Relational Symbol Grounding through Affordance Learning: An Overview of the ReGround Project

Symbol grounding is the problem of associating symbols from language with a corresponding referent in the environment. Traditionally, research has focused on identifying single objects and their properties. The ReGround project hypothesizes that the grounding process must consider the full context of the environment, including multiple objects, their properties, and relationships among these objects. ReGround targets the development of a novel framework for “affordance grounding”, by which an agent placed in a new environment can adapt to its new setting and interpret possibly multi-modal input in order to correctly carry out the requested tasks.

[1]  Jos Elfring,et al.  Semantic world modeling using probabilistic multiple hypothesis anchoring , 2013, Robotics Auton. Syst..

[2]  Alessandro Saffiotti,et al.  Maintaining Coherent Perceptual Information Using Anchoring , 2005, IJCAI.

[3]  Luc De Raedt,et al.  Inducing Probabilistic Relational Rules from Probabilistic Examples , 2015, IJCAI.

[4]  J. R. Quinlan.  Learning Logical Definitions from Relations , 1990 .

[5]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Dan Klein,et al.  Learning to Compose Neural Networks for Question Answering , 2016, NAACL.

[7]  Tetsunari Inamura,et al.  Bayesian learning of tool affordances based on generalization of functional feature to estimate effects of unseen tools , 2013, Artificial Life and Robotics.

[8]  Luc De Raedt,et al.  Learning the Structure of Dynamic Hybrid Relational Models , 2016, ECAI.

[9]  Mark Steedman,et al.  Plans, Affordances, And Combinatory Grammar , 2002 .

[10]  Lucas Paletta,et al.  Learning Predictive Features in Affordance based Robotic Perception Systems , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Luc De Raedt,et al.  ProbLog: A Probabilistic Prolog and its Application in Link Discovery , 2007, IJCAI.

[12]  Patrick Doherty,et al.  Towards Affordance-based Robot Control Dagstuhl Seminar 06231 June 5 – 9 , 2006 , 2006 .

[13]  Deb Roy,et al.  Situated Language Understanding as Filtering Perceived Affordances , 2007, Cogn. Sci..

[14]  Henrik I. Christensen,et al.  Efficient Organized Point Cloud Segmentation with Connected Components , 2013 .

[15]  Alessandro Saffiotti,et al.  An introduction to the anchoring problem , 2003, Robotics Auton. Syst..

[16]  Joachim Hertzberg,et al.  Towards Affordance-Based Robot Control - International Seminar, Dagstuhl Castle, Germany, June 5-9, 2006. Revised Papers , 2008, Towards Affordance-Based Robot Control.

[17]  Amy Loutfi,et al.  Learning Actions to Improve the Perceptual Anchoring of Objects , 2017, Front. Robot. AI.

[18]  Alexandre Bernardino,et al.  Affordance based word-to-meaning association , 2009, 2009 IEEE International Conference on Robotics and Automation.