Search

As artificial intelligence (AI) is having an increasingly disruptive impact across industries, companies continue to report having difficulty when recruiting for AI roles, while new graduates find it difficult to find employment, indicating a skills gap or skills misalignment. International approaches to AI skills programmes can offer a guide to future policy development of a skilled workforce, best placed to harness the economic opportunities that AI may support. The authors performed a systematic literature review on AI skills in government policies and documents from seven countries: Australia, Canada, China, Singapore, Sweden, the United Kingom and the United States. We found a divide between countries which emphasised a broader, nationwide approach to upskill and educate all citizens at different levels, namely the United States and Singapore and those countries which emphasised a narrower focus on educating a smaller group of experts with advanced AI knowledge and skills, namely China, Sweden and Canada. We found that the former, broader approaches tended to correlate with higher AI readiness and index scores than the narrower, expert‐driven approach. Our findings indicate that, to match world‐leading AI readiness, future AI skills policy should follow these broad, nationwide approaches to upskill and educate all citizens at different levels of AI expertise. [ABSTRACT FROM AUTHOR]

Human Factors play a significant role in the development and integration of avionic systems to ensure that they are trusted and can be used effectively. As Unoccupied Aerial Vehicle (UAV) technology becomes increasingly important to the aviation domain this holds true. This study aims to gain an understanding of UAV operators' trust requirements when piloting UAVs by utilising a popular aviation interview methodology (Schema World Action Research Method), in combination with key questions on trust identified from the literature. Interviews were conducted with six UAV operators, with a range of experience. This identified the importance of past experience to trust and the expectations that operators hold. Recommendations are made that target training to inform experience, in addition to the equipment, procedures and organisational standards that can aid in developing trustworthy systems. The methodology that was developed shows promise for capturing trust within human-automation interactions. [ABSTRACT FROM AUTHOR]

The Agents, Interaction and Complexity research group at the University of Southampton has a long track record of research in multiagent systems (MAS). We have made substantial scientific contributions across learning in MAS, game-theoretic techniques for coordinating agent systems, and formal methods for representation and reasoning. We highlight key results achieved by the group and elaborate on recent work and open research challenges in developing trustworthy autonomous systems and deploying human-centred AI systems that aim to support societal good. [ABSTRACT FROM AUTHOR]

Summary: In this paper, we present the study of interactional arrangements that support the collaboration of headquarters (HQ), field responders, and a computational planning agent in a time‐critical task setting created by a mixed‐reality game. Interactional arrangements define the extent to which control is distributed between the collaborative parties. We provide 2 field trials, one to study an "on‐the‐loop" arrangement in which HQ monitors and intervenes in agent instructions to field players on demand and the other, to study a version that places HQ more tightly "in‐the‐loop." The studies provide an understanding of the sociotechnical collaboration between players and the agent in these interactional arrangements by conducting interaction analysis of video recordings and game log data. The first field trial focuses on the collaboration of field responders with the planning agent. Findings highlight how players negotiate the agent guidance within the social interaction of the collocated teams. The second field trial focuses on the collaboration between the automated planning agent and the HQ. We find that the human coordinator and the agent can successfully work together in most cases, with human coordinators inspecting and "correcting" the agent‐proposed plans. Through this field trial‐driven development process, we generalise interaction design implications of automated planning agents around the themes of supporting common ground and mixed‐initiative planning. [ABSTRACT FROM AUTHOR]

In this article, we report on one lab study and seven follow-up studies on a crowdsourcing platform designed to investigate the potential of animation cues to influence users' perception of two smart systems: a handwriting recognition and a part-of-speech tagging system. Results from the first three studies indicate that animation cues can influence a participant's perception of both systems' performance. The subsequent three studies, designed to try and identify an explanation for this effect, suggest that this effect is related to the participants' mental model of the smart system. The last two studies were designed to characterize the effect more in detail, and they revealed that different amounts of animation do not seem to create substantial differences and that the effect persists even when the system's performance decreases, but only when the difference in performance level between the systems being compared is small. [ABSTRACT FROM AUTHOR]

