The DOI matches its Crossref record; 119 of the 119 references it cites were found in a registry or an index.
Interactive Perception: Leveraging Action in Perception and Perception in Action
Open accessAbstract
Recent approaches in robot perception follow the insight that perception is facilitated by interaction with the environment. These approaches are subsumed under the term Interactive Perception (IP). This view of perception provides the following benefits. First, interaction with the environment creates a rich sensory signal that would otherwise not be present. Second, knowledge of the regularity in the combined space of sensory data and action parameters facilitates the prediction and interpretation of the sensory signal. In this survey, we postulate this as a principle for robot perception and collect evidence in its support by analyzing and categorizing existing work in this area. We also provide an overview of the most important applications of IP. We close this survey by discussing remaining open questions. With this survey, we hope to help define the field of Interactive Perception and to provide a valuable resource for future research.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Such structure is called Action Perception Regularity [1], and is believed to be the key for IP to reveal richer signals, which is impossible for passive and one-shot perception.”
From Interactive Perception for Deformable Object Manipulation (2024) · cites this paper as [1]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Interactive Perception (IP) exploits various types of forceful interactions with the environment to facilitate perception [1].”
From Interactive Perception for Deformable Object Manipulation (2024) · cites this paper as [1]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Very Deep Convolutional Networks for Large-Scale Image Recognition
Simonyan, K., & Zisserman, A. (2014) · arXiv · doi:10.48550/arxiv.1409.1556 · Cited by 114,148
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 1×
“t given only a single input image. A method has to cope with occlusions, different lighting conditions, scale of the images, just to name a few. State-of-the-art approaches in Computer Vision as e.g. [107, 108] require enormous amounts of training data to handle these variations. Interactive Perception approaches allo…”
MethodMicrosoft COCO: Common Objects in Context
Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Dollár, P., & Zitnick, C. L. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_48 · Cited by 45,460
ImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“These three examples illustrate that biological perception and perceptually-guided behavior intrinsically rely on active exploration and knowledge of the relation between action and sensory response.”
BackgroundFully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
The pascal visual object classes (VOC) challenge
Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., & Zisserman, A. (2010) · International Journal of Computer Vision · doi:10.1007/s11263-009-0275-4 · Cited by 19,599 · cited 2×
“The most successful approaches learn models from data sets that contain hundreds of thousands of semantically annotated static images, such as Pascal VOC [6], ImageNet [7] or Microsoft COCO [8].”
BackgroundContour Detection and Hierarchical Image Segmentation
Arbeláez, P., Maire, M., Fowlkes, C., & Malik, J. (2011) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2010.161 · Cited by 5,454 · cited 1×
“This emphasizes the blurred boundary which is traditionally drawn between manipulation and perception.”
BackgroundLaValle, S. M. (2006) · Cambridge University Press eBooks · doi:10.1017/cbo9780511546877 · Cited by 5,211
Computational modelling of visual attention
Itti, L., & Koch, C. (2001) · Nature Reviews Neuroscience · doi:10.1038/35058500 · Cited by 4,733 · cited 1×
“of freedom [17]–[19] and models of visual attention [20], [21] that these active vision systems could use for guiding their gaze.”
BackgroundReinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160 · cited 2×
“Reinforcement learning [126] is also a common choice to learn a policy for action selection under these complex conditions.”
BackgroundA sensorimotor account of vision and visual consciousness
O'Regan, J. K., & Noë, A. (2001) · Behavioral and Brain Sciences · doi:10.1017/s0140525x01000115 · Cited by 3,126 · cited 1×
“T is compelling evidence that visual perception in humans and animals is a process that is active and exploratory [1, 2].”
BackgroundLevine, S., Pastor, P., Krizhevsky, A., Ibarz, J., & Quillen, D. (2018) · The International Journal of Robotics Research · doi:10.1177/0278364917710318 · Cited by 1,971 · cited 2×
“[79] 7 [36], [78] ), [79]) [36], [79], [78] [36], [78] , [36], [78] Object [77] CNS OD 7 P 7 ision) DOM Object [76] APR AP 7 P 3 actile EU,SOM Learn- ing [75] APR OD 7 P 7 orque) DOM I [82], [111] , [112] CNS [82], [111] , [82], [111] , [82], [111] , [112] 7 [111] G [112] ,(dependent algorithm [82]) [82], M[111] , [11…”
BackgroundEnd-to-End Training of Deep Visuomotor Policies
Levine, S., Finn, C., Darrell, T. J., & Abbeel, P. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1504.00702 · Cited by 1,344 · cited 6×
“) [49] no dynamics model [45, 46], SDM [49, 42, 43], SOM [45], DOM [46, 49, 42, 43] XXV Manipulation”
BackgroundMethodInfluentialMovement-produced stimulation in the development of visually guided behavior.
Held, R., & Hein, A. (1963) · Journal of Comparative and Physiological Psychology · doi:10.1037/h0040546 · Cited by 1,161
Modeling visual attention via selective tuning
Tsotsos, J. K., Culhane, S. M., Kei Wai, W. Y., Lai, Y., Davis, N., & Nuflo, F. (1995) · Artificial Intelligence · doi:10.1016/0004-3702(95)00025-9 · Cited by 1,143 · cited 1×
“of freedom [17]–[19] and models of visual attention [20], [21] that these active vision systems could use for guiding their gaze.”
BackgroundSupersizing self-supervision: Learning to grasp from 50K tries and 700 robot hours
Pinto, L., & Gupta, A. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487517 · Cited by 1,047 · cited 4×
“1) Commonalities and differences between CNS and APR: Approaches that exploit the novel sensory signal (CNS) also rely on regularities in the sensory response to an interaction.”
