Search results

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.

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.

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.

This provides a timely review of recent bin picking research and commercial developments.

To describe how one innovative company has developed software which teamed with a vision system allows an agile robot to be taught how to pick randomly place parts from a multi‐layered bin.

Software, which runs on an industrial PC‐based computer platform, has unique algorithms, which can identify randomly placed 3D parts in a bin and calculate the path the robot needs to take to pick each part.

The software has been successfully applied to picking many different part configurations, including odd‐shaped brackets, long slender vehicle axles, round brake rotors and cylindrical shaped pistons and other automotive housings.

Vision‐guided robotic picking can now be more efficient and faster than manual part picking in many applications. Users need to rethink part picking.

A long‐sought solution to quickly picking parts from bins is now a reality.

This paper aims to introduce and identify a new 3D handling operation (bin picking) for natural discrete food products using food categorisation.

The research shows a new food categorisation and the relation between food ordering processes and food categories. Bin picking in the food industry needs more flexible vision software compared to the manufacturing industry in order to decrease the degree of disarray of food products and transfer them into structure.

It has been shown that there are still manual operated ordering processes in food industry such as bin picking; it just needs new ideas of image processing algorithms such as active shape models (ASMs) on its development in order to recognise the highly varying shapes of food products.

This research was aimed at locating a new ordering process and proving a new principle, but for practical implementation this bin picking solution needs to be developed and tested further.

Identifying new ordering processes via food categorisation is unique and applying ASMs to bin picking opens a new industrial sector (food industry) for 3D handling.

For robot motion planning there exists a large number of different algorithms, each appropriate for a certain domain, and the right choice of planner depends on the specific use case. The purpose of this paper is to consider the application of bin picking and benchmark a set of motion planning algorithms to identify which are most suited in the given context.

The paper presents a selection of motion planning algorithms and defines benchmarks based on three different bin-picking scenarios. The evaluation is done based on a fixed set of tasks, which are planned and executed on a real and a simulated robot.

The benchmarking shows a clear difference between the planners and generally indicates that algorithms integrating optimization, despite longer planning time, perform better due to a faster execution.

The originality of this work lies in the selected set of planners and the specific choice of application. Most new planners are only compared to existing methods for specific applications chosen to demonstrate the advantages. However, with the specifics of another application, such as bin picking, it is not obvious which planner to choose.

This paper aims to provide details of recent developments in random bin picking (RBP) technologies and products, together with an insight into its commercial status and prospects.

Following an introduction to RBP, this article discusses the technology, benefits and limitations of RBP. It then considers a number of products and applications and concludes with a brief discussion.

This article shows that RBP offers significant economic and operational benefits, but it is a complex technology and applications remain limited. It is underpinned by advanced machine vision and sophisticated image processing algorithms and continues to be the topic of academic research. Many RBP products have been launched in the past but the latest generation of dedicated vision systems, software packages and fully integrated robotic systems suggest that more widespread applications are imminent.

This paper provides a timely introduction to the rapidly developing field of RBP by discussing the technologies and a range of products and applications.

It is now possible to pick randomly placed parts from a bin automatically. SVIA have developed a patented bin‐picking system that is general and easy for the operator to teach. It is possible because of the combination of a high precision optical 3D‐measuring technique, modern image processing and six‐axis robot technology.

The purpose of this paper is twofold, first: to define the profile of adopters of labor-enhancing technologies (e.g. platforms) identifying factors – such as operations size, mix of fruits grown, apple operation location, principal operators socio-demographics – and second: to estimate the efficiency threshold for platform adoption during apple harvesting to be financially feasible considering future increases in farm labor wages.

The authors conducted a mixed-mode survey in January-February 2010. Data were analyzed using a bivariate probit model, considering that the decision to adopt platforms was related with the orchard planting system. The authors conducted simulation scenarios to estimate the efficiencies – harvest – platforms must achieve in order to be economically feasible.

In total, 11 percent of the 316 apple operations covered by the survey used platforms. Orchard operations most likely to invest in planar structures are relatively large, produce high-value varieties, use organic systems, and have relatively young and educated operators. Similarly, operations producing high-value fruit such as “Honeycrisp” and controlled or patented varieties and relatively large operations are more likely to invest in platforms. The results of the comparison of the cost of harvesting apples using platforms vs ladders under several production assumptions indicate that platforms must increase labor productivity by at least 13 percent in order to be adopted by the industry.

This study caveat is the lack of inclusion of production and marketing uncertainties in the estimation of future apple harvest costs. Further research to deeper analyze these issues is needed.

The authors present information on the profile of mechanization adopters, so extension educators and engineers could concentrate efforts on them to increase adoption levels. In addition the authors provide a threshold of efficiencies for harvest platforms associated with cost savings compared to manual harvest.

Enabling the adoption of mechanization technologies by specialty crop industries would decrease the dependence on labor, decreasing labor uncertainties and facilitating the production of high quality produce to satisfy the needs of consumers. Second, it will end an era of importing poverty, given that the specialty crop industry has long benefited from seasonal migrant workers. It will improve rural American communities to shorten pools of farm workers, giving them access to permanent jobs with higher salaries.

The contribution of this study is to improve understanding of the degree of mechanization, financial feasibility of current existing technologies, and barriers to greater mechanization by the Washington apple industry. Given the similar labor challenges faced, in general, by the US specialty crop agriculture, results could be applicable to the entire industry.

The purpose of this paper is to review how far the use of vision has come in providing high‐end integration of robotic handling systems in production lines, and look ahead to a future where robots are equal partners with humans in the production line.

Considers the benefits of 1D, 2D and 3D machine vision.

Finds that the “next generation” of integrating 3D vision with robotics can achieve solutions that have previously eluded technology developers, in particular gripping complex shapes and profiles, picking at variable heights, measuring volume and mass, unpacking products in a random arrangement, e.g. in a bin or pile of parts, or where the products obscure one another.

Shows that calibration of the 3D vision system can be more complex and time consuming. Therefore, as part of the integration process, it is important that a robust calibration capability of the vision system is built‐in, for example using objects of known parameters as standards.

It has always taken vision to invest in robotic automation, now the 3D provides extra perspective on an opportunity to gain competitive advantage and achieve good returns on investment.

The paper aims to discuss the review of the most recent PackExpo show in Chicago with emphasis on the new robot innovations and applications on display.

In-depth interviews with exhibitors of robots, integrators of robots and suppliers of robot accessories at the show.

Robots continue to develop to match an ever-increasing number of packaging tasks.

Customers may be surprised at the robot innovations and new applications to which robots are being applied in the packaging field.

A review of some of the latest robot innovations and applications for packaging that one might have seen if they had been on the exhibition floor at the most recent Chicago PackExpo show.

The purpose of this paper is to review the International Manufacturing Technology Show in Chicago with emphasis on innovative robot applications on display.

In‐depth interviews with exhibitors of robots as well as system integrators who apply robots to specific categories of applications.

Robots are becoming smarter with more integrated capabilities such as vision and autonomous part picking from random bin locations. They are becoming more economical, faster and more application specific. Robot system integrators are creating more efficient solutions for customers to consider.

The paper is of value to users who investigated robot solutions in the past and found they did not meet applications requirements and who may need to revisit robotics. Robot builders and system integrators are providing more suitable solutions that can better address application needs in a more cost‐effective manner than ever before.