In this paper, we critically evaluate the performance of nine machine learning classification techniques when applied to the match outcome prediction problem presented by American Football. Specifically, we implement and test nine techniques using real-world datasets of 1280 games over 5 seasons from the National Football League (NFL). We test the nine different classifier techniques using a total of 42 features for each team and we find that the best performing algorithms are able to improve one previous published works. The algoriothms achieve an accuracy of between 44.64% for a Guassian Process classifier to 67.53% with a Naïve Bayes classifer. We also test each classifier on a year by year basis and compare our results to those of the bookmakers and other leading academic papers. [ABSTRACT FROM AUTHOR]

This paper outlines a novel approach to optimising teams for Daily Fantasy Sports (DFS) contests. To this end, we propose a number of new models and algorithms to solve the team formation problems posed by DFS. Specifically, we focus on the National Football League (NFL) and predict the performance of real-world players to form the optimal fantasy team using mixed-integer programming. We test our solutions using real-world data-sets from across four seasons (2014-2017). We highlight the advantage that can be gained from using our machine-based methods and show that our solutions outperform existing benchmarks, turning a profit in up to 81.3% of DFS game-weeks over a season. [ABSTRACT FROM AUTHOR]

We propose offline and online scheduling algorithms for the charging of electric vehicles (EVs) in a single charging station (CS). The station has available cheaper, but limited, energy from renewable energy sources (RES). The EVs are capable of and willing to participate in vehicle-to-vehicle (V2V) energy transfers that are used to reduce the charging cost and increase the RES utilization. The algorithms are centralized and aim to minimize the total charging cost for the EVs. We formulate the problem as a mixed integer programming (MIP) one and we solve it optimally assuming full knowledge of the EV demand and energy generation. Later, we propose an online algorithm that iteratively calls the offline one and copes with unknown future interruptions by arriving the EVs and with the inability to predict accurately RES production. In addition, a novel technique called virtual demand is developed that increases the demand of already existing EVs, in order to store renewable energy and later transfer it via V2V to EVs that will arrive at the CS in the future. This technique is used for mitigating the inefficiency due to the uncertainty about future actions that real-time scheduling entails. In a setting with up to 150 EVs and using real data regarding the RES production, our algorithms are shown to have low execution times, while the use of virtual demand increases RES utilization by 12% and reduces cost by 3.3%. [ABSTRACT FROM AUTHOR]

Featured Application: Patrol, Search, and Rescue Aerial Robots. This paper investigated the effects of varying noise levels and varying lighting levels on speech and gesture control command interfaces for aerobots. The aim was to determine the practical suitability of the multimodal combination of speech and visual gesture in human aerobotic interaction, by investigating the limits and feasibility of use of the individual components. In order to determine this, a custom multimodal speech and visual gesture interface was developed using CMU (Carnegie Mellon University) sphinx and OpenCV (Open source Computer Vision) libraries, respectively. An experiment study was designed to measure the individual effects of each of the two main components of speech and gesture, and 37 participants were recruited to participate in the experiment. The ambient noise level was varied from 55 dB to 85 dB. The ambient lighting level was varied from 10 Lux to 1400 Lux, under different lighting colour temperature mixtures of yellow (3500 K) and white (5500 K), and different background for capturing the finger gestures. The results of the experiment, which consisted of around 3108 speech utterance and 999 gesture quality observations, were presented and discussed. It was observed that speech recognition accuracy/success rate falls as noise levels rise, with 75 dB noise level being the aerobot's practical application limit, as the speech control interaction becomes very unreliable due to poor recognition beyond this. It was concluded that multi-word speech commands were considered more reliable and effective than single-word speech commands. In addition, some speech command words (e.g., land) were more noise resistant than others (e.g., hover) at higher noise levels, due to their articulation. From the results of the gesture-lighting experiment, the effects of both lighting conditions and the environment background on the quality of gesture recognition, was almost insignificant, less than 0.5%. The implication of this is that other factors such as the gesture capture system design and technology (camera and computer hardware), type of gesture being captured (upper body, whole body, hand, fingers, or facial gestures), and the image processing technique (gesture classification algorithms), are more important in developing a successful gesture recognition system. Some further works were suggested based on the conclusions drawn from this findings which included using alternative ASR (Automatic Speech Recognition) speech models and developing more robust gesture recognition algorithm. [ABSTRACT FROM AUTHOR]