BackgroundInfluentialBallard, D. H. (1991) · Artificial Intelligence · doi:10.1016/0004-3702(91)90080-4 · Cited by 1,022 · cited 1×
“These signals are beneficial for estimating the quantities that are relevant to manipulation problems such as haptic, audio and visual data correlated over time.”
BackgroundAloimonos, J., Weiss, I., & Bandyopadhyay, A. (1988) · International Journal of Computer Vision · doi:10.1007/bf00133571 · Cited by 931 · cited 4×
“One example is models of multiview or perspective geometry for camera sensors [14], [124].”
BackgroundMethodInfluentialBajcsy, R. (1988) · Proceedings of the IEEE · doi:10.1109/5.5968 · Cited by 830 · cited 5×
“Recently, Bajcsy et al. [22] revisited AP giving an excellent historical perspective on the field and a new, broader definition of an active perceiver based on decades of research: “An agent is an active perceiver if it knows why it wishes to sense, and then chooses what to perceive, and determines how, when and where…”
MethodInfluentialUnsupervised Learning for Physical Interaction through Video Prediction
Finn, C., Goodfellow, I., & Levine, S. (2016) · arXiv · doi:10.48550/arxiv.1605.07157 · Cited by 759 · cited 1×
“Less obvious is the result by Kjellström et al. [11] who showed that classifying objects is easier if they are observed while being used by a person.”
Estimation of Inertial Parameters of Manipulator Loads and Links
Atkeson, C. G., An, C. H., & Hollerbach, J. M. (1986) · The International Journal of Robotics Research · doi:10.1177/027836498600500306 · Cited by 590 · cited 2×
“[75] estimate the dynamics parameters of a robotic arm and the load at the end effector.”
BackgroundLearning to Poke by Poking: Experiential Learning of Intuitive PhysicsPreprint
Agrawal, P., Nair, A., Abbeel, P., Malik, J., & Levine, S. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.07419 · Cited by 570
An exploration of sensorless manipulation
Erdmann, M. A., & Mason, M. T. (1988) · IEEE Journal on Robotics and Automation · doi:10.1109/56.800 · Cited by 463
A survey of point-based POMDP solvers
Shani, G., Pineau, J., & Kaplow, R. (2013) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-012-9200-2 · Cited by 422
Bayesian Exploration for Intelligent Identification of Textures
Fishel, J. A., & Loeb, G. E. (2012) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2012.00004 · Cited by 358 · cited 2×
“More recent examples include [23] to learn haptic object representations, [34]–[36] for object detection and pose estimation, [37]–[39] for reconstructing the shape of objects or the environment, and [40]–[42] for texture classification or description.”
BackgroundBajcsy, R., Aloimonos, Y., & Tsotsos, J. K. (2018) · Autonomous Robots · doi:10.1007/s10514-017-9615-3 · Cited by 328 · cited 2×
“A more complete review of these early approaches toward active haptic perception is contained in [22] and [30].”
BackgroundA Survey of Robot Tactile Sensing Technology
Nicholls, H. R., & Lee, M. H. (1989) · The International Journal of Robotics Research · doi:10.1177/027836498900800301 · Cited by 325 · cited 2×
“A more complete review of these early approaches toward active haptic perception is contained in [22] and [30].”
BackgroundMethodDiscriminatively Trained Sparse Code Gradients for Contour Detection
Ren, X., & Bo, L. (2012) · neural information processing systems · Cited by 296
Learning contact-rich manipulation skills with guided policy search
Levine, S., Wagener, N., & Abbeel, P. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7138994 · Cited by 267 · cited 1×
“Less obvious is the result by Kjellström et al. [11] who showed that classifying objects is easier if they are observed while being used by a person.”
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning
Wu, J., Yildirim, I., Lim, J. J., Freeman, W. T., & Tenenbaum, J. B. (2016) · Cited by 264
Team IHMC's Lessons Learned from the DARPA Robotics Challenge Trials
Johnson, M., Shrewsbury, B., Bertrand, S., Wu, T., Duran, D., Floyd, M., Abeles, P., Stephen, D., Mertins, N., Lesman, A., et al. (2015) · Journal of Field Robotics · doi:10.1002/rob.21571 · Cited by 250 · cited 1×
“One can further ask: how can manipulation actions be found that combine these two objectives—achieving a goal and obtaining information—in such a way that desirable criteria about the resulting sequence of actions (time, effort, risk, etc.) are optimized?”
BackgroundCreating Realistic Virtual Textures from Contact Acceleration Data
Romano, J. M., & Kuchenbecker, K. J. (2012) · IEEE Transactions on Haptics · doi:10.1109/toh.2011.38 · Cited by 244 · cited 1×
“For example, in [92] and [42], it has been shown that surface and material properties of objects can be more accurately estimated if the robot’s haptic sensor is moved along the surface of the object.”
BackgroundSE3-nets: Learning rigid body motion using deep neural networks
Byravan, A., & Fox, D. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989023 · Cited by 236 · cited 1×
“One example is models of multiview or perspective geometry for camera sensors [14], [124].”
MethodVisual object-action recognition: Inferring object affordances from human demonstration
Kjellström, H., Romero, J., & Kragić, D. (2011) · Computer Vision and Image Understanding · doi:10.1016/j.cviu.2010.08.002 · Cited by 232
A computational approach for obstruction-free photography
Xue, T., Rubinstein, M., Liu, C., & Freeman, W. T. (2015) · ACM Transactions on Graphics · doi:10.1145/2766940 · Cited by 225 · cited 1×
“[13] exploit whole image sequences to separate obstructing foreground like fences or window reflections from the main subject of the images, i.”
