COSMO: Contextualized scene modeling with Boltzmann Machines

Download

index.pdf

Date

2019-03-01

Author

Bozcan, Ilker
Kalkan, Sinan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

209
views

119
downloads

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-of-context 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.

Subject Keywords

Control and Systems Engineering, Software, General Mathematics, Computer Science Applications

URI

https://hdl.handle.net/11511/37283

Journal

ROBOTICS AND AUTONOMOUS SYSTEMS

DOI

https://doi.org/10.1016/j.robot.2018.12.009

Collections

Department of Computer Engineering, Article

Suggestions

OpenMETU
Core

Contextualized scene modeling using boltzmann machines Bozcan, İlker; Kalkan, Sinan; Department of Computer Engineering (2018) Scene modeling is very crucial for robots that need to perceive, reason about and manipulate the objects in their environments. In this thesis, we propose a variant of Boltzmann Machines (BMs) for contextualized scene modeling. Although many computational models have been proposed for the problem, 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 introduced with ...
Free gait generation with reinforcement learning for a six-legged robot Erden, Mustafa Suphi; Leblebicioğlu, Mehmet Kemal (Elsevier BV, 2008-03-31) In this paper the problem of free gait generation and adaptability with reinforcement learning are addressed for a six-legged robot. Using the developed free gait generation algorithm the robot maintains to generate stable gaits according to the commanded velocity. The reinforcement learning scheme incorporated into the free gait generation makes the robot choose more stable states and develop a continuous walking pattern with a larger average stability margin. While walking in normal conditions with no ext...
Dynamic modeling and parameter estimation for traction, rolling, and lateral wheel forces to enhance mobile robot trajectory tracking BAYAR, Gokhan; Koku, Ahmet Buğra; Konukseven, Erhan İlhan (Cambridge University Press (CUP), 2015-12-01) Studying wheel and ground interaction during motion has the potential to increase the performance of localization, navigation, and trajectory tracking control of a mobile robot. In this paper, a differential mobile robot is modeled in a way that (traction, rolling, and lateral) wheel forces are included in the overall system dynamics. Lateral wheel forces are included in the mathematical model together with traction and rolling forces. A least square parameter estimation process is proposed to estimate the ...
Estimation of parameters for dynamic volume spline models Ulusoy, İlkay; WEBER, GERHARD WİEHELM (Informa UK Limited, 2010-01-01) Soft tissue models are of many types, but each type has its own problems in terms of realistic appearance and computational efficiency. In this study, we propose a hybrid model based on dynamic volume splines which combine the advantages of these models. To simulate a realistic appearance, biomechanical properties of the real tissue are obtained by force-displacement experiments and used to tune the parameters of the model. Unlike the usual types described in the literature, a new experiment is proposed whe...
3-D Rigid Body Tracking Using Vision and Depth Sensors Gedik, O. Serdar; Alatan, Abdullah Aydın (Institute of Electrical and Electronics Engineers (IEEE), 2013-10-01) In robotics and augmented reality applications, model-based 3-D tracking of rigid objects is generally required. With the help of accurate pose estimates, it is required to increase reliability and decrease jitter in total. Among many solutions of pose estimation in the literature, pure vision-based 3-D trackers require either manual initializations or offline training stages. On the other hand, trackers relying on pure depth sensors are not suitable for AR applications. An automated 3-D tracking algorithm,...

Citation Formats

I. Bozcan and S. Kalkan, “COSMO: Contextualized scene modeling with Boltzmann Machines,” ROBOTICS AND AUTONOMOUS SYSTEMS, pp. 132–148, 2019, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/37283.