Search

In this work we explore implicit communication between humans and robots—through movement—in multi-party (or multi-user) interactions. In particular, we investigate how a robot can move to better convey its intentions using legible movements in multi-party interactions. Current research on the application of legible movements has focused on single-user interactions, causing a vacuum of knowledge regarding the impact of such movements in multi-party interactions. We propose a novel approach that extends the notion of legible motion to multi-party settings, by considering that legibility depends on all human users involved in the interaction, and should take into consideration how each of them perceives the robot’s movements from their respective points-of-view. We show, through simulation and a user study, that our proposed model of multi-user legibility leads to movements that, on average, optimize the legibility of the motion as perceived by the group of users. Our model creates movements that allow each human to more quickly and confidently understand what are the robot’s intentions, thus creating safer, clearer and more efficient interactions and collaborations.

This paper proposes an end-to-end framework that can learn and decompose complex movements provided by a human demonstrator and generate new complex motions. Our approach analyzes the demonstration by the human expert and uses geometric criteria to decompose the observed movement into segments that are stored as dynamic movement primitives (DMPs) in a library. Then, given a new environment configuration, our system autonomously composes different motion primitives to construct an optimized trajectory that meets the constraints imposed by the new environment. Our system is therefore able to construct new DMPs to execute complex motions in environments that differ from the one where the original motions were taught. Our approach is also compatible with existing run-time obstacle avoidance approaches. We illustrate the application of our approach both in simulation and with a Baxter robot.

This paper explores the role of prosocial behaviour when people team up with robots in a collaborative game that presents a social dilemma similar to a public goods game. An experiment was conducted with the proposed game in which each participant joined a team with a prosocial robot and a selfish robot. During 5 rounds of the game, each player chooses between contributing to the team goal (cooperate) or contributing to his individual goal (defect). The prosociality level of the robots only affects their strategies to play the game, as one always cooperates and the other always defects. We conducted a user study at the office of a large corporation with 70 participants where we manipulated the game result (winning or losing) in a between-subjects design. Results revealed two important considerations: (1) the prosocial robot was rated more positively in terms of its social attributes than the selfish robot, regardless of the game result; (2) the perception of competence, the responsibility attribution (blame/credit), and the preference for a future partner revealed significant differences only in the losing condition. These results yield important concerns for the creation of robotic partners, the understanding of group dynamics and, from a more general perspective, the promotion of a prosocial society.

This PhD project aims at investigating how a social robot can adapt its behaviours to the group members in order to achieve more positive group dynamics, which we identify as group intelligence. This goal is supported by our previous work, which contains relevant data and insightful results to the understanding of group interactions between humans and robots. Finally, we examine and discuss the future work we have planned and what are the contributions to Human-Robot Interaction (HRI) field.

In this paper we develop design guidelines for mental state induction in first-person shooters (FPS). To illustrate our design guidelines, we develop four versions of a first-person shooter video game each inducing a specific mental state on the player following our guidelines. We also conduct an evaluation using the self-perceived mental state of the participants as a metric to compare the mental state induced with each version. Results show that we were able to induce frustration, suggesting that further research is needed to fully understand the relation of gameplay and mental state inducement on FPS games.

This work studies the relevance of flow in gameplay adaptability and how it may offer a better gaming experience, since it provides a better enjoyment of an activity. We developed a first-person shooter video game that adapts its in-game difficulty and environmental settings based on a representation of the mental state of the user to keep a balance between the skills of the player and the challenge of the game. The mental state of the player is measured with their physiological signals, namely the heart rate and the beta band of the brainwaves, and we distinguish the mental state of the player with an accuracy of 87%. We also conducted an evaluation using self-perceived flow and in-game scores as metrics to compare the mental state-based adaptability with a performance-based version. Results show that the latter provided a better gaming experience, suggesting that further research is needed to fully understand the relation of flow and gameplay on FPS games.

This paper addresses the problem of human-robot collaboration in scenarios where a robot assists a human by executing a complex motion involving the manipulation of an object. We focus on tasks in which success in the task depends on reaching a target pose that is controlled by the human. We contribute a reinforcement learning-based approach that allows the robot to reason about its own ability to successfully complete the task given the current target pose and indirectly adjust that pose by prompting the human user. Our approach allows the robot both to trade-off the benefits of adjusting the target position against the cost of bothering the human user while, at the same time, adapting to each user's responses. Our approach was tested in a real-world human-robot collaboration scenario involving the Baxter robot.

