Jörg P. Müller

Clausthal University of Technology | TUC · Department of Computer Science

Traffic simulation is needed for planning safe routes of self-driving cars and in analyzing traffic situations of a given area. Commonly supervised learning methods of vehicle, bicycle, and pedestrian traffic models have several limitations such as drifting errors and weak generalization to novel scenarios. Reinforcement learning can address these...

Imitation learning aims at teaching agents to perform desired behaviors by observing expert demonstrations. This approach can be generalized to multi-agent environments, where it is possible to achieve a mutually beneficial policies equilibrium through the use of specialized rewards. One such reward structure can be implemented by using centralized...

In the evolving landscape of human-centered AI, fostering a synergistic relationship between humans and AI agents in decision-making processes stands as a paramount challenge. This work considers a problem setup where an intelligent agent comprising a neural network-based prediction component and a deep reinforcement learning component provides adv...

In the evolving landscape of human-centered AI, fostering a synergistic relationship between humans and AI agents in decision-making processes stands as a paramount challenge. This work considers a problem setup where an intelligent agent comprising a neural network-based prediction component and a deep reinforcement learning component provides adv...

Sustainable concepts for on-demand transportation, such as ridesharing or ridehailing, require advanced technologies and novel dynamic planning and prediction methods. In this paper, we consider the prediction of taxi trip durations, focusing on the problem of the estimated time of arrival (ETA). ETA can be used to compute and compare alternative t...

Accurate prediction of short-term taxi demand allows taxi services to strategically position idle vehicles in areas with insufficientsupply, thus reducing idle times for taxis and waiting times for passengers. Towards this end, state-of-the-art a pproaches useMachine Learning (ML) models based on historic demand data, such as Long Short-Term Memory...

The prediction of city-wide taxi demand is used to proactively relocate idle taxis. Often neural network-based models are applied to tackle this problem, which is difficult due to its multivariate input and output space. As these models are composed of multiple layers, their predictions become opaque. This opaqueness makes debugging, optimising, an...

Shared mobility has emerged as a sustainable alternative to both private transportation and traditional public transport, promising to reduce the number of private vehicles on roads while offering users greater flexibility. Today, urban areas are home to a myriad of innovative services, including car-sharing, ride-sharing, and micromobility solutio...

To achieve the goals set by the European Green Deal, the European Commission plans to expand the available cycling infrastructure. As a result, the number of cyclists is expected to rise, raising safety concerns, specifically in shared spaces where multiple road users interact. One major dilemma that urban planners will face is assessing the safety...

Accurate taxi demand prediction has the potential to increase customer satisfaction and hence the usage of ride-sharing by predicting the number of taxis needed at a certain place and time. When reviewing the related work on demand prediction, we observed that in taxi demand prediction different grid topologies – e.g. rectangular subdivisions of an...

Multi-agent mixed traffic modelling and simulation are needed for safety estimation of traffic situations. Many of the most accurate traffic prediction models use deep learning methods that are considered black box models. This means that the output cannot be directly interpreted based on the input. However, such interpretation can be valuable in p...

Individuals are frequently confronted with privacy-related decisions under uncertainty especially in online contexts. The resulting privacy concerns are a decisive factor for individuals to (not) use online services. In order to support individuals to make more informed decisions, we assess the current state of practice of certain online services....

Modeling mixed-traffic motion and interactions is crucial to assess safety, efficiency, and feasibility of future urban areas. The lack of traffic regulations, diverse transport modes, and the dynamic nature of mixed-traffic zones like shared spaces make realistic modeling of such environments challenging. This paper focuses on the generalizability...

Participating in urban traffic is inherently risky for humans. There-fore, in psychology, behavioural studies have been using Virtual Reality (VR) to simulate and experiment with human behaviour. Safety critical interactions (e.g. conflict, collision or near collision) can be captured from the motion trajectories. However, the motion data in virtua...

Nowadays mobile positioning devices, such as global navigation satellite systems (GNSS) but also external sensor technology like cameras allow an efficient online collection of trajectories, which reflect the behavior of moving objects, such as cars. The data can be used for various applications, e.g., traffic planning or updating maps, which need...

To compare alternative taxi schedules and to compute them, as well as to provide insights into an upcoming taxi trip to drivers and passengers, the duration of a trip or its Estimated Time of Arrival (ETA) is predicted. To reach a high prediction precision, machine learning models for ETA are state of the art. One yet unexploited option to further...

Scheduling of taxis can reduce cost and potentially decreases CO2 emissions. However, with a rising number of taxis or travel requests, the time for computing schedules increases. A promising alternative is to estimate trip durations based on historical trip data without calculating routes. Based on an analysis of the state of the art, in this pape...

