Semantic world modeling using probabilistic multiple hypothesis anchoring

Elfring, Jos; Dries, S. van den; Molengraft, René van de; Steinbuch, M Maarten

doi:10.1016/j.robot.2012.11.005

Cited by 48 publications

(57 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An extension to consider large-scale knowledge bases, such as a Cyc knowledge base (Lenat, 1995), together with commonsense reasoning was later presented by Daoutis et al (2012). Another notable work is the introduction of probabilistic multiple hypothesis anchoring by Elfring et al (2013), where multiple hypothesis tracking-based data association is used to maintain changes in anchored objects. As an alternative to traditional anchoring, an earlier work on perception and probabilistic anchoring was presented by Blodow et al (2010).…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Learning Actions to Improve the Perceptual Anchoring of Objects

2017

View full text Add to dashboard Cite

In this paper, we examine how to ground symbols referring to objects in perceptual data from a robot system by examining object entities and their changes over time. In particular, we approach the challenge by (1) tracking and maintaining object entities over time; and (2) utilizing an artificial neural network to learn the coupling between words referring to actions and movement patterns of tracked object entities. For this purpose, we propose a framework that relies on the notations presented in perceptual anchoring. We further present a practical extension of the notation such that our framework can track and maintain the history of detected object entities. Our approach is evaluated using everyday objects typically found in a home environment. Our object classification module has the possibility to detect and classify over several 100 object categories. We demonstrate how the framework creates and maintains, both in space and time, representations of objects such as "spoon" and "coffee mug." These representations are later used for training of different sequential learning algorithms to learn movement actions such as "pour" and "stir." We finally exemplify how learned movements actions, combined with commonsense knowledge, further can be used to improve the anchoring process per se.

show abstract

Section: Related Workmentioning

confidence: 99%

“…Inspired by the work on probabilistic multiple hypothesis anchoring presented by Elfring et al (2013), we further utilize a track functionality that is integrated with the object tracking procedure, described in Section 3.1:…”

Section: Object Anchoringmentioning

confidence: 99%

Learning Actions to Improve the Perceptual Anchoring of Objects

2017

View full text Add to dashboard Cite

show abstract

“…In this work the probabilistic multiple hypothesis anchoring algorithm introduced in Elfring et al (2013a) and implemented by the WIRE 1 stack in ROS is used. Measurements from sensors are associated with objects in the world model using a multiple hypothesis-based data association approach and object instances are linked to grounded symbols using anchoring.…”

Section: World Modeling Algorithmmentioning

confidence: 99%

“…The uncertainty in the world state estimate increases during propagation and decreases after measurement updates. A more detailed explanation can be found in Elfring et al (2013a).…”

Section: World Modeling Algorithmmentioning

confidence: 99%

Semi-task-dependent and uncertainty-driven world model maintenance

2014

View full text Add to dashboard Cite

“…The Knowledge Base is a SWI-PL [22] The World Model [23] contains a sophisticated tracking and data association algorithm that quantifies streams of sequential measurements, called evidence, into unique objects. At its core, the World Model is a multiple-hypotheses filter, able to combine different forms of evidence into a common, dynamically updated world representation.…”

Section: A Reasonermentioning

confidence: 99%

Integrating planning and execution for ROS enabled service robots using hierarchical action representations

Janssen

Meijl

Marco

et al. 2013

2013 16th International Conference on Advanced Robotics (ICAR)

View full text Add to dashboard Cite

Abstract-The aim of the RoboEarth project is to develop a globally accessible database, that enables service robots to share reusable information relevant to the execution of their daily tasks. Examples of this information are the hierarchical task descriptions, or action recipes, that represent typical household tasks as symbolic action sequences. By annotating these static action representations with hierarchical planner predicates, they can be interpreted by the Hierarchical Task Network planner SHOP2 to compose more flexible, optimized robot plans, based on the actual state of the environment and the available capabilities of the robot. To subsequently execute the composed plans in a typical household environment, the CRAM executive toolbox is adopted, allowing a tight integration between plan execution and run-time knowledge inference. This paper presents the integration of these two components into one cohesive planning and execution framework, tailored for the safe execution of abstract tasks in a challenging household environment. The resulting framework is implemented on the AMIGO service robot and a basic experiment is conducted to demonstrate the frameworks integral functionality.

show abstract

Semantic world modeling using probabilistic multiple hypothesis anchoring

Cited by 48 publications

References 25 publications

Learning Actions to Improve the Perceptual Anchoring of Objects

Learning Actions to Improve the Perceptual Anchoring of Objects

Semi-task-dependent and uncertainty-driven world model maintenance

Integrating planning and execution for ROS enabled service robots using hierarchical action representations

Contact Info

Product

Resources

About