Browsing by Subject "AI"

Now showing 1 - 2 of 2

AI-based planting and monitoring of cabbage with a robotic platform
(2024) Lüling, Nils; Griepentrog, Hans W.
Labour shortages, price pressure and changes in legislation are just a few of the drivers of automation and digitalization in field vegetable cultivation. Due to its high-value crops and its high demands on crop maintenance, field vegetable cultivation is the ideal working area for agricultural robotics. However, the versatile and rapid establishment of agricultural robotics systems has so far failed due to the limited adaptivity to the complex working environment under outdoor conditions, the process chain and the applications that an agricultural robot has to carry out in a field. Only through the developing possibilities of using cameras and artificial intelligence can complex automated applications be implemented. The overall aim of this cumulative dissertation was the development and analysis of systems for AI-based crop establishment and crop maintenance of white cabbage with a robotic platform. Three aspects were analysed: (1) Design, prototyping and evaluation of a planting unit for an autonomous planting process of cabbage with a robotic platform. By using AI-based image classification, a camera at the end of the planting unit was used to evaluate the planting quality and dynamically adjust individual planting parameters. (2) Development of a camera-based vegetation monitoring system for determining the fruit volume and leaf area of white cabbage across several growth stages. (3) Analysis of a method for unsupervised image translation for automated exposure adjustment. By reducing the exposure variation, a lower implementation effort and a higher robustness of the detection and segmentation of white cabbage are aimed for. As part of the autonomous crop establishment, a planting unit was developed and constructed that can carry out an automated crop stand establishment process using a robot platform. The analysis of the quality of the planting process showed a comparable planting performance and planting accuracy to conventional systems of automated field vegetable planting. During the development of the planting unit, the focus was placed on an adaptive design of the unit so that machine parameters can be dynamically adjusted during the planting process. It was possible to reduce the energy requirement of the overall system by dynamically opening and closing the planting furrow during the planting process in order to minimize the draft force. It also creates the basis for an autonomous planting process. Using an attached camera and an AI for image classification, the planting quality can also be recorded and planting parameters such as the planting depth and furrow width can then be adjusted in order to influence the plant placement. At the same time, the AI-based image classification can also be used to control the planting process itself. If the planting tape tears or the separation is blocked, no seedlings are planted. The AI recognizes this and can instruct the robot to suspend the planting process. For automated crop monitoring, the camera, in cooperation with a neural network for instance segmentation, offers the possibility of a contact-free and high-resolution recording of plant parameters. Using instance segmentation of the cabbage head, the cabbage plant and the individual cabbage leaves, as well as a depth image generation using structure-from-motion, it was possible to determine plant parameters such as the absolute leaf area, the number of leaves or the fruit volume of the cabbage head across several growth stages. This offers farmers new opportunities in crop management, which can be tailored even more specifically to individual plants using the information collected. As many possibilities as the use of cameras in combination with neural network-based image analysis offers, there are still some challenges. One of the fundamental challenges lies in the provision and annotation of image data to ensure robust image analysis. The more complex the use case, the more varying images the data set must contain in order to provide the neural network with a basis of information with which it can learn the necessary features. To reduce the complexity of the use case of detecting and segmenting cabbage plants, an AI-based image translation was used to standardize the exposure variations. No annotation is required to train the AI-based image translation, which is trained unsupervised. By standardizing the exposure, the complexity of the images can be reduced, which means that fewer images need to be annotated for a robust use of instance segmentation. This method was also tested for varying growth stages and varieties.
Behind the scenes of emerging technologies – Opportunities, challenges, and solution approaches along a socio-technical continuum
(2021) Bayer, Sarah; Gimpel, Henner
Digitalization is a socio-technical phenomenon that shapes our lives as individuals, economies, and societies. The perceived complexity of technologies continues to increase, and technology convergence makes a clear separation between technologies impossible. A good example of this is the Internet of Things (IoT) with its embedded Artificial Intelligence (AI). Furthermore, a separation of the social and the technical component has become near enough impossible, for which there is increasing awareness in the Information Systems (IS) community. Overall, emerging technologies such as AI or IoT are becoming less understandable and transparent, which is evident for instance when AI is described in terms of a “black box”. This opacity undermines humans’ trust in emerging technologies, which, however, is crucial for both its usage and spread, especially as emerging technologies start to perform tasks that bear high risks for humans, such as autonomous driving. Critical perspectives on emerging technologies are often discussed in terms of ethics, including such aspects as the responsibility for decisions made by algorithms, the limited data privacy, and the moral values that are encoded in technology. In sum, the varied opportunities that come with digitalization are accompanied by significant challenges. Research on the negative ramifications of AI is crucial if we are to foster a human-centered technological development that is not simply driven by opportunities but by utility for humanity. As the IS community is positioned at the intersection of the technological and the social context, it plays a central role in finding answers to the question as to how the advantages outweigh the challenges that come with emerging technologies. Challenges are examined under the label of “dark side of IS”, a research area which receives considerably less attention in existing literature than the positive aspects (Gimpel & Schmied, 2019). With its focus on challenges, this dissertation aims to counterbalance this. Since the remit of IS research is the entire information system, rather than merely the technology, humanistic and instrumental goals ought to be considered in equal measure. This dissertation follows calls for research for a healthy distribution along the so-called socio-technical continuum (Sarker et al., 2019), that broadens its focus to include the social as well as the technical, rather than looking at one or the other. With that in mind, this dissertation aims to advance knowledge on IS with regard to opportunities, and in particular with a focus on challenges of two emerging technologies, IoT and AI, along the socio-technical continuum. This dissertation provides novel insights for individuals to better understand opportunities, but in particular possible negative side effects. It guides organizations on how to address these challenges and suggests not only the necessity of further research along the socio-technical continuum but also several ideas on where to take this future research. Chapter 2 contributes to research on opportunities and challenges of IoT. Section 2.1 identifies and structures opportunities that IoT devices provide for retail commerce customers. By conducting a structured literature review, affordances are identified, and by examining a sample of 337 IoT devices, completeness and parsimony are validated. Section 2.2 takes a close look at the ethical challenges posed by IoT, also known as IoT ethics. Based on a structured literature review, it first identifies and structures IoT ethics, then provides detailed guidance for further research in this important and yet under-appreciated field of study. Together, these two research articles underline that IoT has the potential to radically transform our lives, but they also illustrate the urgent need for further research on possible ethical issues that are associated with IoTs’ specific features. Chapter 3 contributes to research on AI along the socio-technical continuum. Section 3.1 examines algorithms underlying AI. Through a structured literature review and semi-structured interviews analyzed with a qualitative content analysis, this section identifies, structures and communicates concerns about algorithmic decision-making and is supposed to improve offers and services. Section 3.2 takes a deep dive into the concept of moral agency in AI to discuss whether responsibility in human-computer interaction can be grasped better with the concept of “agency”. In section 3.3, data from an online experiment with a self-developed AI system is used to examine the role of a user’s domain-specific expertise in trusting and following suggestions from AI decision support systems. Finally, section 3.4 draws on design science research to present a framework for ethical software development that considers ethical issues from the beginning of the design and development process. By looking at the multiple facets of this topic, these four research articles ought to guide practitioners in deciding which challenges to consider during product development. With a view to subsequent steps, they also offer first ideas on how these challenges could be addressed. Furthermore, the articles offer a basis for further, solution-oriented research on AI’s challenges and encourage users to form their own, informed, opinions.