection [6, 11] .  ... 
doi:10.1007/s11548-009-0291-4 pmid:20033588 fatcat:zjb6scrkgbc4nplidqalgy256q

DiSECt: A Differentiable Simulator for Parameter Inference and Control in Robotic Cutting [article]

Eric Heiden, Miles Macklin, Yashraj Narang, Dieter Fox, Animesh Garg, Fabio Ramos
2022 arXiv   pre-print
We first show that the simulator can be calibrated to match resultant forces and deformation fields from a state-of-the-art commercial solver and real-world cutting datasets, with generality across cutting  ...  Robotic cutting of soft materials is critical for applications such as food processing, household automation, and surgical manipulation.  ...  Acknowledgments We thank Yan-Bin Jia and Prajjwal Jamdagni for providing the dataset of real-world cutting trajectories and meshes that we used in our experiments from section 5.  ... 
arXiv:2203.10263v1 fatcat:xdtslus5cjfzpnjkxreo2hxmpe

THE AMBIGUITY AVERSION LITERATURE: A CRITICAL ASSESSMENT

Nabil I. Al-Najjar, Jonathan Weinstein
2009 Economics and Philosophy  
These choices can arise when decision makers form heuristics that serve them well in real-life situations where odds are manipulable, and misapply them to experimental settings.  ...  We provide a critical assessment of the ambiguity aversion literature, which we characterize in terms of the view that Ellsberg choices are rational responses to ambiguity, to be explained by relaxing  ...  As Epstein and Le Breton (1993: 2) write: "a satisfactory treatment of updating is a prerequisite for fruitful application of models of non-Bayesian beliefs [. . .]  ... 
doi:10.1017/s026626710999023x fatcat:wziu6skwpzgw5ahnmg6rj2pjpu

An Early Stage Researcher's Primer on Systems Medicine Terminology

Massimiliano Zanin, Nadim A.A. Aitya, José Basilio, Jan Baumbach, Arriel Benis, Chandan K. Behera, Magda Bucholc, Filippo Castiglione, Ioanna Chouvarda, Blandine Comte, Tien-Tuan Dao, Xuemei Ding (+43 others)
2021 Network and Systems Medicine  
Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels  ...  Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and  ...  The specification of prior distribution is a matter of ongoing concern for those contemplating the use of Bayesian methods in medical research. 48 It is not without a reason that frequentists object to  ... 
doi:10.1089/nsm.2020.0003 pmid:33659919 pmcid:PMC7919422 fatcat:izso73zmcjf2foc54wgl6bnloi

Dark, Beyond Deep: A Paradigm Shift to Cognitive AI with Humanlike Common Sense

Yixin Zhu, Tao Gao, Lifeng Fan, Siyuan Huang, Mark Edmonds, Hangxin Liu, Feng Gao, Chi Zhang, Siyuan Qi, Ying Nian Wu, Joshua B. Tenenbaum, Song-Chun Zhu
2020 Engineering  
Recent progress in deep learning is essentially based on a "big data for small tasks" paradigm, under which massive amounts of data are used to train a classifier for a single narrow task.  ...  Specifically, we propose a "small data for big tasks" paradigm, wherein a single artificial intelligence (AI) system is challenged to develop "common sense", enabling it to solve a wide range of tasks  ...  glance of a real-world scene?  ... 
doi:10.1016/j.eng.2020.01.011 fatcat:dltxealx3zgk5eyi2hlszbjhmu

The 1st Asian Symposium on Computer Aided Surgery

2005 Journal of Japan Society of Computer Aided Surgery  
Discussion The objective of this paper was to propose a new manipulator for RAO and evaluate its ability.  ...  to the treatment.  ...  For that purpose, we constructed a skeletal model on the basis of CT and optical motion capture data collected in real-time.  ... 
doi:10.5759/jscas1999.7.127 fatcat:ewnubdsecvekdbemcksjkv557e

Synthetic Data for Deep Learning [article]

Sergey I. Nikolenko
2019 arXiv   pre-print
In this work, we attempt to provide a comprehensive survey of the various directions in the development and application of synthetic data.  ...  Second, we discuss in detail the synthetic-to-real domain adaptation problem that inevitably arises in applications of synthetic data, including synthetic-to-real refinement with GAN-based models and domain  ...  They apply this idea to augmenting synthetic images for sim-to-real policy transfer for robotic manipulation and report improved results in real world tasks such as cube stacking or cup placing.  ... 
arXiv:1909.11512v1 fatcat:qquxnw4dfvgmfeztbpdqhr44gy

Embodied Artificial Intelligence: Trends and Challenges [chapter]

Rolf Pfeifer, Fumiya Iida
2004 Lecture Notes in Computer Science  
Although there are specialized machines for virtually any kind of manipulation (driving a screw, picking up objects for packaging in production lines, lifting heavy objects in construction sites), the  ...  general purpose manipulation abilities of natural systems are to date unparalleled.  ...  We would also like to thank the members of the Artificial Intelligence Laboratory of the University of Zurich for numerous stimulating discussions on this topic.  ... 
doi:10.1007/978-3-540-27833-7_1 fatcat:4jzfgrviabffdesvml7cnbf6dq
« Previous Showing results 1 — 15 out of 270 results