BackgroundOnline movement adaptation based on previous sensor experiences
Pastor, P., Righetti, L., Kalakrishnan, M., & Schaal, S. (2011) · 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2011.6095059 · Cited by 219 · cited 4×
“This emphasizes the blurred boundary which is traditionally drawn between manipulation and perception.”
BackgroundMethodInfluentialSelf-citationAutonomous generation of complete 3D object models using next best view manipulation planning
Krainin, M., Curless, B., & Fox, D. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980429 · Cited by 199 · cited 1×
“[88] present an approach where a robot autonomously builds an object model while holding the object in its hand.”
BackgroundGaussian process implicit surfaces for shape estimation and grasping
Dragiev, S., Toussaint, M., & Gienger, M. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980395 · Cited by 197 · cited 13×
“[58] [58, 59, 70] B RO C [58, 59], M [70] P [70],M [58], B [59] 3(Tactile, Vision [59, 58]), 7(Vision [70]) static environment [58, 59], no dynamics [70], SOM, EU”
BackgroundInfluentialModeling and Rendering Realistic Textures from Unconstrained Tool-Surface Interactions
Culbertson, H., Unwin, J., & Kuchenbecker, K. J. (2014) · IEEE Transactions on Haptics · doi:10.1109/toh.2014.2316797 · Cited by 192 · cited 1×
“[91] demonstrate how either unconstrained interactions in a plane or fixed interaction primitives lead to novel haptic sensory signals to ease the learning of material properties.”
BackgroundThe Curious Robot: Learning Visual Representations via Physical Interactions
Pinto, L., Gandhi, D., Han, Y., Park, Y., & Gupta, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-46475-6_1 · Cited by 190
Global Localization of Objects via Touch
Petrovskaya, A., & Khatib, O. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2138450 · Cited by 168 · cited 1×
“More recent examples include [23] to learn haptic object representations, [34]–[36] for object detection and pose estimation, [37]–[39] for reconstructing the shape of objects or the environment, and [40]–[42] for texture classification or description.”
BackgroundReactive grasping using optical proximity sensors
Hsiao, K., Nangeroni, P., Huber, M., Saxena, A., & Ng, A. Y. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152849 · Cited by 162 · cited 3×
“Examples of these approaches include [37], [84], [87], [94], and [102].”
BackgroundInfluentialA Probabilistic Framework for Learning Kinematic Models of Articulated Objects
Sturm, J., Stachniss, C., & Burgard, W. (2011) · Journal of Artificial Intelligence Research · doi:10.1613/jair.3229 · Cited by 161 · cited 2×
“Examples are [100] and the following in paper set Object Segmentation I: [44], [53], [54], [55], [95], [99], and [96].”
BackgroundMethodClosing the learning-planning loop with predictive state representations
Boots, B., Siddiqi, S. M., & Gordon, G. J. (2011) · The International Journal of Robotics Research · doi:10.1177/0278364911404092 · Cited by 159 · cited 2×
“Such methods are often solved by formulating them as POMDPs.”
MethodLearning state representations with robotic priors
Jonschkowski, R., & Brock, O. (2015) · Autonomous Robots · doi:10.1007/s10514-015-9459-7 · Cited by 158 · cited 9×
“Jonschkowski and Brock [71] achieve this by introducing a set of hand-defined priors in a loss function that is minimal if the state representation best matches these priors.”
BackgroundMethodInfluentialSelf-citationRobotic learning of haptic adjectives through physical interaction
Chu, V. C.-M., McMahon, I. T., Riano, L., McDonald, C. G., He, Q. L., Perez-Tejada, J. M., Arrigo, M., Darrell, T., & Kuchenbecker, K. J. (2014) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2014.09.021 · Cited by 158 · cited 2×
“More recent examples include [23] to learn haptic object representations, [34]–[36] for object detection and pose estimation, [37]–[39] for reconstructing the shape of objects or the environment, and [40]–[42] for texture classification or description.”
BackgroundCombining active learning and reactive control for robot grasping
Kroemer, O., Detry, R. J., Piater, J., & Peters, J. (2010) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2010.06.001 · Cited by 152 · cited 1×
“For the first three applications (Object Segmentation, Articulation Model Estimation and Object Dynamics Learning), we use a couple of simple examples (Figures 5 and 6) to allow the reader to better appreciate the benefits of IP and understand its distinction to Active Perception.”
MethodBringing clothing into desired configurations with limited perception
Cusumano-Towner, M., Singh, A., Miller, S., O’Brien, J. F., & Abbeel, P. (2011) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2011.5980327 · Cited by 144
Learning force-based manipulation of deformable objects from multiple demonstrations
Lee, A. X., Lu, H., Gupta, A., Levine, S., & Abbeel, P. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7138997 · Cited by 140 · cited 4×
“et al. [44] where the authors learn the mapping from current state to next best action in a policy search framework. In approaches such as those of Kappler et al. [45], Pastor et al. [46], Lee et al. [47], the training data is given by demonstrations instead of letting the robot autonomously explore through trial and…”
BackgroundMethodInfluentialEnhancing visual perception of shape through tactile glances
Björkman, M., Bekiroglu, Y., Högman, V., & Kragić, D. (2013) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2013.6696808 · Cited by 126 · cited 2×
“[90] show examples that initialize a model from visual data and then further augment it with tactile data.”
BackgroundPhysics-Based Grasp Planning Through Clutter
Doğar, M. R., Hsiao, K., Ciocarlie, M., & Srinivasa, S. S. (2012) · Robotics: Science and Systems · doi:10.15607/rss.2012.viii.008 · Cited by 119 · cited 1×
“Furthermore, we explain the two postulated benefits of IP in more detail.”