Autonomous robots and vehicles are expected to become an integral part of our environment soon. Unsatisfactory issues (esp. for path planning) regarding interaction with existing road users, performance in mixed-traffic areas, and lack of interpretable behavior remain key obstacles. To address these, we present a physics-based neural network, based...

Modelling and simulation of mixed-traffic zones is an important tool for transportation planners to assess safety, efficiency, and human-friendliness of future urban areas. This paper addresses problems of calibration and transferability of existing shared space models when applied to scenarios that differ in terms of cultural aspects, traffic cond...

In shared space environments, urban space is shared among different types of road users, who frequently interact with each other to negotiate priority and coordinate their trajectories. Instead of traffic rules, interactions among them are conducted by informal rules like speed limitations and by social protocols e.g., courtesy behavior. Social gro...

Autonomous robots and vehicles are expected to soon become an integral part of our environment. Unsatisfactory issues regarding interaction with existing road users, performance in mixed-traffic areas and lack of interpretable behavior remain key obstacles. To address these, we present a physics-based neural network, based on a hybrid approach comb...

Digital services like ride sharing rely heavily on personal data, e.g. name or age, as individuals have to disclose personal information in order to gain access to the market. This information is exchanged with other participants; yet, the service provider usually gives little to no information regarding the privacy status of the disclosed data. To...

Digital services like ride sharing rely heavily on personal data as individuals have to disclose personal information in order to gain access to the market and exchange their information with other participants; yet, the service provider usually gives little to no information regarding the privacy status of the disclosed information though privacy...

In shared spaces, motorized and non-motorized road users share the same space with equal priority. Their movements are not regulated by traffic rules, hence they interact more frequently to negotiate priority over the shared space. To estimate the safeness and efficiency of shared spaces, reproducing the traffic behavior in such traffic places is i...

Our research is developing flexible strategies for forming and routing future platoons of automated urban logistics vehicles. We propose the notion of compensational platooning using automated negotiation between agents representing vehicles. After the vehicles reach the end of a common route, an agent can propose part of its route along with a mon...

Modelling and simulation of mixed-traffic zones is an essential tool for transportation planners to assess safety, efficiency, and human-friendliness of future urban areas. This paper addresses the calibration and transferability of existing shared space models for pedestrians and cars. Specifically, our first contribution is enhancing the Game-The...

Platoons, vehicles that travel very close together acting as one, promise to improve road usage on freeways and city roads alike. We study platoon formation in the context of same-day delivery in urban environments. Multiple self-interested logistic service providers (LSP) carry out same-day deliveries by deploying autonomous electric vehicles that...

Realistically modelling behaviour and interaction of heterogeneous road users (pedestrians and vehicles) in mixed-traffic zones (a.k.a. shared spaces) is challenging. The dynamic nature of the environment, heterogeneity of transport modes, and the absence of classical traffic rules make realistic microscopic traffic simulation hard problems. Existi...

Modeling mixed-traffic motion and interactions is crucial to assess safety, efficiency, and feasibility of future urban areas. The lack of traffic regulations, diverse transport modes, and the dynamic nature of mixed-traffic zones like shared spaces make realistic modeling of such environments challenging. This paper focuses on the generalizability...

In mixed traffic scenarios, a certain number of pedestrians might coexist in a small area while interacting with vehicles. In this situation, every pedestrian must simultaneously react to the surrounding pedestrians and vehicles. Analytical modeling of such collective pedestrian motion can benefit intelligent transportation practices like shared sp...

Shared space, an emerging alternative to conventional traffic design, encourages and requires social interaction among heterogeneous traffic participants and efficient space usage by doing away with explicit road divisions and rules. However, concerns about its efficiency and safety give rise to a need for realistic simulation models. While there i...

Modelling and simulation of mixed-traffic zones is an essential tool for transportation planners to assess safety, efficiency, and human-friendliness of future urban areas. This paper addresses problems of calibration and transferability of existing shared space models for pedestrians and cars when applied to scenarios that differ in terms of cultu...

The way humans and artificially intelligent machines interact is undergoing a dramatic change. This change becomes particularly apparent in domains where humans and machines collaboratively work on joint tasks or objects in teams, such as in industrial assembly or disassembly processes. While there is intensive research work on human–machine collab...

Realistically modelling behaviour and interaction of mixed road users (pedestrians and vehicles) in shared spaces are challenging due to the heterogeneity of transport modes and the absence of classical traffic rules. Existing models have mostly used the expert-based approach, combining symbolic modelling and reasoning paradigm with the hand-crafte...

Realistically modelling behaviour and interaction of heterogeneous road users (pedestrians and vehicles) in mixed-traffic zones (a.k.a. shared spaces) is challenging. The dynamic nature of the environment, heterogeneity of transport modes, and the absence of classical traffic rules make realistic microscopic traffic simulation hard problems. Exist...

