Towards Automated Models of Activities of Daily Life

We propose automated probabilistic models of everyday activities (AM-EvA) as a novel technical means for the perception, interpretation, and analysis of everyday manipulation tasks and activities of daily life. AM-EvAs are based on action-related concepts in everyday activities such as action-related places (the place where cups are taken from the cupboard), capabilities (the objects that can be picked up single-handedly), etc. These concepts are probabilistically derived from a set of previous activities that are fully and automatically observed by computer vision and additional sensor systems. AM-EvA models enable robots and technical systems to analyze activities in the complete situation and activity context. They render the classification and the assessment of actions and situations objective and can justify the probabilistic interpretation with respect to the activities the concepts have been learned from. In this paper, we describe the current state of implementation of the system that realizes this idea of automated models of everyday activities and show example results from the observation and analysis of table setting episodes.

[1]  Ian D. Reid,et al.  Articulated Body Motion Capture by Stochastic Search , 2005, International Journal of Computer Vision.

[2]  Trevor Darrell,et al.  Discriminative Gaussian process latent variable model for classification , 2007, ICML '07.

[3]  Moritz Tenorth,et al.  Understanding and executing instructions for everyday manipulation tasks from the World Wide Web , 2010, 2010 IEEE International Conference on Robotics and Automation.

[4]  Michael Beetz,et al.  Compact models of human reaching motions for robotic control in everyday manipulation tasks , 2009, 2009 IEEE 8th International Conference on Development and Learning.

[5]  Michael J. Black,et al.  HumanEva: Synchronized Video and Motion Capture Dataset for Evaluation of Articulated Human Motion , 2006 .

[6]  Michael Beetz,et al.  Accurate Human Motion Capture Using an Ergonomics-Based Anthropometric Human Model , 2008, AMDO.

[7]  Moritz Tenorth,et al.  KNOWROB — knowledge processing for autonomous personal robots , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Michael Isard,et al.  Partitioned Sampling, Articulated Objects, and Interface-Quality Hand Tracking , 2000, ECCV.

[9]  David J. Fleet,et al.  Gaussian Process Dynamical Models , 2005, NIPS.

[10]  Michael Beetz,et al.  Bayesian Logic Networks , 2009 .

[11]  Matthew Richardson,et al.  Markov logic networks , 2006, Machine Learning.

[12]  Jessica K. Hodgins,et al.  Guide to the Carnegie Mellon University Multimodal Activity (CMU-MMAC) Database , 2008 .

[13]  Michael Beetz,et al.  Evaluation of Hierarchical Sampling Strategies in 3D Human Pose Estimation , 2008, BMVC.

[14]  Moritz Tenorth,et al.  The TUM Kitchen Data Set of everyday manipulation activities for motion tracking and action recognition , 2009, 2009 IEEE 12th International Conference on Computer Vision Workshops, ICCV Workshops.