BackgroundLearning Dynamic Tactile Sensing With Robust Vision-Based Training
Kroemer, O., Lampert, C. H., & Peters, J. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2121130 · Cited by 113 · cited 1×
“, [45], [46], [51], [52], and [56] in Object Segmentation I, [93] in Multimodal Object Model Learning I and [39], [90] in Multimodal Object Model Learning II, the planar motion assumption is used not only for scene segmentation, but also to track the movement of objects in the environment.”
BackgroundInteractive segmentation for manipulation in unstructured environments
Kenney, J., Buckley, T., & Brock, O. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152393 · Cited by 113 · cited 4×
“[55] push an object on the plane and accumulate visual data to build a model of the object.”
BackgroundInfluentialSelf-citationAsfour, T., Welke, K., Azad, P., Ude, A., & Dillmann, R. (2008) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2008.4755993 · Cited by 107 · cited 1×
“of freedom [17]–[19] and models of visual attention [20], [21] that these active vision systems could use for guiding their gaze.”
BackgroundNo falls, no resets: Reliable humanoid behavior in the DARPA robotics challenge
Atkeson, C. G., Franklin, P., Gennert, M. A., Graff, J. P., Peng, H., Jaeger, A. M., Kim, J., Knoedler, K., Li, L., Liu, C., et al. (2015) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2015.7363436 · Cited by 105
Interactive singulation of objects from a pile
Chang, L., Smith, J. R., & Fox, D. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224575 · Cited by 104 · cited 4×
“Examples are clustering methods that assign fixed labels [45], [50], [51], [56] to the variable of interest.”
BackgroundMethodInfluentialUnderstanding Hand-Object Manipulation with Grasp Types and Object Attributes
Cai, M., Kitani, K., & Sato, Y. (2016) · Robotics: Science and Systems · doi:10.15607/rss.2016.xii.034 · Cited by 104 · cited 2×
“An interaction may only be locally applied to the scene (e.g. through pushing or pulling a specific object) or it may affect the scene globally (e.g. shaking a tray with objects standing on it).”
BackgroundLearning to Manipulate Unknown Objects in Clutter by Reinforcement
Boularias, A., Bagnell, J. A., & Stentz, A. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9378 · Cited by 104 · cited 3×
“This emphasizes the blurred boundary which is traditionally drawn between manipulation and perception.”
BackgroundMethodPose estimation for planar contact manipulation with manifold particle filters
Koval, M. C., Pollard, N. S., & Srinivasa, S. S. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915571007 · Cited by 95
Kraft, D., Pugeault, N., Başeski, E., Popović, M., Kragić, D., Kalkan, S., Wörgötter, F., & Krüger, N. (2008) · International Journal of Humanoid Robotics · doi:10.1142/s021984360800139x · Cited by 80
Autoscanning for coupled scene reconstruction and proactive object analysis
Xu, K., Huang, H. F., Shi, Y., Li, H., Long, P., Caichen, J., Sun, W., & Chen, B. (2015) · ACM Transactions on Graphics · doi:10.1145/2816795.2818075 · Cited by 79 · cited 1×
“Other IP approaches pursue either a grasping or manipulation goal.”
BackgroundJain, A., & Kemp, C. C. (2010) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2010.5509445 · Cited by 79
Active articulation model estimation through interactive perception
Hausman, K., Niekum, S., Osentoski, S., & Sukhatme, G. S. (2015) · 2015 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2015.7139655 · Cited by 77 · cited 3×
“Examples of such approaches can be seen in paper sets Object Segmentation II [98], [101], in Articulation Model Estimation II [36] and in the paper set Pose”
BackgroundMethodSelf-citationGrounding semantic categories in behavioral interactions: Experiments with 100 objects
Sinapov, J., Schenck, C., Staley, K., Sukhoy, V., & Stoytchev, A. (2012) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2012.10.007 · Cited by 76 · cited 2×
“[59], [60], and Sinapov and Stoytchev [62] let a robot interact with a set of objects that are characterized by different attributes, such as rigid or deformable, heavy or light, and slippery or not.”
BackgroundPre- and post-contact policy decomposition for planar contact manipulation under uncertainty
Koval, M. C., Pollard, N. S., & Srinivasa, S. S. (2015) · The International Journal of Robotics Research · doi:10.1177/0278364915594474 · Cited by 74 · cited 4×
“1) Commonalities and differences between CNS and APR: Approaches that exploit the novel sensory signal (CNS) also rely on regularities in the sensory response to an interaction.”
BackgroundInfluentialProbabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments
van Hoof, H., Kroemer, O., & Peters, J. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2014.2334912 · Cited by 73 · cited 3×
“This emphasizes the blurred boundary which is traditionally drawn between manipulation and perception.”
BackgroundZhang, L., & Trinkle, J. C. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225125 · Cited by 72 · cited 6×
“They also use the knowledge of the interaction in [62, 60] to correlate various sensor modalities in the S ×A× t. Zhang and Trinkle [76], Koval et al. [78] track object pose using visual and tactile data while a robot is pushing this object on a plane.”
BackgroundInfluentialUsing manipulation primitives for brick sorting in clutter
Gupta, M., & Sukhatme, G. S. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6224787 · Cited by 71 · cited 9×
“[56], Gupta and Sukhatme [50], Hausman et al.”
