In this study, inverse kinematics solution based on numerical methods that can be applied universally to various robot systems was introduced. In particular, it was solved by analyzing and solving ...various problems of the existing inverse kinematics method from different perspectives by constructing and solving this problem as a mathematical optimization problem rather than the general numerical inverse kinematics method obtained using Jacobian. In addition, to verify the efficiency and stability of the proposed method, various simulations and tests were performed by applying to bin picking process using the 5-and 6-axis robot. Finally, in case the geometric information of the target object that was obtained based on deep learning was given, the inverse kinematics solutions for the robot led the robot to pick it up and move it to the target point.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Industrial bin picking is a challenging task as lots of highly reflective and textureless objects are stacked. Previous methods generally predict gripper configurations or 6-D object pose by ...expensive industrial 3-D cameras, ignoring the role of consumer-grade red, green, blue, depth (RGB-D) cameras in this task. For highly reflective objects, depth maps of consumer-grade RGB-D cameras are generally of a lower quality with much stronger noise, making it challenging to detect robust grasp poses in stacked industrial scenarios. To address these challenges, we propose a novel grasp detection framework, including a synthetic data generation pipeline, a novel local grasp detection method, and a global search algorithm (GS). Specifically, in the training phase, we utilize the Pybullet and OpenGL to generate synthetic data by approximate 3-D models. We introduce a novel grasp representation and propose MixStyle (MS)-ResUnet to predict and achieve sim2real transfer for this representation. In the testing phase, the object singleness metric (OSM) is proposed for the global search block to evaluate the graspable probability. In addition, the RGB image enhanced by the edge feature is utilized as the input of the network, which can bridge the domain shift. Extensive experiments in real scenes demonstrate that our method can achieve competitive results in grasping disordered metal parts. In over 2400 robotic grasp trials, our method achieves an average success rate of 91.1% in dense stack scenarios. We also confirm that the proposed method can be applied to unseen objects that are not included in the training dataset. Code and videos are available at: https://github.com/sunhan1997/IndusGrasp .
This research article presents an advanced robotic system designed for efficient pick-and-place of deformable poultry pieces from cluttered bins. The system incorporates a novel architecture with ...seamless integration of various modules, enabling the robot to handle deformable poultry with precision. It introduces a comprehensive evaluation approach to assess the system's performance, considering perception, state modeling, planning and control, gripping and manipulation. The experiments were conducted on two different samples of chicken pieces with varying weights and shapes, under complex and simple scenarios. Performance indicators, failure categories, and cycle time were used for evaluation. The evaluation revealed an overall success rate of 49.4% for picking and placing chicken pieces, with failure rates of 21.8% for perception, 30.7% for gripping, and 11% for manipulation modules. These results highlight areas of improvement, particularly in object detection, grasp pose estimation in clutter, and gripper designs for deformable products, to create a robust pick-and-place solution. The proposed robotic system and evaluation method hold immense potential for revolutionizing the meat processing industry and other food processing sectors, making automation more efficient and adaptable to meet the increasing demand in the food industry.