This paper develops a new approach to speed up Generalized Distributive Law (GDL) based message passing algorithms that are used to solve large-scale Distributed Constraint Optimization Problems (DCOPs) in multi-agent systems. In particular, we significantly reduce computation and communication costs in terms of convergence time for algorithms such as Max-Sum, Bounded Max-Sum, Fast Max-Sum, Bounded Fast Max-Sum, BnB Max-Sum, BnB Fast Max-Sum and Generalized Fast Belief Propagation. This is important since it is often observed that the outcome obtained from such algorithms becomes outdated or unusable if the optimization process takes too much time. Specifically, the issue of taking too long to complete the internal operation of a DCOP algorithm is even more severe and commonplace in a system where the algorithm has to deal with a large number of agents, tasks and resources. This, in turn, limits the practical scalability of such algorithms. In other words, an optimization algorithm can be used in larger systems if the completion time can be reduced. However, it is challenging to maintain the solution quality while minimizing the completion time. Considering this trade-off, we propose a generic message passing protocol for GDL-based algorithms that combines clustering with domain pruning, as well as the use of a regression method to determine the appropriate number of clusters for a given scenario. We empirically evaluate the performance of our method in a number of settings and find that it brings down the completion time by around 37–85% (1.6–6.5 times faster) for 100–900 nodes, and by around 47–91% (1.9–11 times faster) for 3000–10 000 nodes compared to the current state-of-the-art. [ABSTRACT FROM AUTHOR]

The coalition structure generation problem is well known in the area of multi-agent systems. Its goal is to establish coalitions between agents while maximizing the global welfare. Among the existing different algorithms designed to solve the coalition structure generation problem, DP and IDP are the ones with smaller temporal complexity. After analyzing the operation of the dynamic programming and improved dynamic programming algorithms, we have identified which are the most frequent operations and propose an optimized method. In addition, we study and implement a method for dividing the work into different threads. To describe incremental improvements of the algorithm design, we first compare performance of an improved single central processing unit core version where we obtain speedups ranging from 7 × to 11 × . Then, we describe the best resource use in a multi-thread optimized version where we obtain an additional 7.5 × speedup running in a 12-core machine. [ABSTRACT FROM AUTHOR]

Coalition formation typically involves the coming together of multiple, heterogeneous, agents to achieve both their individual and collective goals. In this article, we focus on a special case of coalition formation known as Graph-Constrained Coalition Formation (GCCF) whereby a network connecting the agents constrains the formation of coalitions. We focus on this type of problem given that in many real-world applications, agents may be connected by a communication network or only trust certain peers in their social network. We propose a novel representation of this problem based on the concept of edge contraction, which allows us to model the search space induced by the GCCF problem as a rooted tree. Then, we propose an anytime solution algorithm (Coalition Formation for Sparse Synergies (CFSS)), which is particularly efficient when applied to a general class of characteristic functions called m + a functions. Moreover, we show how CFSS can be efficiently parallelised to solve GCCF using a nonredundant partition of the search space. We benchmark CFSS on both synthetic and realistic scenarios, using a real-world dataset consisting of the energy consumption of a large number of households in the UK. Our results show that, in the best case, the serial version of CFSS is four orders of magnitude faster than the state of the art, while the parallel version is 9.44 times faster than the serial version on a 12-core machine. Moreover, CFSS is the first approach to provide anytime approximate solutions with quality guarantees for very large systems of agents (i.e., with more than 2,700 agents). [ABSTRACT FROM AUTHOR]