BackgroundMethodInfluentialSelf-citationKatz, D., Pyuro, Y., & Brock, O. (2008) · Robotics: Science and Systems IV · doi:10.15607/rss.2008.iv.033 · Cited by 70 · cited 2×
“del Estimation Otte et al. [68] Pillai et al. [16] Hausman et al. [33] Barragan et al. [60]´ Mart´ın Mart ´ın and Brock [17] Jain and Kemp [56] Sturm et al. [15] Karayiannidis et al. [57] Katz et al. [69] Katz et al. [14] Fig. 6. Paper categorization based on application areas. Papers that address multiple application…”
BackgroundSelf-citationUncertainty aware grasping and tactile exploration
Dragiev, S., Toussaint, M., & Gienger, M. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630564 · Cited by 67 · cited 14×
“[58] [58, 59, 70] B RO C [58, 59], M [70] P [70],M [58], B [59] 3(Tactile, Vision [59, 58]), 7(Vision [70]) static environment [58, 59], no dynamics [70], SOM, EU”
BackgroundInfluentialEfficient touch based localization through submodularity
Javdani, S., Klingensmith, M., Bagnell, J. A., Pollard, N. S., & Srinivasa, S. S. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630818 · Cited by 66 · cited 4×
“More recent examples include [23] to learn haptic object representations, [34]–[36] for object detection and pose estimation, [37]–[39] for reconstructing the shape of objects or the environment, and [40]–[42] for texture classification or description.”
BackgroundMethodInfluentialRobust grasping under object pose uncertainty
Hsiao, K., Kaelbling, L. P., & Lozano‐Pérez, T. (2011) · Autonomous Robots · doi:10.1007/s10514-011-9243-2 · Cited by 64 · cited 2×
“[113] estimate the belief state by conditioning the observations on the expected action outcomes.”
BackgroundLearning deep dynamical models from image pixels
Wahlström, N., Schön, T. B., & Deisenroth, M. P. (2015) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2015.12.271 · Cited by 61
Doğar, M. R., Koval, M. C., Tallavajhula, A., & Srinivasa, S. S. (2013) · Autonomous Robots · doi:10.1007/s10514-013-9372-x · Cited by 58
Self-supervised learning of grasp dependent tool affordances on the iCub Humanoid robot
Mar, T., Tikhanoff, V., Giorgio Metta, B., & Natale, L. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139640 · Cited by 57 · cited 4×
“1) Commonalities and differences between CNS and APR: Approaches that exploit the novel sensory signal (CNS) also rely on regularities in the sensory response to an interaction.”
BackgroundInfluentialThree-dimensional object reconstruction of symmetric objects by fusing visual and tactile sensing
Ilonen, J., Bohg, J., & Kyrki, V. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913497816 · Cited by 56 · cited 2×
“It requires the agent to reason about so called Expectation-Action tuples to select the next best action.”
BackgroundMethodSelf-citationMartin Martin, R., & Brock, O. (2014) · 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2014.6942902 · Cited by 55 · cited 3×
“Most recent methods include reasoning about actions to actively reduce the uncertainty in the articulation model estimates [98, 100, 101].”
BackgroundMethodSelf-citationLearning relational object categories using behavioral exploration and multimodal perception
Sinapov, J., Schenck, C., & Stoytchev, A. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907696 · Cited by 55 · cited 2×
“[59], [60], and Sinapov and Stoytchev [62] let a robot interact with a set of objects that are characterized by different attributes, such as rigid or deformable, heavy or light, and slippery or not.”
BackgroundMethodData-Driven Online Decision Making for Autonomous Manipulation
Kappler, D., Pástor, P., Kalakrishnan, M., Wüthrich, M., & Schaal, S. (2015) · Robotics: Science and Systems · doi:10.15607/rss.2015.xi.044 · Cited by 55 · cited 3×
“[66] represent the task as a sequence of demonstrated be-”
MethodInfluentialSelf-citationLearning compound multi-step controllers under unknown dynamics
Han, W., Levine, S., & Abbeel, P. (2015) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2015.7354297 · Cited by 51 · cited 1×
“Less obvious is the result by Kjellström et al. [11] who showed that classifying objects is easier if they are observed while being used by a person.”
Efficient Planning in Non-Gaussian Belief Spaces and Its Application to Robot Grasping
Platt, R., Kaelbling, L. P., Lozano‐Pérez, T., & Tedrake, R. (2016) · Springer tracts in advanced robotics · doi:10.1007/978-3-319-29363-9_15 · Cited by 48 · cited 2×
“Examples of these approaches include [81] and [83].”
BackgroundLearning Articulated Motions From Visual Demonstration
Pillai, S., Walter, M. R., & Teller, S. J. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.050 · Cited by 47 · cited 3×
“[99], and Martı́n Martı́n and Brock [96] aim at understanding the structure of AO by observing their motion when they are interacted with.”
BackgroundMethodThe next best touch for model-based localization
Hebert, P. D. N., Howard, T. M., Hudson, N., Ma, J., & Burdick, J. W. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630562 · Cited by 42 · cited 1×
“More recent examples include [23] to learn haptic object representations, [34, 35, 36] for object detection and pose estimation, [37, 38, 39] for reconstructing the shape of objects or the environment as well as [40, 41, 42] for texture classification or description.”
BackgroundMAKING OBJECT LEARNING AND RECOGNITION AN ACTIVE PROCESS
Ude, A., Omrčen, D., & Cheng, G. (2008) · International Journal of Humanoid Robotics · doi:10.1142/s0219843608001406 · Cited by 42 · cited 1×
“This means that they aim to manipulate the environment to bring it into a desired state.”
BackgroundUnifying perception, estimation and action for mobile manipulation via belief space planning
Kaelbling, L. P., & Lozano‐Pérez, T. (2012) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2012.6225237 · Cited by 41 · cited 3×
“Similarly, Koval et al. [78], Kaelbling and Lozano-Pérez [81], Platt et al. [83] exploit the regularities in S×A× t to facilitate task oriented grasping, i.e locate and grasp an object of interest.”
