Adoption of Collaborative Robotics in Fruit Harvesting

The paper proposes a new approach as an alternative to full automation of processes that meets current economic trends — collaborative multi-agent systems. In this concept, people and robots are considered as agents in a single sensory-information field, who perform tasks to achieve the goals of the collaborative multi-agent system. The urgency of collaborative multi-agent systems results from the fact that the industrial use of fully automated multi-component systems is limited by the financial and infrastructural unavailability of various industries to switch to completely unmanned technologies. The proposed approach combines the latest, but remaining quite recouped, technological advances along with highly skilled human labor. The use of collaborative multi-agent systems will be economically justified in the manufacture of products in small batches, in the conditions of rapid change of product lines, as well as the presence of staff shortages. The article shows that such an approach can significantly reduce automation costs, while ensuring that the specified production indicators are met. This approach allows taking a fresh look at a human, considering him and a robot as equal partners within a collaborative system. The basic concepts and distinctive characteristics of collaborative multi-agent systems are formulated and presented in the work, justifications for their use are given. Creating a new class of collaborative multi-agent systems requires solving a number of problems associated with the interaction of man and robot. The article considers issues related to the work of a person within a collaborative system, with a rational separation of human functions and an automated production system, in accordance with the necessary level of collaboration. The inclusion of a person with his psychoemotional and physical characteristics as an equivalent agent of a multi-agent system causes difficulties in formalizing collaborative multi-agent systems associated with the need to take these features into account and create a sensory-information system. The inclusion of a person with his psychoemotional and physical characteristics as an equivalent agent of a multi-agent system causes difficulties in formalizing collaborative multi-agent systems associated with the need to take these features into account and create a sensory-information system. The paper discusses ways to formalize a collaborative multi-agent system and management approaches.

Multicriterial analyses of Pareto-efficiency for collaborative multi-agent systems using genetic algorithm with variations

On the perception and handling of deformable objects – A robotic cell for white goods industry

We outline a new model of multi-agent coalition formation which focuses on how collaborative agents can improve their coalition formation skills over time, learning from their prior interactions. The proposed research direction builds on our prior work on distributed coalition formation in collaborative multi-agent systems (MAS), centered at partitioning the underlying network of agents into non-overlapping cliques. At the core of that prior research is the MCDCF algorithm which provides a semantically simple, fully decentralized, local and (for sufficiently sparse networks) scalable mechanism for multi-agent coalition formation [1, 2, 3]. Our goal is to extend the MCDCF-based coalition formation along several new dimensions. First, we want to consider candidate coalitions that (i) no longer have to be cliques but can be more general types of (connected) subgraphs, and (ii) that also satisfy additional, more complex “compatibility” properties stemming from individual agents’ capabilities and preferences. Second, we begin exploration of semantically more rich and versatile ways of capturing this inter-agent compatibility than what’s found in the existing literature. In particular, we propose applying graph pattern techniques to capture a variety of qualitative “compatibility relationships” among agents. Next, we revisit approaches to and benefits of reinforcement learning (RL) in the context of autonomous agents repeatedly engaging in coalition formation. Last but not least, we discuss benefits of each agent maintaining other agents’ reputations that quantify those agents’ coalition formation effectiveness in the past. With these extensions, we argue that the resulting modeling framework adequately captures core aspects of a much richer class of multi-agent coalition formation scenarios, as well as, more broadly, of a variety of distributed consensus reaching problems in collaborative MAS.

A unified framework for reinforcement learning, co-learning and meta-learning how to coordinate in collaborative multi-agent systems

In the medical field - especially in nursing - collaborative robotic systems are rarely used as they are not yet a real facilitator in practical application. However, the increased use of such systems would be particularly valuable due to the shortage of skilled workers in this field. The systems must become easier to use and more flexible in application for the mostly non-technical users. A simple and safe interaction with the robotic end effectors is especially important, because in collaborative systems the caregiver or patient are in direct contact with them.To advance collaborative robotics for nursing, an instrument holder was developed as end effector, under consultation of the target group. It was indicated by them that less complex systems are preferred. In addition, solutions that give the user direct visual and haptic feedback and promise simple correction options for the alignment of the instrument were selected. The outcome is based on a passive (no actuators) bistable clamping principle. It is activated by pressing the instrument onto two flexible belts through which they wrap around the handle. The design process was automated essentially by setting the handle geometry in relation to a cubic Bezier curve.In a first application "hair blow-drying with severely limited shoulder mobility" it was shown, that this passive bistable instrument holder can be a facilitator for nontechnical users. The instrument is pressed into the holder and then held in the desired position. Together with a robot, it can additionally be moved. In operation the holder was intuitive to users and saved time and physical effort. It would also be able to assist in similar tasks. For more complicated tasks or people in need of more intensive care, it is worthwhile to further research this collaborative system and expand it with sensors and independent grasping techniques.

An experimental human-robot collaborative disassembly cell

Industry 4.0 places great importance on collaborative robotics in industrial production and, therefore, on the safe interaction between humans and robots. In previous decades, robots that were part of flexible manufacturing systems remained isolated from human operators through physical enclosures, but current human-robot collaboration activities require a simultaneous concurrent workspace for both actors. Collaborative robotics security systems have used (among others) artificial vision systems based on red, green and blue additive color model images, as proven solutions in detecting humans within the work area of robots. In recent work, the combination of red, green, and blue additive color model imaging with depth imaging systems has demonstrated low sensitivity to lighting changes and a high positional match between distance data and color pixels in both types of acquired images. However, a detailed review resulted in the absence of databases of industrial robotic environments in this type of images. In this paper, an extensive database is delivered in the format already explained that contains people in robotic industrial settings. Furthermore, evaluating the database using machine learning techniques enables computer vision researchers to gain a better understanding of human detection using a Kinect sensor and convolutional neural networks.