We investigate a decentralized patrolling problem for dynamic environments where information is distributed alongside threats. In this problem, agents obtain information at a location, but may suffer attacks from the threat at that location. In a decentralized fashion, each agent patrols in a designated area of the environment and interacts with a limited number of agents. Therefore, the goal of these agents is to coordinate to gather as much information as possible while limiting the damage incurred. Hence, we model this class of problem as a transition-decoupled partially observable Markov decision process with health constraints. Furthermore, we propose scalable decentralized online algorithms based on Monte Carlo tree search and a factored belief vector. We empirically evaluate our algorithms on decentralized patrolling problems and benchmark them against the state-of-the-art online planning solver. The results show that our approach outperforms the state-of-the-art by more than 56% for six agents patrolling problems and can scale up to 24 agents in reasonable time. [ABSTRACT FROM PUBLISHER]

Smart systems are becoming increasingly ubiquitous and consequently transforming our lives. The level of system autonomy plays a vital role in the development of smart systems as it profoundly affects how people and these systems interact with each other. However, to date, there are very few studies on human interaction with such systems. This paper presents findings from two field studies where two different prototypes for automating energy tariff-switching were developed and evaluated in the wild. Both prototypes offer flexible autonomy by which users can shift the system's level of autonomy among three options: suggestion-only, semi-autonomy, and full autonomy, whenever they like. Our findings based on thematic analysis show that flexible autonomy is a promising way to sustain users' engagement with smart systems, despite their occasional mistakes. The findings also suggest that users take responsibility for the undesired outcomes of automated actions when delegation of autonomy can be adjusted flexibly. [ABSTRACT FROM AUTHOR]

Along with the development of smart grids, the wide adoption of electric vehicles (EVs) is seen as a catalyst to the reduction of \CO2 emissions and more intelligent transportation systems. In particular, EVs augment the grid with the ability to store energy at some points in the network and give it back at others and, therefore, help optimize the use of energy from intermittent renewable energy sources and let users refill their cars in a variety of locations. However, a number of challenges need to be addressed if such benefits are to be achieved. On the one hand, given their limited range and costs involved in charging EV batteries, it is important to design algorithms that will minimize costs and, at the same time, avoid users being stranded. On the other hand, collectives of EVs need to be organized in such a way as to avoid peaks on the grid that may result in high electricity prices and overload local distribution grids. In order to meet such challenges, a number of technological solutions have been proposed. In this paper, we focus on those that utilize artificial intelligence techniques to render EVs and the systems that manage collectives of EVs smarter. In particular, we provide a survey of the literature and identify the commonalities and key differences in the approaches. This allows us to develop a classification of key techniques and benchmarks that can be used to advance the state of the art in this space. [ABSTRACT FROM PUBLISHER]

The Orchid Project, in partnership with Rescue Global, is a collaborative project that drives the science of human-agent collectives to real-world applications in disaster response.During the 2014 Angel Thunder exercise in the USA, researchers from the Orchid Project embedded with Rescue Global to complete an ethnographic study (Fischer et al., 2015). The study analysed Rescue Global's decision-making process and how the team managed situational uncertainty through their manual tabletop planning work.As a result, the Orchid Project has formed a number of principles, which are now leading the development of a system, the ‘Augmented Bird Table’, which aims to facilitate greatly improved situational awareness by producing a “common operation picture” which informs command-and-control functions. This form of human-agent collective is based upon real needs established by the collaboration between academics and practitioners, and can therefore deliver real benefits in order to save lives in complex environments. [ABSTRACT FROM AUTHOR]

We investigate a multi-agent patrolling problem where information is distributed alongside threats in environments with uncertainties. Specifically, the information and threat at each location are independently modelled as multi-state Markov chains, whose states are not observed until the location is visited by an agent. While agents will obtain information at a location, they may also suffer damage from the threat at that location. Therefore, the goal of the agents is to gather as much information as possible while mitigating the damage incurred. To address this challenge, we formulate the single-agent patrolling problem as a Partially Observable Markov Decision Process (POMDP) and propose a computationally efficient algorithm to solve this model. Building upon this, to compute patrols for multiple agents, the single-agent algorithm is extended for each agent with the aim of maximising its marginal contribution to the team. We empirically evaluate our algorithm on problems of multi-agent patrolling and show that it outperforms a baseline algorithm up to 44% for 10 agents and by 21% for 15 agents in large domains. [ABSTRACT FROM AUTHOR]