BackgroundAn integrated approach to visual perception of articulated objects
Martin-Martin, R., Hofer, S., & Brock, O. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487714 · Cited by 41 · cited 1×
“7 ision) 56, 44, 49], [109] , [49], [109] II 48] APR AP M P 7 ision) EU - I [57] CNS PM M P 7 ision) DOM - II [58] APR AP G P 7 ision) EU Esti- gmen- tation [43] CNS O 7 P 7 ision) SOM Esti- I [100], [103, 95, 110] CNS 7 95, 110] [100] P 7 ision) dynamics [103] SDM [99, 110] EU 99, 110] [100] Esti- II 102, 98, 101] AP…”
Self-citationMaximally informative interaction learning for scene exploration
van Hoof, H., Kroemer, O., Amor, H. B., & Peters, J. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6386008 · Cited by 39 · cited 2×
“The vast research area of Computer Vision focuses on interpreting static images, video or other visual data.”
BackgroundEarly integration of vision and manipulation
Metta, G., & Fitzpatrick, P. (2004) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2003.1223994 · Cited by 39
Learning reliable manipulation strategies without initial physical models
Christiansen, A. D., Mason, M. T., & Mitchell, T. M. (2002) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.1990.126165 · Cited by 38 · cited 2×
“[79] demonstrate this in a tray-tilting task for bringing the object lying on this tray into a desired configuration.”
BackgroundTracking-based interactive segmentation of textureless objects
Hausman, K., Bálint-Benczédi, F., Pangercic, D., Márton, Z.-C., Ueda, R., Okada, K., & Beetz, M. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6630713 · Cited by 38 · cited 3×
“Examples are clustering methods that assign fixed labels [45], [50], [51], [56] to the variable of interest.”
BackgroundMethodSelf-citationIntegrating visual perception and manipulation for autonomous learning of object representations
Schiebener, D., Morimoto, J., Asfour, T., & Ude, A. (2013) · Adaptive Behavior · doi:10.1177/1059712313484502 · Cited by 37 · cited 2×
“proaches that perform object segmentation and categorization can be found in [46] and [57].”
BackgroundTsikos, C. J., & Bajcsy, R. K. (1991) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.88140 · Cited by 36 · cited 1×
“Tsikos and Bajcsy [25], [26] propose to use a robot arm to make the scene simpler for the vision system through actions like pick, push, and shake.”
BackgroundBayesian Action&Perception: Representing the World in the Brain
Loeb, G. E., & Fishel, J. A. (2014) · Frontiers in Neuroscience · doi:10.3389/fnins.2014.00341 · Cited by 33 · cited 1×
“The problem of selecting the next best action may be based on submodularity [36], the variance in a Gaussian Process [37], [39], or the Bhattacharyya coefficient between two normal distributions [40], [41].”
BackgroundPhysical interaction for segmentation of unknown textured and non-textured rigid objects
Schiebener, D., Ude, A., & Asfour, T. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907586 · Cited by 30
Active In-Hand Object Recognition on a Humanoid Robot
Browatzki, B., Tikhanoff, V., Giorgio Metta, B., Bülthoff, H., & Wallraven, C. (2014) · IEEE Transactions on Robotics · doi:10.1109/tro.2014.2328779 · Cited by 29 · cited 1×
“tile) EU Object I [93, 89], [23] CNS [93] 7 P 3 ac- 89], [23] [93], [23] , [89], [23] 89], [23] , [89] Object II 39, 90], [117, 119, 120] , [121] APR O,AP [117, 120] 90], [121] , OD 119] , 90] M[88], [118, 119] , 7 [39, 90], [117, 120] , [121] P[88, 39], [121] , [117, 120] , B[37], [119] 3 ision[37, 90], [117] ), 7 [8…”
Towards manipulation-driven vision
Fitzpatrick, P., & Giorgio Metta, B. (2003) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/irds.2002.1041360 · Cited by 27 · cited 9×
“Fitzpatrick and Metta [53], Metta and Fitzpatrick [54], Kenney et al. [55] propose example approaches that assume no stochasticity in the system, and model both the dynamics and observations deterministically.”
BackgroundInfluentialInteractive Bayesian identification of kinematic mechanisms
Barragán, P. R., Kaelbling, L. P., & Lozano‐Pérez, T. (2014) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2014.6907126 · Cited by 22 · cited 2×
“Most recent methods include reasoning about actions to actively reduce the uncertainty in the articulation model estimates [98], [100], [101].”
BackgroundMethodHardware development of the Yorick series of active vision systems
SHARKEY, P. M., Murray, D. W., McLauchlan, P. F., & Brooker, J. P. (1998) · Microprocessors and Microsystems · doi:10.1016/s0141-9331(98)00051-9 · Cited by 22 · cited 1×
“In this context, researchers developed artificial vision systems with many degrees of freedom [17, 18, 19] and models of visual attention [20, 21] that these active vision systems could use for guiding their gaze.”
BackgroundStrategies for multi-modal scene exploration
Bohg, J., Johnson‐Roberson, M., Björkman, M., & Kragić, D. (2010) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2010.5652967 · Cited by 21 · cited 3×
“More recent examples include [23] to learn haptic object representations, [34]–[36] for object detection and pose estimation, [37]–[39] for reconstructing the shape of objects or the environment, and [40]–[42] for texture classification or description.”
BackgroundSelf-citationObject segmentation and learning through feature grouping and manipulation
Kuzmič, E. S., & Ude, A. (2010) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2010.5686266 · Cited by 21 · cited 4×
“These are listed in paper set Object Segmentation I which include the works of Chang et al. [56], Gupta and Sukhatme [50], Hausman et al. [51, 45], Kuzmic and Ude [52], Schiebener et al. [46].”
BackgroundInfluentialScene Understanding through Autonomous Interactive Perception
Bergström, N., Ek, C. H., Björkman, M., & Kragić, D. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23968-7_16 · Cited by 20 · cited 1×
“Examples are [100] and the following in paper set Object Segmentation I: [44], [53], [54], [55], [95], [99], and [96].”
BackgroundEntropy-based strategies for physical exploration of the environment's degrees of freedom
Otte, S., Kulick, J., Toussaint, M., & Brock, O. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942623 · Cited by 20 · cited 2×
“Examples of such approaches can be seen in paper sets Object Segmentation II [98], [101], in Articulation Model Estimation II [36] and in the paper set Pose”
BackgroundMethodSelf-citationSensorimotor coordination in a “baby” robot: learning about objects through grasping
Natale, L., Orabona, F., Giorgio Metta, B., & Sandini, G. (2007) · Progress in brain research · doi:10.1016/s0079-6123(07)64022-9 · Cited by 19
Model-free robot manipulation of doors and drawers by means of fixed-grasps
Karayiannidis, Y., Smith, C., Vina, F., Ögren, P., & Kragić, D. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631214 · Cited by 19 · cited 2×
“This emphasizes the blurred boundary which is traditionally drawn between manipulation and perception.”
BackgroundMethodActive Perception and Exploratory Robotics
Bajcsy, R. K. (1993) · Springer eBooks · doi:10.1007/978-3-642-58069-7_1 · Cited by 15 · cited 1×
“Bajcsy [27] and Bajcsy and Sinha [28] propose the Looker and”
BackgroundA Factorization Approach to Manipulation in Unstructured Environments
Katz, D., & Brock, O. (2011) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-19457-3_17 · Cited by 14 · cited 6×
“Examples include: Barragán et al. [100] and the following authors in paper set Object Segmentation I: Fitzpatrick and Metta [53], Metta and Fitzpatrick [54], Kenney et al. [55] and Bergström et al. [44], Sturm et al. [95], Pillai et al. [99], Martı́n Martı́n and Brock [96].”
InfluentialSelf-citationExploration of unknown object by active touch of robot hand
Kim, M. J., Choi, M., Kim, Y. B., Liu, F., Moon, H., Koo, J. C., & Choi, H. R. (2014) · International Journal of Control Automation and Systems · doi:10.1007/s12555-013-0328-x · Cited by 14 · cited 1×
“approaches towards active haptic perception is contained in [30, 22]. More recent examples include [23] to learn haptic object representations, [34, 35, 36] for object detection and pose estimation, [37, 38, 39] for reconstructing the shape of objects or the environment as well as [40, 41, 42] for texture classificatio…”
ResultRobotic manipulation in object composition space
Pajarinen, J., & Kyrki, V. (2014) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2014.6942372 · Cited by 12 · cited 3×
“1) Commonalities and differences between CNS and APR: Approaches that exploit the novel sensory signal (CNS) also rely on regularities in the sensory response to an interaction.”
BackgroundMichel, D., Zabulis, X., & Argyros, A. (2014) · Machine Vision and Applications · doi:10.1007/s00138-014-0602-9 · Cited by 12 · cited 1×
“90], [117] ), 7 [88], [119] , [121] ), 3 [118]) , 3 FT[117]) , actile, [120] no 90], 119, 120] , [121] , DDM[117] , DOM[120] 90], [119] , 90], [118] No [119] Object Object Recognition 62, 60], [122] [123] CNS 62, 60],[122] 7 P 3 actile), 7 123]) 60] [122] , SDM[123] 62, 60] [122] , [123] 60] [122] Object Grasp Plannin…”
Decision making under uncertain segmentations
Pajarinen, J., & Kyrki, V. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139359 · Cited by 10 · cited 1×
“State-of-the-art approaches in Computer Vision as e.g. [107, 108] require enormous amounts of training data to handle these variations.”
BackgroundGrounded object individuation by a humanoid robot
Sinapov, J., & Stoytchev, A. (2013) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2013.6631289 · Cited by 10 · cited 3×
“[59], [60], and Sinapov and Stoytchev [62] let a robot interact with a set of objects that are characterized by different attributes, such as rigid or deformable, heavy or light, and slippery or not.”
BackgroundLearning Predictive State Representation for in-hand manipulation
Stork, J. A., Ek, C. H., Bekiroglu, Y., & Kragić, D. (2015) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2015.7139641 · Cited by 9
Sensorimotor processes for learning object representations
Omrčen, D., Ude, A., Welke, K., Asfour, T., & Dillmann, R. (2007) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2007.4813861 · Cited by 9 · cited 1×
“on[37, 90], [117] ), 7 [88], [119] , [121] ), 3 [118]) , 3 FT[117]) , actile, [120] no 90], 119, 120] , [121] , DDM[117] , DOM[120] 90], [119] , 90], [118] No [119] Object Object Recognition 62, 60], [122] [123] CNS 62, 60],[122] 7 P 3 actile), 7 123]) 60] [122] , SDM[123] 62, 60] [122] , [123] 60] [122] Object Grasp…”
Exploration of Surfaces for Robot Mobility
Sinha, P. R., & Bajcsy, R. K. (1990) · ScholarlyCommons (University of Pennsylvania) · Cited by 7
Sensorimotor Learning Using Active Perception in Continuous Domains
Salganicoff, M., & Bajcsy, R. K. (1991) · ScholarlyCommons (University of Pennsylvania) · Cited by 6
Towards Interactive Object Recognition
Hausman, K., Corcos, C., Mueller, J., Sha, F., & Sukhatme, G. S. (2014) · Cited by 5
Self-citationInteractive Segmentation of Textured and Textureless Objects
Hausman, K., Pangercic, D., Márton, Z.-C., Bálint-Benczédi, F., Bersch, C., Gupta, M., Sukhatme, G. S., & Beetz, M. (2015) · Studies in systems, decision and control · doi:10.1007/978-3-319-26327-4_10 · Cited by 3 · cited 3×
“Examples are clustering methods that assign fixed labels [45], [50], [51], [56] to the variable of interest.”
