Incremental learning using partial feedback for gesture-based human-swarm interaction

In this paper we consider a human-swarm interaction scenario based on hand gestures. We study how the swarm can incrementally learn hand gestures through the interaction with a human instructor providing training gestures and correction feedback. The main contribution of the paper is a novel incremental machine learning approach that makes the robot swarm learn and recognize the gestures in a distributed and decentralized fashion using binary (i.e., yes/no) feedback. It exploits cooperative information exchange and swarm's intrinsic parallelism and redundancy. We perform extensive tests using real gesture images, showing that good classification accuracies are obtained even with rather few training samples and relatively small swarms. We also show the good scalability of the approach and its relatively low requirements in terms of communication overhead.

[1]  Nikolaos Papanikolopoulos,et al.  Scalable Active Learning for Multiclass Image Classification , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Nikolaos Papanikolopoulos,et al.  Breaking the interactive bottleneck in multi-class classification with active selection and binary feedback , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[3]  Peter Auer,et al.  Using Confidence Bounds for Exploitation-Exploration Trade-offs , 2003, J. Mach. Learn. Res..

[4]  Luca Maria Gambardella,et al.  Max-pooling convolutional neural networks for vision-based hand gesture recognition , 2011, 2011 IEEE International Conference on Signal and Image Processing Applications (ICSIPA).

[5]  Yunmei Chen,et al.  Projection Onto A Simplex , 2011, 1101.6081.

[6]  Gang Chen,et al.  Beyond Banditron: A Conservative and Efficient Reduction for Online Multiclass Prediction with Bandit Setting Model , 2009, 2009 Ninth IEEE International Conference on Data Mining.

[7]  Claudio Gentile,et al.  Robust bounds for classification via selective sampling , 2009, ICML '09.

[8]  V. Vovk.  Competitive On‐line Statistics , 2001 .

[9]  Rong Jin,et al.  A Potential-based Framework for Online Multi-class Learning with Partial Feedback , 2010, AISTATS.

[10]  Rong Jin,et al.  Learning to trade off between exploration and exploitation in multiclass bandit prediction , 2011, KDD.

[11]  Wei-Min Shen.  Efficient Incremental Induction of Decision Lists. Can Incremental Learning Outperform Non-Incremental Learning? , 1996 .

[12]  Ambuj Tewari,et al.  Efficient bandit algorithms for online multiclass prediction , 2008, ICML '08.

[13]  Giuseppe Pirlo,et al.  Updating Knowledge in Feedback-Based Multi-classifier Systems , 2011, 2011 International Conference on Document Analysis and Recognition.

[14]  Koby Crammer,et al.  Multiclass classification with bandit feedback using adaptive regularization , 2012, Machine Learning.

[15]  Ryan M. Rifkin,et al.  In Defense of One-Vs-All Classification , 2004, J. Mach. Learn. Res..

[16]  Eliseo Ferrante,et al.  Swarmanoid: A Novel Concept for the Study of Heterogeneous Robotic Swarms , 2013, IEEE Robotics & Automation Magazine.

[17]  Manfred K. Warmuth,et al.  Relative Loss Bounds for On-Line Density Estimation with the Exponential Family of Distributions , 1999, Machine Learning.

[18]  Luca Maria Gambardella,et al.  Cooperative sensing and recognition by a swarm of mobile robots , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  Christophe G. Giraud-Carrier,et al.  A Note on the Utility of Incremental Learning , 2000, AI Commun..

[20]  Claudio Gentile,et al.  Incremental Algorithms for Hierarchical Classification , 2004, J. Mach. Learn. Res..

[21]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..

[22]  Jing Peng,et al.  SVM vs regularized least squares classification , 2004, ICPR 2004.