This paper describes the motivation for the development of the HuroCupcompetition and follows the rule development from its inaugural competition from2002 to 2015. The history of HuroCup is broken down into its growing phase(2002–2006), a time of explosive growth (2007–2011), and currenttimes. This paper describes the main research focus of HuroCup, the multi-eventhumanoid robot competition: (a) active balancing, (b) complex motion planning,and (c) human–robot interaction and shows how the various HuroCup eventsrelate to those research topics. This paper concludes with some medium- andlong-term goals of the rule development for HuroCup.

Usually, humanoid walking gaits are only roughly distinguished between stable andunstable. The evaluation of a stable humanoid walking gait is difficult toquantify in scales. And, it is extremely hard to adjust humanoid robots insuitable a walking gait for different movement objectives such as fast walking,uneven floor walking, and so on. This paper proposes a stability marginconstructed by center of pressure (COP) to evaluate the gait stability ofhumanoid walking. The stability margin is modeled by the COP regions that ahumanoid robot needs for stable standing. We derive the mathematical model forCOP position by dividing the walking gait into single and double support phasesin order to measure the stability of the COP regions. An actual measuring systemfor the stable COP regions is designed and implemented. The measured COPtrajectory of a walking gait is eventually evaluated with respect to the stableCOP regions for the stability margins. The evaluation focuses on weak stabilityareas to be improved for robust walking gaits. To demonstrate the robustness ofthe improved walking gait, we replicate the experiment on three differentterrains. The experiments demonstrate that the walking gaits developed based onstable COP region can be applied for different movement objectives.

This paper presents a parameterized gait generator based on linear invertedpendulum model (LIPM) theory, which allows users to generate a natural gaitpattern with desired step sizes. Five types of zero moment point (ZMP)components are proposed for formulating a natural ZMP reference, where ZMP movescontinuously during single support phases instead of staying at a fixed point inthe sagittal and lateral plane. The corresponding center of mass (CoM)trajectories for these components are derived by LIPM theory. To generate aparameterized gait pattern with user-defined parameters, a gait planningalgorithm is proposed, which determines related coefficients and boundaryconditions of the CoM trajectory for each step. The proposed parameterized gaitgenerator also provides a concept for users to generate gait patterns withself-defined ZMP references by using different components. Finally, thefeasibility of the proposed method is validated by the experimental results witha teen-sized humanoid robot, David, which won first place in the sprint event atthe 20th Federation of International Robot-soccer Association (FIRA) RoboWorldCup.

We survey the use and effect of decomposition-based techniques in qualitativespatial and temporal constraint-based reasoning, and clarify the notions of atree decomposition, a chordal graph, and a partitioning graph, and theirimplication with a particular constraint property that has been extensively usedin the literature, namely, patchwork. As a consequence, we prove that a recentlyproposed decomposition-based approach that was presented in the study byNikolaou and Koubarakis for checking the satisfiability of qualitative spatialconstraint networks lacks soundness. Therefore, the approach becomes quitecontroversial as it does not seem to offer any technical advance at all, whileresults of an experimental evaluation of it in a following work presented in thestudy by Sioutis become questionable. Finally, we present a particular treedecomposition that is based on the biconnected components of the constraintgraph of a given large network, and show that it allows for cost-freeutilization of parallelism for a qualitative constraint language that haspatchwork for satisfiable atomic networks.

Obstacle avoidance is an important issue in robotics. In this paper, the particleswarm optimization (PSO) algorithm, which is inspired by the collectivebehaviors of birds, has been designed for solving the obstacle avoidanceproblem. Some animals that travel to the different places at a specific time ofthe year are called migrants. The migrants also represent the particles of PSOfor defining the walking paths in this work. Migrants consider not only thecollective behaviors, but also geomagnetic fields during their migration innature. Therefore, in order to improve the performance and the convergence speedof the PSO algorithm, concepts from the migrant navigation method have beenadopted for use in the proposed hybrid particle swarm optimization (H-PSO)algorithm. Moreover, the potential field navigation method and the designedfuzzy logic controller have been combined in H-PSO, which provided a goodperformance in the simulation and the experimental results. Finally, theFederation of International Robot-soccer Association (FIRA) HuroCup Obstacle RunEvent has been chosen for validating the feasibility and the practicability ofthe proposed method in real time. The designed adult-sized humanoid robot alsoperformed well in the 2015 FIRA HuroCup Obstacle Run Event through utilizing theproposed H-PSO.

This paper presents our preliminary research into the autonomous control of analpine skiing robot. Based on our previous experience with active balancing ondifficult terrain and developing an ice-skating robot, we have implemented asimple control system that allows the humanoid robot Jennifer to steer around asimple alpine skiing course, brake, and actively control the pitch and roll ofthe skis in order to maintain stability on hills with variable inclination.