This paper describes an architecture for modeling cooperating systems of communicating agents. The authors' goal is not that of providing a framework to implement multi-agents systems (there are tools--such as CORBA, Java and DCOM--that do an excellent job on that), but rather to provide an architectural metaphor upon which collaborative multi-agent systems could be modeled. The approach is based on requirements defined with a practical view of the communicational and resource-oriented nature of distributed collaborative multi-agent systems.

Currently, an agricultural method called SynecocultureTM has been receiving attention as a means for multiple crop production and recovering from environmental degradation; it helps in regreening the environment and establishing an augmented ecosystem with high biodiversity. In this method, several types of plants are grown densely, and their management relies mainly on manual labor, since conventional agricultural machines and robots cannot be applied in complex vegetation. To improve work efficiency and boost regreening by scaling-up Synecoculture, we developed a robot that can sow, prune, and harvest in dense and diverse vegetation that grows under solar panels, towards the achievement of compatibility between food and energy production on a large scale. We adopted a four-wheel mechanism with sufficient ability to move on uneven terrain, and a two orthogonal axes mechanism with adjusted tool positioning while performing management tasks. In the field experiment, the robot could move straight on shelving slopes and overcome obstacles, such as small steps and weeds, and succeeded in harvesting and weeding with human operation, using the tool maneuver mechanism based on the recognition of the field situation through camera image.

Maintaining logical consistency in a knowledge base that receives asynchronous events from collaborative agents poses a challenge, due to multiple agent perspectives of the knowledge base. Facades and filters further complicate this problem by distorting the definition of consistent knowledge. Therefore, maintaining logical consistency of the knowledge base requires an infrastructure for handling truth maintenance. This paper presents a generic, object-oriented framework for truth maintenance in collaborative multi-agent systems. The core of the framework is an agent that autonomously reasons on system events, thus guaranteeing the integrity of the knowledge base independent of external agents. Specialization to a particular domain is achieved through the description of tests that verify the consistency of the knowledge base. This paper shows an example of this approach in a real-world, multi-agent system and discusses performance and maintainability in such a system.

In this article we consider the issue of optimal control in collaborative multi-agent systems with stochastic dynamics. The agents have a joint task in which they have to reach a number of target s...

In this article we consider the issue of optimal control in collaborative multi-agent systems with stochastic dynamics. The agents have a joint task in which they have to reach a number of target states. The dynamics of the agents contains additive control and additive noise, and the autonomous part factorizes over the agents. Full observation of the global state is assumed. The goal is to minimize the accumulated joint cost, which consists of integrated instantaneous costs and a joint end cost. The joint end cost expresses the joint task of the agents. The instantaneous costs are quadratic in the control and factorize over the agents. The optimal control is given as a weighted linear combination of single-agent to single-target controls. The single-agent to single-target controls are expressed in terms of diffusion processes. These controls, when not closed form expressions, are formulated in terms of path integrals, which are calculated approximately by Metropolis-Hastings sampling. The weights in the control are interpreted as marginals of a joint distribution over agent to target assignments. The structure of the latter is represented by a graphical model, and the marginals are obtained by graphical model inference. Exact inference of the graphical model will break down in large systems, and so approximate inference methods are needed. We use naive mean field approximation and belief propagation to approximate the optimal control in systems with linear dynamics. We compare the approximate inference methods with the exact solution, and we show that they can accurately compute the optimal control. Finally, we demonstrate the control method in multi-agent systems with nonlinear dynamics consisting of up to 80 agents that have to reach an equal number of target states.

We investigate collaborative multi-agent systems and how they can use simple, scalable negotiation protocols to coordinate in a fully decentralized manner. Specifically, we study multi-agent distributed coalition formation. We summarize our past and ongoing research on collaborative coalition formation and describe our original distributed coalition formation algorithm. The present paper focuses on negotiation-based view of coalition formation in collaborative Multi-Agent Systems (MAS). While negotiation protocols have been extensively studied in the context of competitive, self-interested agents, we argue that negotiation-based approach may be potentially very useful in the context of collaborative agents, as well – as long as those agents, due to limitations of their sensing and communication abilities, have different views of and preferences over the states of the world. In particular, we show that our coalition formation algorithm has several important, highly desirable properties when viewed as a negotiation protocol.Keywordscollaborative multi-agent systemsmulti-agent coordinationnegotiation protocolscoalition formationdistributed consensus

Two enabling technologies for envisioned tactical network systems are mobile ad hoc network (MANET) routing and collaborative multiagent systems (MAS). Despite their respective technical value in enabling more distributed, autonomous networking, open research and engineering questions remain regarding robust interoperation, standardization, and design of these two technologies. Little work has been done to date to examine the interaction and performance of distributed agent designs within MANET environments. This paper examines the interactions and effects of running a team of belief-desire-intention (BDI) agents within a wireless network using emerging MANET protocol frameworks. The focus of the interagent communication model applied in this study is a form of MANET multicast routing and is aimed at improving group-based agent collaboration. The developed simulation testing environment is specified and results from various experiments are discussed. We present recent results examining overall MAS task performance vs. related knowledge loss induced by the underlying MANET network disruptions. We conclude by outlining several open issues and areas of further work.