Mixed-model assembly usually involves numerous component variants that require effective materials supply. Here, picking activities are often performed manually, but the prospect of robotics for bin ...picking has potential to improve quality while reducing man-hour consumption. Robots can make use of vision systems to learn how to perform their tasks. This paper aims to understand the differences in two learning approaches, supervised learning, and unsupervised learning. An experiment containing engineering preparation time (EPT) and recognition quality (RQ) is performed. The findings show an improved RQ but longer EPT with a supervised compared to an unsupervised approach.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Entangled workpiece situations often occur in random bin picking of chaotically stored objects and are a common source of problem in the bin picking process. Previous methods for averting this ...problem, such as randomly shaking the gripper over the bin, lead to decreasing production efficiency and an increase in cycle time. A promising new strategy uses supervised learning and deep neural networks to learn the separation. However, this approach requires a large amount of labeled data. To overcome this issue, this paper proposes a deep reinforcement learning approach to separate entangled workpieces and to minimize the setup effort.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Vision-based robotic picking enables automation of commissioning and sortation of disordered parts. To locate parts for grasping, state-of-the-art approaches rely on convolutional neural networks for ...instance segmentation in 2D images. However, this requires sufficiently large training datasets, which are expensive to capture and annotate. Therefore, training with synthetic data is promising as the data can be generated automatically. We present an approach for the cut-paste method to create synthetic images for industrial use cases. With this approach, an end-user first prepares the image generation with just a smartphone and about 20 minutes of manual effort. Then, a versatile dataset with instance segmentation labels is generated automatically. In addition, a procedure for grasp pose computation is applied to enable robotic picking based on instance segmentation. For evaluation, training data is generated for a wide range of rigid parts and deformable linear objects. Testing with real-world data and practical experiments demonstrates the effectiveness of the proposed cut-paste method for industrial applications.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Industrial part supply often uses universal load carriers. Bin picking offers a variant-flexible option for separating the unordered parts in universal load carriers. While numerous approaches exist ...for bin picking of rigid objects, deformable objects pose challenges. This paper presents a concept for localization and grasp planning for bin picking of deformable linear objects (DLOs). First, a method for localization and reconstruction of unordered DLOs is introduced. Then an approach for part selection and uncertainty evaluation is described. The proposed concept promises to identify grasp regions for picking selected DLOs.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
This paper addresses the problem of pose estimation from 2D images for textureless industrial metallic parts for a semistructured bin-picking task. The appearance of metallic reflective parts is ...highly dependent on the camera viewing direction, as well as the distribution of light on the object, making conventional vision-based methods unsuitable for the task. We propose a solution using direct light at a fixed position to the camera, mounted directly on the robot’s gripper, that allows us to take advantage of the reflective properties of the manipulated object. We propose a data-driven approach based on convolutional neural networks (CNN), without the need for a hard-coded geometry of the manipulated object. The solution was modified for an industrial application and extensively tested in a real factory. Our solution uses a cheap 2D camera and allows for a semi-automatic data-gathering process on-site.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Purpose
The purpose of this paper is to provide an insight into the present-day state of bin picking by considering research, technology, products and applications.
Design/methodology/approach
...Following a short introduction, this first provides examples of recent bin picking research. It then discusses a selection of commercial product developments and applications. Finally, brief conclusions are drawn.
Findings
Bin picking has the potential to eliminate repetitive, manual part handling practices in many sectors of the manufacturing and logistics industries. Systems combine robotic gripping and manipulation with machine vision and specialist software and tend to be complex to install and commission. They are produced by robot manufacturers, system integrators, software developers and machine vision specialists and all are constantly developing and improving the technology. These developments are supported by a strong academic research effort, much involving artificial intelligence methods, and while the technology is evolving rapidly, it is yet to reach the point where deployments are routine and widespread.
Originality/value
This provides a timely review of recent bin picking research and commercial developments.
We present an object pose estimation approach exploiting both geometric depth and photometric color information available from an RGB-D sensor. In contrast to various efforts relying on object ...segmentation with a known background structure, our approach does not depend on the segmentation and thus exhibits superior performance in unstructured environments. Inspired by a voting-based approach employing an oriented point pair feature, we present a voting-based approach which further incorporates color information from the RGB-D sensor and which exploits parallel power of the modern parallel computing architecture. The proposed approach is extensively evaluated with three state-of-the-art approaches on both synthetic and real datasets, and our approach outperforms the other approaches in terms of both computation time and accuracy.
•A point pair feature describing both geometric shape and photometric color and its application to a voting-based 6-DOF object pose estimation.•Parallel algorithms significantly accelerating the voting process on modern GPU architectures.•Effective in unstructured scenes in which the prevailing segmentation-based approaches may not be applicable.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP