Integrating spatial concepts into a probabilistic concept web

Çelikkanat, Hande; Şahi̇n, Erol; Kalkan, Sinan

doi:10.1109/icar.2015.7251465

Cited by 3 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These approaches defined relations using rules based on 2D/3D distances between objects, e.g., [17]. With advances in probabilistic graphical modeling, many approaches used models such as Markov Random Fields [4], [18], Conditional Random Fields [6], Implicit Shape Models [19], latent generative models [10]. Many studies also proposed formulating relation detection as a classification problem, e.g., using logistic regression [20], and deep learning [21].…”

Section: A Related Workmentioning

confidence: 99%

What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling

Bozcan

Oymak

Alemdar

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

Scene models allow robots to reason about what is in the scene, what else should be in it, and what should not be in it. In this paper, we propose a hybrid Boltzmann Machine (BM) for scene modeling where relations between objects are integrated. To be able to do that, we extend BM to include tri-way edges between visible (object) nodes and make the network to share the relations across different objects. We evaluate our method against several baseline models (Deep Boltzmann Machines, and Restricted Boltzmann Machines) on a scene classification dataset, and show that it performs better in several scene reasoning tasks.

show abstract

Section: A Related Workmentioning

confidence: 99%

What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling

Bozcan

Oymak

Alemdar

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the second category of methods, which use probabilistic graphical models such as Markov Random Fields [6,10], Conditional Random Fields [16], Implicit Shape Models [25], and latent generative models [5], a probability distribution is modeled for relations between objects or entities. In these studies, Anand et al.…”

Section: Relation Estimation and Reasoningmentioning

confidence: 99%

“…In the second category of methods, which use probabilistic graphical models such as Markov Random Fields [6,10], Conditional Random Fields [16], Implicit…”

Section: Relation Estimation and Reasoningmentioning

confidence: 99%

COSMO: Contextualized scene modeling with Boltzmann Machines

Bozcan

Kalkan

2019

Robotics and Autonomous Systems

Self Cite

View full text Add to dashboard Cite

Scene modeling is very crucial for robots that need to perceive, reason about and manipulate the objects in their environments. In this paper, we adapt and extend Boltzmann Machines (BMs) for contextualized scene modeling. Although there are many models on the subject, ours is the first to bring together objects, relations, and affordances in a highly-capable generative model. For this end, we introduce a hybrid version of BMs where relations and affordances are incorporated with shared, tri-way connections into the model. Moreover, we introduce a dataset for relation estimation and modeling studies. We evaluate our method in comparison with several baselines on object estimation, out-ofcontext object detection, relation estimation, and affordance estimation tasks.Moreover, to illustrate the generative capability of the model, we show several example scenes that the model is able to generate, and demonstrate the benefits of the model on a humanoid robot. The code and the dataset are publicly made available at: https://github.com/bozcani/COSMO

show abstract

“…Hydraulic manifolds, which house tortuous circuit layouts and are usually adopted in mobile machinery like mobile robots and civil machinery [1][2][3][4], can introduce high pressure loss. This is because the priority of minimizing mass and size outweighs the importance of reducing pressure loss.…”

Section: Introductionmentioning

confidence: 99%

3D Printing for Energy-Saving: Evidence from Hydraulic Manifolds Design

et al. 2019

View full text Add to dashboard Cite

With the compact circuit layout and small size, hydraulic manifolds sometimes cause high pressure loss. The purpose of this paper is to investigate the pressure loss under different circumstances with various geometry features and present solutions to reduce pressure loss. The pressure loss performance is evaluated by both experimental and numerical methods. Verified by the experiments, the numerical simulations are qualified to depict the correct trend of the pressure drop. After the basic analysis of traditional passages, three novel forms are proposed, which are very hard to be manufactured by a common method. Furthermore, the geometrical features are selected optimally by means of full factorial experiments to balance the pressure loss and space requirement. Moreover, taking advantage of 3D printing, it is possible to build the passages in novel forms which are beyond the capacity of conventional manufacturing. Results show that the pressure loss can be reduced considerably by adopting a smooth transition, where the reduction can reach up to 50%.

show abstract

Integrating spatial concepts into a probabilistic concept web

Cited by 3 publications

References 22 publications

What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling

What is (Missing or Wrong) in the Scene? A Hybrid Deep Boltzmann Machine for Contextualized Scene Modeling

COSMO: Contextualized scene modeling with Boltzmann Machines

3D Printing for Energy-Saving: Evidence from Hydraulic Manifolds Design

Contact Info

Product

Resources

About