The robot steers and brakes by using the edges of the skis to dig into the snow,by inclining both skis to one side the robot can turn in an arc. By rolling theskis outward and pointing the toes together the robot creates a snowplough shapethat rapidly reduces its forward velocity.

To keep the skis in constant contact with the hill we use two independentproportional-integral-derivative (PID) controllers to continually adjust therobot’s inclination in the frontal and sagittal planes.

Our experiments show that these techniques are sufficient to allow a smallhumanoid robot to alpine ski autonomously down hills of different inclinationwith variable snow conditions.

Recent advancements in location-based recommendation system (LBRS) and theavailability of online applications, such as Twitter, Instagram, Foursquare,Path, and Facebook have introduced new research challenges in the area of LBRS.Use of content, such as geo-tagged media, point location-based, andtrajectory-based information help in connecting the gap between the onlinesocial networking services and the physical world. In this article, we present asystematic review of the scientific literature of LBRS and summarize the effortsand contributions proposed in the literature. We have performed a qualitativecomparison of the existing techniques used in the area of LBRS. We present thebasic filtration techniques used in LBRS followed by a discussion on theservices and the location features the LBRS utilizes to perform therecommendations. The classification of criteria for recommendations andevaluation metrics are also presented. We have critically investigated thetechniques proposed in the literature for LBRS and extracted the challenges andpromising research topics for future work.

Robot Interaction has always been a challenge in collaborative robotics. In taskscomprising Inter-Robot Interaction, robot detection is very often needed. Weexplore humanoid robots detection because, humanoid robots can be useful in manyscenarios, and everything from helping elderly people live in their own homes toresponding to disasters. Cameras are chosen because they are reach and cheapsensors, and there are lots of mature two-dimensional (2D) and 3D computervision libraries which facilitate Image analysis. To tackle humanoid robotdetection effectively, we collected a data set of various humanoid robots withdifferent sizes in different environments. Afterward, we tested the well-knowncascade classifier in combination with several image descriptors like Histogramsof Oriented Gradients (HOG), Local Binary Patterns (LBP), etc. on this data set.Among the feature sets, Haar-like has the highest accuracy, LBP the highestrecall, and HOG the highest precision. Considering Inter-Robot Interaction, itis evident that false positives are less troublesome than false negatives, thusLBP is more useful than the others.

This study presents the algorithm for a humanoid robot to accomplish an obstaclerun in the FIRA HuroCup competition. It includes the integration of imageprocessing and robot motion. DARwIn-OP (Dynamic Anthropomorphic Robot withIntelligence–Open Platform) was used as the humanoid robot, and it isequipped with a webcam as a vision system to obtain an image of what is in frontof the robot. Image processing skills such as erosion, dilation, andeight-connected component labeling are applied to reduce image noise. Moreover,we use navigation grids with filters to avoid the obstacles. Fuzzy logic rulesare used to implement the robot’s motion, allowing a humanoid robot toaccess any routes using obstacle avoidance to perform the tasks in theobstacle-run event.

Semantic relatedness (SR) is a form of measurement that quantitatively identifiesthe relationship between two words or concepts based on the similarity orcloseness of their meaning. In the recent years, there have been noteworthyefforts to compute SR between pairs of words or concepts by exploiting variousknowledge resources such as linguistically structured (e.g. WordNet) andcollaboratively developed knowledge bases (e.g. Wikipedia), among others. Theexisting approaches rely on different methods for utilizing these knowledgeresources, for instance, methods that depend on the path between two words, or avector representation of the word descriptions. The purpose of this paper is toreview and present the state of the art in SR research through a hierarchicalframework. The dimensions of the proposed framework cover three main aspects ofSR approaches including the resources they rely on, the computational methodsapplied on the resources for developing a relatedness metric, and the evaluationmodels that are used for measuring their effectiveness. We have selected 14representative SR approaches to be analyzed using our framework. We compare andcritically review each of them through the dimensions of our framework, thus,identifying strengths and weaknesses of each approach. In addition, we provideguidelines for researchers and practitioners on how to select the most relevantSR method for their purpose. Finally, based on the comparative analysis of thereviewed relatedness measures, we identify existing challenges and potentiallyvaluable future research directions in this domain.

Reusing requirements improves product quality and the productivity of thedevelopment process. This paper investigates how the development of newrequirements can be made more productive through reuse of the experience gainedon similar requirements. This can be facilitated using a component-based reuseapproach supported by a framework. Therefore, the central challenge for thisresearch work is double: (1) to define a new concept for the requirementcomponent as the combination of two types of knowledge: reusable knowledge andknowledge of reuse; (2) to define AFR (Analysis For Reuse) that represents thecapitalization process by opposition to Analysis By Reuse that represents theprocess of reuse itself. Finally, we provide a case study related to therequirements of a hotel system to explain how the first process works. Throughthis approach, we use a framework ‘Requirements Repository Framework(R2F)’ in order to capitalize existing requirements within a repositoryfor future reuse. We present the results of an experiment with threesecond-level student sections that used R2F in their IS240 course project; aswell as with four student groups that used R2F in their respective seniorprojects. The objective of this experiment is to measure the usability of theproposed AFR process.