Research on optimization in multi-agent systems (MASs) has contributed with a wealth of techniques to solve many of the challenges arising in a wide range of multi-agent application domains. Multi-agent optimization focuses on casting MAS problems into optimization problems. The solving of those problems could possibly involve the active participation of the agents in a MAS. Research on multi-agent optimization has rapidly become a very technical, specialized field. Moreover, the contributions to the field in the literature are largely scattered. These two factors dramatically hinder access to a basic, general view of the foundations of the field. This tutorial is intended to ease such access by providing a gentle introduction to fundamental concepts and techniques on multi-agent optimization. [ABSTRACT FROM AUTHOR]

This paper tackles the problem of parallelizing heterogeneous computational tasks across a number of computational nodes (aka agents) where each agent may not be able to perform all the tasks and may have different computational speeds. An equivalent problem can be found in operations research, and it is known as scheduling tasks on unrelated parallel machines (also known as R∥Cmax). Given this equivalence observation, we present the spanning tree decentralized task distribution algorithm (ST-DTDA), the first decentralized solution to R∥Cmax. ST-DTDA achieves decomposition by means of the min–max algorithm, a member of the generalized distributive law family, that performs inference by message-passing along the edges of a graphical model (known as a junction tree). Specifically, ST-DTDA uses min–max to optimally solve an approximation of the original R∥Cmax problem that results from eliminating possible agent-task allocations until it is mapped into an acyclic structure. To eliminate those allocations that are least likely to have an impact on the solution quality, ST-DTDA uses a heuristic approach. Moreover, ST-DTDA provides a per-instance approximation ratio that guarantees that the makespan of its solution (optimal in the approximated R∥Cmax problem) is not more than a factor ρ times the makespan of the optimal of the original problem. In our empirical evaluation of ST-DTDA, we show that ST-DTDA, with a min-regret heuristic, converges to solutions that are between 78 and 95% optimal whilst providing approximation ratios lower than 3. [ABSTRACT FROM AUTHOR]

The industry related to electric vehicles (EVs) has seen a substantial increase in recent years, as such vehicles have the ability to significantly reduce total CO 2 emissions and the related global warming effect. In this paper, we focus on the problem of allocating EVs to charging stations, scheduling and pricing their charging. Specifically, we developed a Mixed Integer Program (MIP) which executes offline and optimally allocates EVs to charging stations. On top, we propose two alternative mechanisms to price the electricity the EVs charge. The first mechanism is a typical fixed-price one, while the second is a variation of the Vickrey–Clark–Groves (VCG) mechanism. We also developed online solutions that incrementally call the MIP-based algorithm and solve it for branches of EVs. In all cases, the EVs' aim is to minimize the price to pay and the impact on their driving schedule, acting as self-interested agents. We conducted a thorough empirical evaluation of our mechanisms and we observed that they had satisfactory scalability. Additionally, the VCG mechanism achieved an up to 2.2 % improvement in terms of the number of vehicles that were charged compared to the fixed-price one and, in cases where the stations were congested, it calculated higher prices for the EVs and provided a higher profit for the stations, but lower utility to the EVs. However, in a theoretical evaluation, we proved that the variant of the VCG mechanism being proposed in this paper still guaranteed truthful reporting of the EVs' preferences. In contrast, the fixed-price one was found to be vulnerable to agents' strategic behavior as non-truthful EVs can charge instead of truthful ones. Finally, we observed the online algorithms to be, on average, at 95.6 % of the offline ones in terms of the average number of serviced EVs. [ABSTRACT FROM AUTHOR]

In this paper, we present a novel decentralised management technique that allows electricity micro-storage devices, deployed within individual homes as part of a smart electricity grid, to converge to profitable and efficient behaviours. Specifically, we propose the use of software agents, residing on the users' smart meters, to automate and optimise the charging cycle of micro-storage devices in the home to minimise its costs, and we present a study of both the theoretical underpinnings and the implications of a practical solution, of using software agents for such micro-storage management. First, by formalising the strategic choice each agent makes in deciding when to charge its battery, we develop a game-theoretic framework within which we can analyse the competitive equilibria of an electricity grid populated by such agents and hence predict the best consumption profile for that population given their battery properties and individual load profiles. Our framework also allows us to compute theoretical bounds on the amount of storage that will be adopted by the population. Second, to analyse the practical implications of micro-storage deployments in the grid, we present a novel algorithm that each agent can use to optimise its battery storage profile in order to minimise its owner's costs. This algorithm uses a learning strategy that allows it to adapt as the price of electricity changes in real-time, and we show that the adoption of these strategies results in the system converging to the theoretical equilibria. Finally, we empirically evaluate the adoption of our micro-storage management technique within a complex setting, based on the UK electricity market, where agents may have widely varying load profiles, battery types, and learning rates. In this case, our approach yields savings of up to 14% in energy cost for an average consumer using a storage device with a capacity of less than 4.5 kWh and up to a 7% reduction in carbon emissions resulting from electricity generation (with only domestic consumers adopting micro-storage and, commercial and industrial consumers not changing their demand). Moreover, corroborating our theoretical bound, an equilibrium is shown to exist where no more than 48% of households would wish to own storage devices and where social welfare would also be improved (yielding overall annual savings of nearly £1.5B). [ABSTRACT FROM AUTHOR]

Emergency responders are faced with a number of significant challenges when managing major disasters. First, the number of rescue tasks posed is usually larger than the number of responders (or agents) and the resources available to them. Second, each task is likely to require a different level of effort in order to be completed by its deadline. Third, new tasks may continually appear or disappear from the environment, thus requiring the responders to quickly recompute their allocation of resources. Fourth, forming teams or coalitions of multiple agents from different agencies is vital since no single agency will have all the resources needed to save victims, unblock roads and extinguish the fires which might erupt in the disaster space. Given this, coalitions have to be efficiently selected and scheduled to work across the disaster space so as to maximize the number of lives and the portion of the infrastructure saved. In particular, it is important that the selection of such coalitions should be performed in a decentralized fashion in order to avoid a single point of failure in the system. Moreover, it is critical that responders communicate only locally given they are likely to have limited battery power or minimal access to long-range communication devices. Against this background, we provide a novel decentralized solution to the coalition formation process that pervades disaster management. More specifically, we model the emergency management scenario defined in the RoboCup Rescue disaster simulation platform as a coalition formation with spatial and temporal constraints (CFST) problem where agents form coalitions to complete tasks, each with different demands. To design a decentralized algorithm for CFST, we formulate it as a distributed constraint optimization problem and show how to solve it using the state-of-the-art Max-Sum algorithm that provides a completely decentralized message-passing solution. We then provide a novel algorithm (F-Max-Sum) that avoids sending redundant messages and efficiently adapts to changes in the environment. In empirical evaluations, our algorithm is shown to generate better solutions than other decentralized algorithms used for this problem. [ABSTRACT FROM PUBLISHER]

Vickrey-Clarke-Groves (VCG) mechanisms are often used to allocate tasks to selfish and rational agents. VCG mechanisms are incentive compatible, direct mechanisms that are efficient (i.e., maximise social utility) and individually rational (i.e., agents prefer to join rather than opt out). However, an important assumption of these mechanisms is that the agents will always successfully complete their allocated tasks. Clearly, this assumption is unrealistic in many real-world applications, where agents can, and often do, fail in their endeavours. Moreover, whether an agent is deemed to have failed may be perceived differently by different agents. Such subjective perceptions about an agent's probability of succeeding at a given task are often captured and reasoned about using the notion of trust. Given this background, in this paper we investigate the design of novel mechanisms that take into account the trust between agents when allocating tasks. Specifically, we develop a new class of mechanisms, called trust-based mechanisms, that can take into account multiple subjective measures of the probability of an agent succeeding at a given task and produce allocations that maximise social utility, whilst ensuring that no agent obtains a negative utility. We then show that such mechanisms pose a challenging new combinatorial optimisation problem (that is NP-complete), devise a novel representation for solving the problem, and develop an effective integer programming solution (that can solve instances with about 2 x 105 possible allocations in 40 seconds). [ABSTRACT FROM AUTHOR]

