A new benchmark for pose estimation with ground truth from virtual reality

Schlette, Christian; Buch, Anders Glent; Aksoy, Eren Erdal; Steil, Thomas; Papon, Jérémie; Savarimuthu, Thiusius Rajeeth; Wörgötter, Florentin; Krüger, Norbert; Roßmann, Jürgen

doi:10.1007/s11740-014-0552-0

Cited by 7 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schlette et al [40] synthesized RGB-D images from simulated object manipulation scenarios involving 4 textureless objects from the Cranfield assembly benchmark [10].…”

Section: Rgb-d Datasetsmentioning

confidence: 99%

T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects

Hodaň

Haluza

Obdržálek

et al. 2017

2017 IEEE Winter Conference on Applications of Computer Vision (WACV)

377

329

View full text Add to dashboard Cite

We introduce T-LESS, a new public dataset for estimating the 6D pose, i.e. translation and rotation, of texture-less rigid objects. The dataset features thirty industry-relevant objects with no significant texture and no discriminative color or reflectance properties. The objects exhibit symmetries and mutual similarities in shape and/or size. Compared to other datasets, a unique property is that some of the objects are parts of others. The dataset includes training and test images that were captured with three synchronized sensors, specifically a structured-light and a time-of-flight RGB-D sensor and a high-resolution RGB camera. There are approximately 39K training and 10K test images from each sensor. Additionally, two types of 3D models are provided for each object, i.e. a manually created CAD model and a semi-automatically reconstructed one. Training images depict individual objects against a black background. Test images originate from twenty test scenes having varying complexity, which increases from simple scenes with several isolated objects to very challenging ones with multiple instances of several objects and with a high amount of clutter and occlusion. The images were captured from a systematically sampled view sphere around the object/scene, and are annotated with accurate ground truth 6D poses of all modeled objects. Initial evaluation results indicate that the state of the art in 6D object pose estimation has ample room for improvement, especially in difficult cases with significant occlusion. The T-LESS dataset is available online at cmp.felk.cvut.cz/t-less. The visual appearance of a texture-less object is dominated by its global shape, color, reflectance properties, and the configuration of light sources. The lack of texture implies that the object cannot be reliably recognized with traditional techniques relying on photometric local patch detectors and descriptors [9,31]. Instead, recent approaches that can deal with texture-less objects have focused on local 3D feature description [33,51,19], and semi-global or arXiv:1701.05498v1 [cs.CV]

show abstract

“…Schlette et al [40] synthesized RGB-D images from simulated object manipulation scenarios involving 4 textureless objects from the Cranfield assembly benchmark [10].…”

Section: Rgb-d Datasetsmentioning

confidence: 99%

T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects

Hodaň

Haluza

Obdržálek

et al. 2017

2017 IEEE Winter Conference on Applications of Computer Vision (WACV)

377

329

View full text Add to dashboard Cite

show abstract

“…Exploiting Virtual Reality: Comparisons of real and virtual data have been carried out before within numerous simulation systems such as V-Rep [31], Gazebo [32] or Microsoft Robotics Developer Studio [33]. However, our approach exceeds the standard camera simulation of other simulation software as it allows for simulating various optical and electronic effects in real-time, due to utilization of rasterization techniques that can be implemented in modern shaderdriven GPUs for hardware accelerated real-time rendering [34].…”

Section: Robot-controlmentioning

confidence: 99%

Teaching a Robot the Semantics of Assembly Tasks

Savarimuthu

Buch

Schlette

et al. 2018

IEEE Trans. Syst. Man Cybern, Syst.

Self Cite

View full text Add to dashboard Cite

We present a three-level cognitive system in a Learning by Demonstration (LbD) context. The system allows for learning and transfer on the sensorimotor level as well as the planning level. The fundamentally different data structures associated to these two levels are connected by an efficient mid-level representation based on so called "Semantic Event Chains". We describe details of the representations and quantify the effect of the associated learning procedures for each level under different amounts of noise. Moreover, we demonstrate the performance of the overall system by three demonstrations that have been performed at a project review. The described system has a Technical Readiness Level (TRL) of 4, which in an ongoing follow-up project will be raised to TRL 6.

show abstract

“…Sensor simulation methods are required to capture accurately such vision-based strategies in simulation. Schlette et al (2014) demonstrated how sensor simulation can be applied to analyze and optimize the parameterization and thus the performance of pose estimation methods in robotic assembly.…”

Section: Modelling and Assembly Simulation In Industrial Contextsmentioning

confidence: 99%

Design, simulation and robotic assembly of reversible timber structures

et al. 2021

Self Cite

View full text Add to dashboard Cite

Wood is more and more seen as a sustainable solution to offset carbon emissions from constructions. In response and in parallel to this, the research in robotic timber construction is evolving rapidly, pushed by Industry 4.0 technologies and the integration of digital and physical robotic assets. This paper presents an approach for the design and assembly automation of layered timber structures, with the use of a flexible cell based on collaborative robots. Advanced assembly procedures and digital design of non-standard timber structures are here established and integrated. The automation process is here enhanced by the (1) use of feedback systems based on the location and force signals, (2) the introduction of a flexible robot setup with automatic screwing, and (3) human-collaboration to provide immediate assistance to the robot in the case the signals do not match the defined assembly conditions. The paper discusses the development and use of a Cyber-Physical System to govern the entire construction process, including reflections on the integrated approach to the design, modelling and simulation of the process.

show abstract

A new benchmark for pose estimation with ground truth from virtual reality

Cited by 7 publications

References 38 publications

T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects

T-LESS: An RGB-D Dataset for 6D Pose Estimation of Texture-Less Objects

Teaching a Robot the Semantics of Assembly Tasks

Design, simulation and robotic assembly of reversible timber structures

Contact Info

Product

Resources

About