Literature-based discovery systems aim at discovering valuable latent connectionsbetween previously disparate research areas. This is achieved by analyzing thecontents of their respective literatures with the help of various intelligentcomputational techniques. In this paper, we review the progress ofliterature-based discovery research, focusing on understanding their technicalfeatures and evaluating their performance. The present literature-baseddiscovery techniques can be divided into two general approaches: the traditionalapproach and the emerging approach. The traditional approach, which dominate thecurrent research landscape, comprises mainly of techniques that rely onutilizing lexical statistics, knowledge-based and visualization methods in orderto address literature-based discovery problems. On the other hand, we have alsoobserved the births of new trends and unprecedented paradigm shifts among therecently emerging literature-based discovery approach. These trends are likelyto shape the future trajectory of the next generation literature-based discoverysystems.

Multi-agent systems (MASs) are a form of distributed intelligence, where multiple autonomous agents act in a common environment. Numerous complex, real world systems have been successfully optimized using multi-agent reinforcement learning (MARL) in conjunction with the MAS framework. In MARL agents learn by maximizing a scalar reward signal from the environment, and thus the design of the reward function directly affects the policies learned. In this work, we address the issue of appropriate multi-agent credit assignment in stochastic resource management games. We propose two new stochastic games to serve as testbeds for MARL research into resource management problems: the tragic commons domain and the shepherd problem domain. Our empirical work evaluates the performance of two commonly used reward shaping techniques: potential-based reward shaping and difference rewards. Experimental results demonstrate that systems using appropriate reward shaping techniques for multi-agent credit assignment can achieve near-optimal performance in stochastic resource management games, outperforming systems learning using unshaped local or global evaluations. We also present the first empirical investigations into the effect of expressing the same heuristic knowledge in state- or action-based formats, therefore developing insights into the design of multi-agent potential functions that will inform future work.

Complex systems often exhibit emergent behaviour, unexpected macro-level behaviour caused by the interaction of micro-level components. In multiagent systems, these micro-level components may be autonomous agents and the emergent behaviour may be expressed as norms—patterns of behaviour that arise among the agents in response to their environment and each other. These emergent norms may be beneficial (e.g. by encouraging cooperative behaviour), or detrimental, but in either case it is useful to recognize these norms as they emerge and either encourage or discourage their establishment. We term this process engineering the emergence of norms and have identified three steps: the identification of a possible norm, evaluation of its benefit and its encouragement (or discouragement). This paper is an attempt to provide a survey of existing research related to these steps. We also provide an analysis of the approaches based upon their suitability for a variety of normative systems: we examine the requirements for agents to have autonomy over their choice of norms, the degree of observability required in the system, and the norm enforcement methods. The paper concludes with an discussion of open issues.

Psychological models have been used to simulate emotions within agents as part of the decision-making process. The body of this work has focussed on applying the process of decision making using emotions to social dilemmas, notably the Prisoner’s Dilemma. Previous work has focussed on agents which do not move around, with an initial analysis on how mobility and the environment can affect the decisions chosen. Additionally simulated mood has been introduced to the decision-making process. Exploring simulated emotions and mood to inform the decision-making process in multi-agent systems allows us to explore in further detail how outside influences can have an effect on different strategies. We expand and clarify aspects of how agents are affected by environmental differences. We show how emotional characters settle on an outcome without deviation by providing a formal proof. We validate how the addition of mood increases cooperation, while also showing how small groups achieve this quicker than large groups. Once pure defectors are added, to test the resilience of the cooperation achieved, we see that while agents with a low starting mood achieve a payoff closest to the pure defectors, they are reduced in numbers the most by the pure defectors.

With the recent increase in the use of Unmanned Aerial Vehicles (UAVs) comes a surge of inexperienced aviators who may not have the requisite skills to react appropriately if weather conditions quickly change while their aircraft are in flight. This creates a dangerous situation, in which the pilot cannot safely land the vehicle. In this work we examine the use of the MAP-Elites algorithm to search for sets of weights for use in an artificial neural network. This neural network directly controls the thrust and pitching torque of a simulated 3-degree of freedom (2 linear, 1 rotational) fixed-wing UAV, with the goal of obtaining a smooth landing profile. We then examine the use of the same algorithm in high-wind conditions, with gusts up to 30 knots.

Our results show that MAP-Elites is an effective method for searching for control policies, and by evolving two separate controllers and switching which controller is active when the UAV is near-ground level, we can produce a wider variety of phenotypic behaviors. The best controllers achieved landing at a vertical speed of <1 m s−1 and at an angle of approach of <1° degree.