Ridesharing can significantly reduce individual passenger transport and thus greenhouse gas emissions generated by traffic. Although ridesharing offers great potential, it is not yet popular enough to be seen as an important contribution to solving the aforementioned problems. Our hypothesis suggests that we need to make the assignment mechanism of...

Modern machine learning methods have the potential to supply industrial product lifecycle management (PLM) with automated classification of product components. However, there is only little work in the literature on this topic. We propose to apply supervised machine learning on component meta-data. By analysing an industrial case study, we identify...

In shared space environments, urban space is shared among different types of road users, who frequently interact with each other to negotiate priority and coordinate their trajectories. Instead of traffic rules, interactions among them are conducted by informal rules like speed limitations and by social protocols e.g., courtesy behavior. Social gro...

In shared space environments, different types of road users share the urban space and frequently interact with each other, e.g., to negotiate priority. Instead of traffic rules, their interactions are governed by social protocols such as courtesy behavior and by informal rules like the rule of the road. Modeling the movement behavior of road users...

Platoons, vehicles that travel very close together acting as one, promise to improve road usage on freeways and city roads alike. We study platoon formation in the context of same-day delivery in urban environments. Multiple self-interested logistic service providers (LSP) carry out same-day deliveries by deploying autonomous electric vehicles that...

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations sh...

Today, top-down processes, centralized IT infrastructures, and one-vendor strategies prevail in Product Lifecycle Management (PLM) of large multi-brand Original Equipment Manufacturer (OEM) groups. Given the usually decentralized organisation and structures and processes that emerge from cross-brand collaboration, these centralized approaches are c...

In shared spaces, motorized and non-motorized road users share the same space with equal priority. Their movements are not regulated by traffic rules, hence they interact more frequently to negotiate priority over the shared space. To estimate the safeness and efficiency of shared spaces, reproducing the traffic behavior in such traffic places is i...

Current work on delay management in railway networks has – to the best of our knowledge – largely ignored the impact of passengers’ behavior on train delays. This paper describes ongoing work aiming to explore this topic. We propose a hybrid agent-based architecture combining a macroscopic railway network simulation with a microscopic simulation of...

Modeling and simulation of pedestrian behavior is used in applications such as planning large buildings, disaster management, or urban planning. Realistically simulating pedestrian behavior is challenging, due to the complexity of individual behavior as well as the complexity of interactions of pedestrians with each other and with the environment....

Changes on components that are commonly used in different products in multi-brand product development, cause various types of conflicts. This paper considers conflicts of interest among individuals that are caused by differing payoffs each brand would realize if a specific change request were accepted. Following an analysis of requirements on multi...

Current BDI agent frameworks often lack necessary modularity, scalability and are hard to integrate with non-agent applications. This paper reports ongoing research on LightJason, a multi-agent BDI framework based on AgentSpeak(L), fine-tuned to concurrent plan execution in a distributed framework; LightJason aims at efficient and scalable integrat...

In 2013, 2+1 roadways have become mandatory for newly constructed rural roadways in Germany. The steady trend towards autonomous vehicles and vehicle-to-X (V2X) communication will enable new automated traffic coordination mechanisms. In our research, we study how traffic flow on 2+1 roadways can be improved by using such mechanisms for coordinating...

We investigate the use of voting methods for multiagent decision-making in cooperative traffic applications. We consider a ride-sharing problem in which passengers use committee elections to collectively decide on sets of points of interest to visit. In this paper, we introduce novel iterative voting protocols for the Minisum Approval and Minimax A...

One of the most persistent problems that plague modern-day road transport facilities is the quality of service provided. Especially during rush hours, this expensive infrastructure does not operate at capacity nor does it provide the level of service required by its users. Congestion has become a problem with severe economic and environmental reper...

In this chapter, we investigate a multiagent based approach to modeling autonomic features in urban traffic management. We provide a conceptual model of a traffic system comprising traffic participants modeled as locally autonomous agents, which act to optimize their operational and tactical decisions (e.g., route choice), and traffic management ce...

This paper aims at closing the gap between early phases (e.g. design) and later phases (e.g. procurement or production) of the Product Development Process (PDP) by proposing a Virtual Product Model (VPM) as a collection of individual components (VPMCs) without the need for a static structure. Based on an analysis of the requirements on product deve...

Using purely agent-based platforms for any kind of simulation requires to address the following challenges: 1) scalability; 2) efficient memory management; 3) modelling. While dedicated professional simulation tools usually provide rich domain libraries and advanced visualisation techniques, and support the simulation of large scenarios, they do no...

Using purely agent-based platforms for any kind of simulation requires to address the following challenges: 1 scalability; 2 efficient memory management; 3 modelling. While dedicated professional simulation tools usually provide rich domain libraries and advanced visualisation techniques, and support the simulation of large scenarios, they do not a...

