Active Learning based on Data Uncertainty and Model Sensitivity

Robots can rapidly acquire new skills from demonstrations. However, during generalisation of skills or transitioning across fundamentally different skills, it is unclear whether the robot has the necessary knowledge to perform the task. Failing to detect missing information often leads to abrupt movements or to collisions with the environment. Active learning can quantify the uncertainty of performing the task and, in general, locate regions of missing information. We introduce a novel algorithm for active learning and demonstrate its utility for generating smooth trajectories. Our approach is based on deep generative models and metric learning in latent spaces. It relies on the Jacobian of the likelihood to detect non-smooth transitions in the latent space, i.e., transitions that lead to abrupt changes in the movement of the robot. When non-smooth transitions are detected, our algorithm asks for an additional demonstration from that specific region. The newly acquired knowledge modifies the data manifold and allows for learning a latent representation for generating smooth movements. We demonstrate the efficacy of our approach on generalising elementary skills, transitioning across different skills, and implicitly avoiding collisions with the environment. For our experiments, we use a simulated pendulum where we observe its motion from images and a 7-DoF anthropomorphic arm.

[1]  Xueyan Jiang,et al.  Metrics for Deep Generative Models , 2017, AISTATS.

[2]  Alexander G. Gray,et al.  Building Bridges: Viewing Active Learning from the Multi-Armed Bandit Lens , 2013, UAI.

[3]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[4]  Adrian F. M. Smith,et al.  Sampling-Based Approaches to Calculating Marginal Densities , 1990 .

[5]  Dana Angluin,et al.  Queries and concept learning , 1988, Machine Learning.

[6]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[7]  W. K. Hastings,et al.  Monte Carlo Sampling Methods Using Markov Chains and Their Applications , 1970 .

[8]  Crystal Chao,et al.  Transparent active learning for robots , 2010, HRI 2010.

[9]  Maya Cakmak,et al.  Designing robot learners that ask good questions , 2012, 2012 7th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[10]  David A. Cohn,et al.  Active Learning with Statistical Models , 1996, NIPS.

[11]  David A. Cohn,et al.  Training Connectionist Networks with Queries and Selective Sampling , 1989, NIPS.

[12]  David Duvenaud,et al.  Reinterpreting Importance-Weighted Autoencoders , 2017, ICLR.

[13]  Zoubin Ghahramani,et al.  Bayesian Active Learning for Classification and Preference Learning , 2011, ArXiv.

[14]  Ruzena Bajcsy,et al.  Active Learning for Vision-Based Robot Grasping , 1996, Machine Learning.

[15]  Burr Settles,et al.  Active Learning Literature Survey , 2009 .

[16]  Lars Kai Hansen,et al.  Latent Space Oddity: on the Curvature of Deep Generative Models , 2017, ICLR.

[17]  Ken E. Whelan,et al.  The Automation of Science , 2009, Science.

[18]  Christopher K. I. Williams,et al.  Magnification factors for the SOM and GTM algorithms , 1997 .

[19]  Mikhail Belkin,et al.  Back to the Future: Radial Basis Function Network Revisited , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[20]  William A. Gale,et al.  A sequential algorithm for training text classifiers , 1994, SIGIR '94.

[21]  Nikolaos Papanikolopoulos,et al.  Multi-class active learning for image classification , 2009, CVPR.

[22]  Antonio Morales,et al.  An active learning approach for assessing robot grasp reliability , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[23]  Pierre-Yves Oudeyer,et al.  Active learning of inverse models with intrinsically motivated goal exploration in robots , 2013, Robotics Auton. Syst..

[24]  Justus H. Piater,et al.  Skill Learning by Autonomous Robotic Playing using Active Learning and Creativity , 2017, ArXiv.

[25]  Ruslan Salakhutdinov,et al.  Importance Weighted Autoencoders , 2015, ICLR.

[26]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Oliver Kroemer,et al.  Combining active learning and reactive control for robot grasping , 2010, Robotics Auton. Syst..

[28]  Xin Li,et al.  Adaptive Active Learning for Image Classification , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[29]  Jan Peters,et al.  Active Incremental Learning of Robot Movement Primitives , 2017, CoRL.

[30]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[31]  Nando de Freitas,et al.  A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning , 2010, ArXiv.

[32]  Zoubin Ghahramani,et al.  Deep Bayesian Active Learning with Image Data , 2017, ICML.