PR2 looking at things &amp;#x2014; Ensemble learning for unstructured information processing with Markov logic networks

Nyga, Daniel; Balint-Benczedi, Ferenc; Beetz, Michael

doi:10.1109/icra.2014.6907427

Cited by 24 publications

(21 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robotics has achieved significant success in terms of both theory and applications in the past five decades [23]; however, research involving context has focused on the environmental aspect only, e.g., in scene interpretation [10], urban search for rescue tasks [24], home security [25] and elderly people's living environments [26], object recognition in daily activities [27], [28], and trying to fulfill possibly incomplete natural language instructions of humans [29].…”

Section: A Context In Cognitive Science and Roboticsmentioning

confidence: 99%

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Çelikkanat

Orhan

Pugeault

et al. 2016

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Abstract-In this article, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field, inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make it incremental so that (i) it does not re-learn everything from scratch given new interactions (i.e., it is online) and (ii) it can discover and add a new context into its model when necessary. We demonstrate on the iCub platform that, partly owing to modeling context on top of the concept web, our approach is adaptive, online and robust: It is adaptive and online since it can learn and discover a new context from new interactions. It is robust since it is not affected by irrelevant stimuli and it can discover contexts after a few interactions only. Moreover, we show how to use the context learned in such a model for two important tasks: object recognition and planning.

show abstract

Section: A Context In Cognitive Science and Roboticsmentioning

confidence: 99%

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Çelikkanat

Orhan

Pugeault

et al. 2016

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

show abstract

“…RO-BOSHERLOCK has an integrated engine for learning of and reasoning about probabilistic first-order knowledge bases, which we use for consolidation of inconsistent annotations. In [6], we have shown how first-order probabilistic models, such as Markov logic networks (MLNs), can be used to combine the strengths of different perception algorithms and the object recognition performance of perception systems can be significantly boosted.…”

Section: E Probabilistic Knowledge Representation and Reasoningmentioning

confidence: 99%

“…4 were run on the table top scene. We used a Markov logic network to combine annotations while taking into account the co-occurrences of objects in the environment as reported in [6]. The annotations of the single perception algorithms as well as the prediction are presented in Fig.…”

Section: Task 3: Reasoning About Objects and Their Propertiesmentioning

confidence: 99%

RoboSherlock: Unstructured information processing for robot perception

Beetz

Balint-Benczedi

Blodow

et al. 2015

2015 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

We present ROBOSHERLOCK, an open source software framework for implementing perception systems for robots performing human-scale everyday manipulation tasks. In ROBOSHERLOCK, perception and interpretation of realistic scenes is formulated as an unstructured information management (UIM) problem. The application of the UIM principle supports the implementation of perception systems that can answer task-relevant queries about objects in a scene, boost object recognition performance by combining the strengths of multiple perception algorithms, support knowledge-enabled reasoning about objects and enable automatic and knowledgedriven generation of processing pipelines. We demonstrate the potential of the proposed framework by three feasibility studies of systems for real-world scene perception that have been built on top of ROBOSHERLOCK.

show abstract

“…Ensemble learning: Many ensemble learning algorithms have been used in robotics to solve problems such as localization, detection, recognition, decision making [24,25]. Ensemble methods have been shown effective in different learning frameworks to achieve high accuracy of predictions [26][27][28].…”

Section: Introductionmentioning

confidence: 99%

Online Multimodal Ensemble Learning Using Self-Learned Sensorimotor Representations

Zambelli

Demiris

2017

IEEE Trans. Cogn. Dev. Syst.

View full text Add to dashboard Cite

Internal models play a key role in cognitive agents by providing on the one hand predictions of sensory consequences of motor commands (forward models), and on the other hand inverse mappings (inverse models) to realise tasks involving control loops, such as imitation tasks. The ability to predict and generate new actions in continuously evolving environments intrinsically requiring the use of different sensory modalities is particularly relevant for autonomous robots, which must also be able to adapt their models online. We present a learning architecture based on self-learned multimodal sensorimotor representations. To attain accurate forward models, we propose an online heterogeneous ensemble learning method that allows us to improve the prediction accuracy by leveraging differences of multiple diverse predictors. We further propose a method to learn inverse models on-the-fly to equip a robot with multimodal learning skills to perform imitation tasks using multiple sensory modalities. We have evaluated the proposed methods on an iCub humanoid robot. Since no assumptions are made on the robot kinematic/dynamic structure, the method can be applied to different robotic platforms.

show abstract

PR2 looking at things — Ensemble learning for unstructured information processing with Markov logic networks

Cited by 24 publications

References 14 publications

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

RoboSherlock: Unstructured information processing for robot perception

Online Multimodal Ensemble Learning Using Self-Learned Sensorimotor Representations

Contact Info

Product

Resources

About