Simulation-based temporal projection of everyday robot object manipulation

Performing everyday manipulation tasks successfully depends on the ability of autonomous robots to appropriately account for the physical behavior of task-related objects. Meaning that robots have to predict and consider the physical effects of their possible actions to take. In this work we investigate a simulation-based approach to naive physics temporal projection in the context of autonomous robot everyday manipulation. We identify the abstractions underlying typical first-order axiomatizations as the key obstacles for making valid naive physics predictions. We propose that temporal projection for naive physics problems should not be performed based on abstractions but rather based on detailed physical simulations. This idea is realized as a temporal projection system for autonomous manipulation robots that translates naive physics problems into parametrized physical simulation tasks, that logs the data structures and states traversed in simulation, and translates the logged data back into symbolic time-interval-based first-order representations. Within this paper, we describe the concept and implementation of the temporal projection system and present the example of an egg-cracking robot for demonstrating its feasibility.

[1]  Wolfram Burgard,et al.  Real-world robot navigation amongst deformable obstacles , 2009, 2009 IEEE International Conference on Robotics and Automation.

[2]  James F. Allen.  Maintaining knowledge about temporal intervals , 1983, CACM.

[3]  Mary-Anne Williams,et al.  Comirit: Commonsense Reasoning by Integrating Simulation and Logic , 2008, AGI.

[4]  Jeffrey Mark Siskind,et al.  Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic , 1999, J. Artif. Intell. Res..

[5]  I. Duncan,et al.  Cracking the Egg , 2013 .

[6]  Marek J. Sergot,et al.  A logic-based calculus of events , 1989, New Generation Computing.

[7]  Benjamin Kuipers,et al.  Qualitative-numeric simulation with Q3 , 1993 .

[8]  Kenneth D. Forbus.  Qualitative Process Theory , 1984, Artificial Intelligence.

[9]  V. Lifschitz.  Cracking an Egg: An Exercise in Commonsense Reasoning , 1998 .

[10]  Marc Cavazza,et al.  Making sense of virtual environments: action representation, grounding and common sense , 2007, IUI '07.

[11]  Leora Morgenstern,et al.  Mid-Sized Axiomatizations of Commonsense Problems: A Case Study in Egg Cracking , 2001, Stud Logica.

[12]  Malik Ghallab,et al.  On Chronicles: Representation, On-line Recognition and Learning , 1996, KR.

[13]  Michael Beetz,et al.  Using Physics- and Sensor-based Simulation for High-Fidelity Temporal Projection of Realistic Robot Behavior , 2009, ICAPS.

[14]  Patrick J. Hayes,et al.  The second naive physics manifesto , 1995 .

[15]  Manuela M. Veloso,et al.  Efficient physics-based planning: sampling search via non-deterministic tactics and skills , 2009, AAMAS.

[16]  L.F. Marin-Urias,et al.  Geometric Tools for Perspective Taking for Human–Robot Interaction , 2008, 2008 Seventh Mexican International Conference on Artificial Intelligence.

[17]  Brian Falkenhainer,et al.  Self-Explanatory Simulations: An Integration of Qualitative and Quantitative Knowledge , 1990, AAAI.

[18]  Johan de Kleer,et al.  Readings in qualitative reasoning about physical systems , 1990 .