Coalition formation is a fundamental type of interaction that involves the creation of coherent groupings of distinct, autonomous, agents in order to efficiently achieve their individual or collective goals. Forming effective coalitions is a major research challenge in the field of multi-agent systems. Central to this endeavour is the problem of determining which of the many possible coalitions to form in order to achieve some goal. This usually requires calculating a value for every possible coalition, known as the coalition value, which indicates how beneficial that coalition would be if it was formed. Once these values are calculated, the agents usually need to find a combination of coalitions, in which every agent belongs to exactly one coalition, and by which the overall outcome of the system is maximized. However, this coalition structure generation problem is extremely challenging due to the number of possible solutions that need to be examined, which grows exponentially with the number of agents involved. To date, therefore, many algorithms have been proposed to solve this problem using different techniques--ranging from dynamic programming, to integer programming, to stochastic search -- all of which suffer from major limitations relating to execution time, solution quality, and memory requirements. [ABSTRACT FROM AUTHOR]

Coalition formation is a fundamental approach to multi-agent coordination, and a key challenge in this context is the coalition structure generation problem, where a set of agents must be partitioned into the best set of coalitions. This problem is NP-hard and typical optimal algorithms do not scale to more than 50 agents: efficient approximate solutions are therefore needed for hundreds or thousands of agents. In this paper we propose a novel heuristic, based on ideas and tools used in the data clustering domain. In particular, we present a coalition formation algorithm inspired by the well known class of hierarchical agglomerative clustering techniques (Linkage algorithms). We present different variants of the algorithm, which we call Coalition Linkage (C-Link) and demonstrate how such algorithm can be adapted to graph restricted coalition formation problems (where an interaction graph defined among the agents restricts the set of feasible coalitions). Moreover, we discuss how we can provide an upper bound on the value of the optimal coalition structure, and we show that for specific characteristic functions we can provide such bounds while maintaining polynomial computational costs and memory requirements. We empirically evaluate the different variants of the C-Link algorithm on two synthetic benchmark data-sets, as well as in two real world scenarios, involving a collective energy purchasing and a ride-sharing application. In these settings C-Link achieves promising results providing high quality solutions and solving problem involving thousands of agents in few minutes. [ABSTRACT FROM AUTHOR]

This paper conducts a comparison of the performance and cognitive workload between three UAV control interfaces on an nCA (navigation control autonomy) Tier 1-III flight navigation task. The first interface is the standard RC Joystick (RCJ) controller, the second interface is the multimodal speech and visual gesture (mSVG) interface, and the third interface is the modified version of the RCJ interface with altitude, attitude, and position (AAP) assist. The modified RCJ interface was achieved with the aid of the Keyboard (KBD). A model of the mSVG interface previously designed and tested was used in this comparison. An experiment study was designed to measure the completion time and navigation accuracy of participants using each of the three interfaces, on a developed path_v02 test flight path. Thirty-seven (37) participants volunteered. The NASA task load index (TLX) survey questionnaire was administered at the end of each interface experiment to access the participants experience and to estimate the interface cognitive workload. A commercial software, the RealFlight Drone Simulator (RFDS) was used to estimate the RCJ skill level of the participants. From the results of the experiment, it was shown that the flying hours, the number of months flying, and the RFDS Level 4 challenge performance was a good estimator for participants RCJ flying skill level. A two-way result was obtained in the comparison of the RCJ and mSVG interfaces. It was concluded that, although the mSVG was better than the standard RCJ interface, the AAP-assisted RCJ was found to be as effective as (in some cases better than) the mSVG interface. It was also shown, from the speech gesture ratio result, that the participants had a preference for gesture over speech when using the mSVG interface. Some further works such as an outdoor field test and a performance comparison at higher nCA levels were suggested. [ABSTRACT FROM AUTHOR]