Persönlicher Status und Werkzeuge

Home Research Naive Physics reasoning by simulation

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
research:naive-physics [2011/07/29 16:43]
tenorth
research:naive-physics [2011/08/01 15:39] (current)
tenorth
Line 1: Line 1:
-====== Naive Physics ​Simulation ​======+====== Naive Physics ​reasoning by simulation ​====== 
 +{{ :​research:​naive-physics:​physics-overview.png?​nolink&​|}} 
 +In this project, we investigate a simulation-based approach to naive physics prediction 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 naive physics reasoning should not be performed based on abstractions but rather based on detailed physical simulations. This idea is realized as a naive physics reasoning 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.  
 + 
 +=== Project details ===  
 + 
 +Physical aspects about Eggs are modelled in an ontology: 
 +{{ :​research:​naive-physics:​physics-ontology.png?​nolink&​ |}} 
 + 
 +Within our reasoning system we describe an egg and its content within description logic and store this information in a knowledge base (KB). 
 +An egg-shaped model is generated based on the information stored in the KB, i.e. mass, size etc. 
 +{{ :​research:​naive-physics:​egg-properties.png?​nolink&​ |}} 
 + 
 + 
 +=== Simulation of a falling egg === 
 +The simulation is automatically configured by a scenario describtion stored in the KB (here: an egg that is placed at some height over the ground). We run the simulation and log the data structures of the simulator. We then translate these logged data into timelines of first-order representations in order to infer the consequences of specific events. For example, for asking what happens if the egg is no longer supported:​ 
 + 
 +  ?- holds-tt(F1,​I1),​ fluentT(F1,​supports),​ 
 +     ​objOf(F1,​egg1),​ after(I2,​I1),​ 
 +     ​holds-tt(F2,​I2),​ objOf(F2,​egg1). 
 + 
 +where F2 is bound to broken(egg1). 
 + 
 +{{:​research:​naive-physics:​egg1.png?​nolink&​125|}} 
 +{{:​research:​naive-physics:​egg2.png?​nolink&​125|}} 
 +{{:​research:​naive-physics:​egg3.png?​nolink&​125|}} 
 +{{:​research:​naive-physics:​egg4.png?​nolink&​125|}}
  
 === Grasping an egg === === Grasping an egg ===
Last edited 01.08.2011 15:39 by tenorth