BackgroundMethodSelf-citationRevisiting Active PerceptionPreprint
Bajcsy, R., Aloimonos, Y., & Tsotsos, J. K. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.02729 · Cited by 3 · cited 2×
“A more complete review of these early approaches toward active haptic perception is contained in [22] and [30].”
BackgroundGrasp, motion, view planning on dual-arm humanoid for manipulating in-hand object
Tsuda, A., Kakiuchi, Y., Nozawa, S., Ueda, R., Okada, K., & Inaba, M. (2011) · IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO) · doi:10.1109/arso.2011.6301957 · Cited by 1 · cited 1×
“Estima- I 42] CNS OD, [42] 7 P 7 actile) [42] Estima- II [41] APR OD M P 7 actile) EU Object I [93, 89], [23] CNS [93] 7 P 3 ac- 89], [23] [93], [23] , [89], [23] 89], [23] , [89] Object II 39, 90], [117, 119, 120] , [121] APR O,AP [117, 120] 90], [121] , OD 119] , 90] M[88], [118, 119] , 7 [39, 90], [117, 120] , [121…”
Research works printed but not linked: 14
- allen, 1985, Two sensors are better than one: Example of integration of vision and touch, Proc Int Symp Robot Res
- goldberg, 1984, Active touch and robot perception, Cognition Brain Theory, 7, 199
- bajscy, 1988, Shape from touch, Advances in Automation and Robotics
- sandini, 1993, Vision During Action
- natale, 0, Learning haptic representation of objects, Proc Int Conf Intell Manipulation Grasping
- noë, 2004, Action in Perception
- gibson, 1966, The Senses Considered as Perceptual Systems
- katz, 0, Interactive segmentation of articulated objects in 3D, Mobile Manipulation Workshop Proc Int Conf Robot Automat
- singh, 2004, Predictive state representations: A new theory for modeling dynamical systems, Proceedings of the 20th conference on Uncertainty in artificial intelligence, 512
- gibson, 1979, The Ecological Approach to Visual Perception
- katz, 2014, Interactive Perception of Articulated Objects, 79, 301
- natale, 0, A sensitive approach to grasping, Proc 6th Int Workshop Epigenetic Robot, 87
- pahlavan, 1993, Active vision as a methodology, Active Perception, 19
- torres-jara, 2005, Tapping into touch, Proc 5th Int Workshop on Epigenetic Robotics, 79
Cited by
Trends and challenges in robot manipulation
Billard, A., & Kragic, D. (2019) · Science · doi:10.1126/science.aat8414 · Cited by 993
“Today, it is also recognized that perception and control are tightly coupled, and the field of interactive perception (63) regardsmanipulation as ameans to perceive and perception as a means to achieve better manipulation.”
BackgroundDeep Reinforcement Learning: An Overview
Li, Y. (2017) · arXiv · doi:10.48550/arxiv.1701.07274 · Cited by 762
Neural Fields in Visual Computing and Beyond
Xie, Y., Takikawa, T., Saito, S., Litany, O., Yan, S., Khan, N., Tombari, F., Tompkin, J., sitzmann, V., & Sridhar, S. (2022) · Computer Graphics Forum · doi:10.1111/cgf.14505 · Cited by 484
Lee, M. A., Zhu, Y., Srinivasan, K., Shah, P., Savarese, S., Fei-Fei, L., Garg, A., & Bohg, J. (2019) · 2019 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2019.8793485 · Cited by 349
“There is compelling evidence that the interdependence and concurrency of different sensory streams aid perception and manipulation [9, 18, 31].”
BackgroundSelf-citationState representation learning for control: An overview
Lesort, T., Díaz-Rodríguez, N., Goudou, J.-F., & Filliat, D. (2018) · Neural Networks · doi:10.1016/j.neunet.2018.07.006 · Cited by 301
“This is for instance the case of representation learning from different temporal signals in [Duan, 2017, Bohg et al., 2017].”
Background
Metadata
- Authors
- Bohg, J., Hausman, K., Sankaran, B., Brock, O., Kragic, D., Schaal, S., & Sukhatme, G. S.
- Affiliations
- Max Planck Institute for Intelligent Systems (DE)
- University of Southern California (US)
- Technische Universität Berlin (DE)
- Venue
- IEEE Transactions on Robotics
- Published
- 2017-12
- Volume
- 33
- Issue
- 6
- Pages
- 1273-1291
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W2337977475
- Cited by
- 227
- References
- 118
- Citations by year
- 2026: 16 · 2025: 37 · 2024: 30 · 2023: 30 · 2022: 27 · 2021: 28 · 2020: 23 · 2019: 22 · 2018: 11 · 2017: 3
- FWCI
- 10.14
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- National Science Foundation (IIS-1205249, IIS-1017134, EECS-0926052)
- Office of Naval Research
- Okawa Foundation
- Max Planck Society
- German Science Foundation (DFG) (BR 2248/3-1)
- European Commission (H2020-ICT-645599)
- Soft Manipulation (Soma)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Keywords
- interactive perception, robot perception, perception-action coupling, perception-action interaction, robot-environment interaction, sensorimotor learning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.