This book constitutes revised, selected, and invited papers from the 4th International Workshop on Engineering Multi-Agent Systems, EMAS 2016, held in Singapore, in May 2016, in conjunction with AAMAS. The 10 full papers presented in this volume were carefully reviewed and selected from 14 submissions. The book also contains 2 invited papers; exten...

We study voting rules as a promising option for collective decision making in traffic applications. The aim of our work is to compare the suitability of several voting rules for different traffic applications and to tackle problems which arise when applying voting rules in traffic management. Here, we propose a multi-agent based voting architecture...

Automotive companies tend to apply modular approaches in their product development processes in order to save costs and meet increasingly diversified customer demands. In largely decentralized environments with cross-branded development projects over multiple departments in different sites this modular approach leads to very complex and large data...

Introduction to the special issue on challenges in agent-oriented software engineering - Volume 30 Issue 4 - Danny Weyns, Jörg P. Müller

In this concept paper, we report on ongoing work aimed at a novel approach to developing complex products. Based on an analysis of the requirements of product development in the automotive industry, the main problems we observe are limited transparency, patency, and reuse. These problems are even more pronounced - and more difficult to manage - in...

Autonomous robots can be used to perform reconnaissance missions in disaster scenarios when the safety of humans cannot be guaranteed. We developed an interdisciplinary approach to autonomous team-based exploration in such settings. The introduced system architecture consists of robust communication and reactive task allocation, built upon a resear...

While there is ample evidence that multiagent systems and technologies (MAS&T) are healthy as a research area, it is unclear what practical application im-pact this research area has accomplished to date. In this paper, we describe method and results of a survey aiming at a comprehensive and up-to-date overview of de-ployed examples of MAS&T. We co...

Using purely agent-based platforms for any kind of simulation requires to address the following challenges: (1) scalability (efficient scheduling of agent cycles is difficult), (2) efficient memory management (when and which data should be fetched, cached, or written to/from disk), and (3) modelling (no generally accepted meta-models exist: what ar...

This book constitutes the proceedings of the 12th German Conference on Multiagent System Technologies, MATES 2014, held in Stuttgart, Germany, in September 2014. The 9 full papers and 7 short papers included in this volume were carefully reviewed and selected from 31 submissions. The book also contains 2 invited talks. The papers are organized in t...

This book constitutes the thoroughly refereed and revised selected papers from the 9th International Workshop on Agents and Data Mining Interaction, ADMI 2013, held in Saint Paul, MN, USA in May 2013. The 10 papers presented in this volume were carefully selected for inclusion in the book and are organized in topical sections named agent mining and...

Kurzfassung Die Produktstruktur mit ihrer unternehmens- und lebenszyklusübergreifenden Funktion bildet die gemeinsame verbindliche Datenbasis für alle Prozesse und Prozesspartner. Ein zentraler Punkt für die Umsetzung einer handlungsfähigen Produktstruktur sind daher die Einflussfaktoren. Durch eine Expertenbefragung hinsichtlich relevanter Einflus...

Contemporary traffic management systems will become more intelligent with advent of future Internet technologies. The systems are expected to become more simple, effective and comfortable for users, but this transformation will require the development of both new system architectures as well as enhanced processing and mining algorithms for large vo...

In this paper we address the problem of retrieving similar resources which are distributed over a multi-agent system (MAS). In distributed environments identification of resources is realized by using cryptographic hash functions like SHA-1. The issue with these functions in connection with similarity search is that they distribute their hash value...

The deployment of future Internet and communication technologies (ICT) provide intelligent transportation systems (ITS) with huge volumes of real-time data (Big Data) that need to be managed, communicated, interpreted, aggregated and analysed. These technologies considerably enhance the effectiveness and user friendliness of ITS, providing consider...

In order to enable energy-efficient operation of factory automation systems during non-productive (idling) phases, the energy-optimal sequence of operating modes has to be calculated. Due to modular structures and runtime constraints, the combinatorial optimization problems that have to be solved to calculate energy-minimizing schedules for today’s...

Automatisierungssysteme konnen einen wesentlichen Beitrag zur Energieeffizienz der Produktion liefern. Einsparpotenziale ergeben sich aus Prozessverbesserungen und insbesondere aus der Nutzung des Energieeinsparpotenzials in Produktionspausen. Nicht-Produktivphasen werden bisher industriell nicht berucksichtigt, um Systeme der Fertigung automatisie...

We propose a norm-based agent-oriented model of decision-making of semi-autonomous vehicles in urban traffic scenarios. Computational norms are used to represent the driving rules and conventions that influence the distributed decision-making process of the vehicles. As norms restrict the admissible behaviour of the agents, we propose to represent...