Semantic Segmentation for Object Detection and Grasping with Humanoid Robots

Aslan, Simge Nur; Uçar, Ayşegül; Güzeliş, Cüneyt

doi:10.1109/asyu50717.2020.9259887

Cited by 3 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another method for detecting objects was introduced in [7], [8]; Maiettini et al [7] used a convolutional neural network (CNN) to train a network in an end-to-end manner on larger datasets with 2D bounding objects, while in [8], a CNN was used to predict the class of an object from the proposed region. Aslan et al [9] introduced semantic segmentation algorithms to a simulation and compared the accuracy, segmentation performance, and number of parameters. A year later, they combined a semantic algorithm with deep reinforcement learning (DRL) to recognize an object moving toward the robot [10].…”

Section: Introductionmentioning

confidence: 99%

Tiny-YOLO distance measurement and object detection coordination system for the BarelangFC robot

Susanto,

Ricardo Silitonga,

Analia

et al. 2023

IJECE

View full text Add to dashboard Cite

<span lang="EN-US">A humanoid robot called BarelangFC was designed to take part in the Kontes Robot Indonesia (KRI) competition, in the robot coordination division. In this division, each robot is expected to recognize its opponents and to pass the ball towards a team member to establish coordination between the robots. In order to achieve this team coordination, a fast and accurate system is needed to detect and estimate the other robot’s position in real time. Moreover, each robot has to estimate its team members’ locations based on its camera reading, so that the ball can be passed without error. This research proposes a Tiny-YOLO deep learning method to detect the location of a team member robot and presents a real-time coordination system using a ZED camera. To establish the coordinate system, the distance between the robots was estimated using a trigonometric equation to ensure that the robot was able to pass the ball towards another robot. To verify our method, real-time experiments was carried out using an NVDIA Jetson NX Xavier, and the results showed that the robot could estimate the distance correctly before passing the ball toward another robot.</span>

show abstract

Section: Introductionmentioning

confidence: 99%

Tiny-YOLO distance measurement and object detection coordination system for the BarelangFC robot

Susanto,

Ricardo Silitonga,

Analia

et al. 2023

IJECE

View full text Add to dashboard Cite

show abstract

“…Some of these methods use visual features in 2D images to localize graspable regions, [2,3] while others use range or depth data for this purpose [4,5,6,7,8], the latter becoming more popular owing to the availability of low-cost RGBD sensors. Recently, the deep learning-based methods are becoming increasingly popular for detecting graspable regions [9,10,11,12,13]. Most of the existing methods for vision-based grasping can be broadly classified into two categories: one that relies on the availability of accurate geometric information about the object (or a CAD model) [14,15,16] making them impractical in several real-world use cases, and the other that computes grasping affordances directly from a RGBD point cloud by harnessing local geometric features without knowing the object identity or its accurate 3D geometry [6,17,18,19].…”

Section: Introductionmentioning

confidence: 99%

“…There are several advantages of this approach. For instance, it does not require any computationally intensive training phase to compute GPD unlike other deep learning methods that attempt to process RGB or RGBD images directly [11,12,13,28,29] and in some cases, make use of simulators like Graspit! [14] to produce examples required for training.…”

Section: Introductionmentioning

confidence: 99%

A novel method for finding grasping handles in a clutter using RGBD Gaussian mixture models

2021

View full text Add to dashboard Cite

The paper proposes a novel method to detect graspable handles for picking objects from a confined and cluttered space, such as the bins of a rack in a retail warehouse. The proposed method combines color and depth curvature information to create a Gaussian mixture model that can segment the target object from its background and imposes the geometrical constraints of a two-finger gripper to localize the graspable regions. This helps in overcoming the limitations of a poorly trained deep network object detector and provides a simple and efficient method for grasp pose detection that does not require a priori knowledge about object geometry and can be implemented online with near real-time performance. The efficacy of the proposed approach is demonstrated through simulation as well as real-world experiment.

show abstract

Artificial Intelligence of Things; Remote Robot System Interacts with Humans and Vice Versa During Pandemic

Metallidou

Psannis

Sarigiannidis

et al. 2022

2022 5th World Symposium on Communication Engineering (WSCE)

View full text Add to dashboard Cite

Semantic Segmentation for Object Detection and Grasping with Humanoid Robots

Cited by 3 publications

References 16 publications

Tiny-YOLO distance measurement and object detection coordination system for the BarelangFC robot

Tiny-YOLO distance measurement and object detection coordination system for the BarelangFC robot

A novel method for finding grasping handles in a clutter using RGBD Gaussian mixture models

Artificial Intelligence of Things; Remote Robot System Interacts with Humans and Vice Versa During Pandemic

Contact Info

Product

Resources

About