Name
Title | ||
|---|---|---|
PR2 looking at things — Ensemble learning for unstructured information processing with Markov logic networks |
Abstract | ||
|---|---|---|
We investigate the perception and reasoning task of answering queries about realistic scenes with objects of daily use perceived by a robot. A key problem implied by the task is the variety of perceivable properties of objects, such as their shape, texture, color, size, text pieces and logos, that go beyond the capabilities of individual state-of-the-art perception methods. A promising alternative is to employ combinations of more specialized perception methods. In this paper we propose a novel combination method, which structures perception in a two-step process, and apply this method in our object perception system. In a first step, specialized methods annotate detected object hypotheses with symbolic information pieces. In the second step, the given query Q is answered by inferring the conditional probability P(Q | E), where E are the symbolic information pieces considered as evidence for the conditional probability. In this setting Q and E are part of a probabilistic model of scenes, objects and their annotations, which the perception method has beforehand learned a joint probability distribution of. Our proposed method has substantial advantages over alternative methods in terms of the generality of queries that can be answered, the generation of information that can actively guide perception, the ease of extension, the possibility of including additional kinds of evidences, and its potential for the realization of self-improving and - specializing perception systems. We show for object categorization, which is a subclass of the probabilistic inferences, that impressive categorization performance can be achieved combining the employed expert perception methods in a synergistic manner. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICRA.2014.6907427 | Robotics and Automation |
Keywords | Field | DocType |
Markov processes,image retrieval,learning (artificial intelligence),object detection,probability,robot vision,statistical distributions,Markov logic networks,PR2 looking at things,conditional probability,ensemble learning,impressive categorization performance,joint probability distribution,object categorization,object hypotheses detection annotation,object perception system,perception task,probabilistic inferences,probabilistic model,query answering,reasoning task,self-improving perception systems,specialized perception methods,symbolic information pieces,two-step process,unstructured information processing | Categorization,Information processing,Joint probability distribution,Conditional probability,Computer science,Statistical model,Artificial intelligence,Probabilistic logic,Perception,Ensemble learning,Machine learning | Conference |
Volume | Issue | ISSN |
2014 | 1 | 1050-4729 |
Citations | PageRank | References |
16 | 0.71 | 14 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Nyga | 1 | 107 | 6.99 |
| Ferenc Balint-Benczedi | 2 | 57 | 6.03 |
| Michael Beetz | 3 | 3784 | 284.03 |