Intent-based Object Grasping by a Robot using Deep Learning

Zunjani, Faheem Hassan; Sen, Souvik; Shekhar, Himanshu; Powale, Aditya; Godnaik, Debadutta; Nandi, Gora Chand

doi:10.1109/iadcc.2018.8692134

Cited by 12 publications

(5 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In certain applications like robotics, it is required to grasp object, and for that purpose an object needs to be identified. To achieve this, in [27], the authors uses detectron R-CNN (Regional Convolutional Neural Network) to make the mask for the object. They used the Cornell Grasping dataset to predict an optimal rectangle for grasping a particular object.…”

Section: B Object Trackingmentioning

confidence: 99%

Automatic Object Tracking and Segmentation Using Unsupervised SiamMask

et al. 2021

View full text Add to dashboard Cite

In this paper we address the basic limitation of Siammask -the state of the art single object tracking and segmentation algorithm. SiamMask requires semi-supervision in that it needs a bounding box to be drawn manually around the object that has to be tracked. This is however not always possible or feasible, and slows down the pipeline even in the best case. We overcome this limitation by using state-of-the-art object detection algorithms: Detectron and YOLO to automatically detect the object and then track using Siammask. We note that YOLO gives better and more meaningful detection of objects in the scene. However, Detectron gives a higher detection speed than YOLO, making the overall detection and tracking process faster.

show abstract

Section: B Object Trackingmentioning

confidence: 99%

Automatic Object Tracking and Segmentation Using Unsupervised SiamMask

et al. 2021

View full text Add to dashboard Cite

show abstract

“…In the past years, the state of the art in grasp planning changed more and more from CAD-based (Miller et al, 2003;Gatrell, 1989) to computer vision (Zhao et al, 2019;Huang et al, 2020) and machine learning (ML) (Zunjani et al, 2018;Depierre et al, 2018) based approaches. One possible reason for this trend is the shifting of robot applications and their use cases in recent years.…”

Section: Related Workmentioning

confidence: 99%

“…There-fore, programming the robot manually for each object (or even type of object) is not feasible. While in recent years numerous approaches using machine learning for grasp planning have been studied (Zelch et al, 2020), they share difficulties of generalizing to previously unknown objects and are typically trained on domain specific datasets as shown by Zunjani et al (2018) and Depierre et al (2018). Since all information is known a priori in our use case, we are able to circumvent these limitations by relying on a completely model-based approach.…”

Section: Introductionmentioning

confidence: 99%

CAD-based Grasp and Motion Planning for Process Automation in Fused Deposition Modelling

Wiedholz

Heider

Nordsieck

et al. 2021

Proceedings of the 18th International Conference on Informatics in Control, Automation and Robotics

View full text Add to dashboard Cite

Planning the right grasp pose and motion into it has been a problem in the robotic community for more than 20 years. This paper presents a model-based approach for a Pick action of a robot that increases the automation of FDM based additive manufacturing by removing a produced object from the build plate. We treat grasp pose planning, motion planning and simulation-based verification as separate components to allow a high exchangeability. When testing a variety of different object geometries, feasible grasps and motions were obtained for all objects. We also found that the computation time is highly dependent on the random seed, leading us to employ a system of budgeted runs for which we report the estimated success probability and expected running time. Within the budget, some objects never found feasible picks. Thus, we rotated these objects by 90 • which lead to a substantial improvement in success probabilities.

show abstract

“…Through these two cascaded training processes and 500 iterations, the network can obtain strong direction prediction ability. Zunjani et al [114] found that robots need to predict the ideal matrix according to the intention of the object to achieve an optimal grabbing strategy. They input the object image and intention type metadata into the full connection layer of the CNN network, which will achieve the ideal rectangular prediction.…”

Section: A Robot Grasp Point and Grasp Strategymentioning

confidence: 99%

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

Bai

Yang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

With the rapid development of machine learning, its powerful function in the machine vision field is increasingly reflected. The combination of machine vision and robotics to achieve the same precise and fast grasping as that of humans requires high-precision target detection and recognition, location and reasonable grasp strategy generation, which is the ultimate goal of global researchers and one of the prerequisites for the large-scale application of robots. Traditional machine learning has a long history and good achievements in the field of image processing and robot control. The CNN (convolutional neural network) algorithm realizes training of large-scale image datasets, solves the disadvantages of traditional machine learning in large datasets, and greatly improves accuracy, thereby positioning CNNs as a global research hotspot. However, the increasing difficulty of labeled data acquisition limits their development. Therefore, unsupervised learning, self-supervised learning and reinforcement learning, which are less dependent on labeled data, have also undergone rapid development and achieved good performance in the fields of image processing and robot capture. According to the inherent defects of vision, this paper summarizes the research achievements of tactile feedback in the fields of target recognition and robot grasping and finds that the combination of vision and tactile feedback can improve the success rate and robustness of robot grasping. This paper provides a systematic summary and analysis of the research status of machine vision and tactile feedback in the field of robot grasping and establishes a reasonable reference for future research.

show abstract

Intent-based Object Grasping by a Robot using Deep Learning

Cited by 12 publications

References 3 publications

Automatic Object Tracking and Segmentation Using Unsupervised SiamMask

Automatic Object Tracking and Segmentation Using Unsupervised SiamMask

CAD-based Grasp and Motion Planning for Process Automation in Fused Deposition Modelling

Object Detection Recognition and Robot Grasping Based on Machine Learning: A Survey

Contact Info

Product

Resources

About