Behavioral data on children with Autism Spectrum Disorders (ASD) are available thanks to standardized diagnostic tools, such as the Autism Diagnostic Observation Schedule (ADOS). This data can be of great use to enhance the learning and reasoning of agents interacting with children with ASD. However, the amount of such available data is limited and may not prove useful by itself to inform the algorithms of complex agents. To address this data scarcity problem, we present a method for generating synthetic behavioral data in the form of feature vectors characterizing a wide range of children with ASD. Our method relies on a thorough analysis and partition of the feature space based on a real dataset containing the ADOS scores of 279 children. We first analyze the real dataset using dimensionality reduction techniques, then introduce data-driven descriptors that partition the feature space into regions naturally arising from the data. We end by presenting a descriptor-based sampling method to generate synthetic feature vectors that successfully preserves the correlation structure of the real dataset.

In this paper, we introduce a Monte-Carlo tree search (MCTS) approach for the game "Hearthstone: Heroes of Warcraft". We argue that, in light of the challenges posed by the game (such as uncertainty and hidden information), Monte Carlo tree search offers an appealing alternative to existing AI players. Additionally, by enriching MCTS with a properly constructed heuristic, it is possible to introduce significant gains in performance. We illustrate through extensive empirical validation the superior performance of our approach against vanilla MCTS and the current state-of-the art AI for Hearthstone.

This article proposes an architecture for an intelligent surveillance system, where the aim is to mitigate the burden on humans in conventional surveillance systems by incorporating intelligent interfaces, computer vision, and autonomous mobile robots. Central to the intelligent surveillance system is the application of research into planning and decision making in this novel context. In this article, we describe the robot surveillance decision problem and explain how the integration of components in our system supports fully automated decision making. Several concrete scenarios deployed in real surveillance environments exemplify both the flexibility of our system to experiment with different representations and algorithms and the portability of our system into a variety of problem contexts. Moreover, these scenarios demonstrate how planning enables robots to effectively balance surveillance objectives, autonomously performing the job of human patrols and responders. This work was partially supported by the Portuguese Fundação para a Ciência e a Tecnologia (FCT), through strategic funding for Institute for Systems and Robotics/Laboratory for Robotics and Engineering Systems (ISR/LARSyS) under grant PEst-OE/EEI/LA0021/2013 and through the Carnegie Mellon Portugal Program under grant CMU-PT/SIA/0023/2009. This study also received national funds through the FCT, with reference UID/CEC/S0021/2013, and through grant FCT UID/EEA/50009/2013 of ISR/LARSyS.

Robots are currently being developed to enter our lives and interact with us in different tasks. For humans to be able to have a positive experience of interaction with such robots, they need to trust them to some degree. In this paper, we present the development and evaluation of a social robot that was created to play a card game with humans, playing the role of a partner and opponent. This type of activity is especially important, since our target group is elderly people - a population that often suffers from social isolation. Moreover, the card game scenario can lead to the development of interesting trust dynamics during the interaction, in which the human that partners with the robot needs to trust it in order to succeed and win the game. The design of the robot's behavior and game dynamics was inspired in previous user-centered design studies in which elderly people played the same game. Our evaluation results show that the levels of trust differ according to the previous knowledge that players have of their partners. Thus, humans seem to significantly increase their trust level towards a robot they already know, whilst maintaining the same level of trust in a human that they also previously knew. Henceforth, this paper shows that trust is a multifaceted construct that develops differently for humans and robots. info:eu-repo/semantics/acceptedVersion

Robot table tennis is a challenging domain in both robotics, artificial intelligence and machine learning. In terms of robotics, it requires fast and reliable perception and control; in terms of artificial intelligence, it requires fast decision making to determine the best motion to hit the ball; in terms of machine learning, it requires the ability to accurately estimate where and when the ball will be so that it can be hit. The use of sophisticated perception (relying, for example, in multi-camera vision systems) and state-of-the-art robot manipulators significantly alleviates concerns with perception and control, leaving room for the exploration of novel approaches that focus on estimating where, when and how to hit the ball. In this paper, we move away from the hardware setup commonly used in this domain—typically relying on robotic manipulators combined with an array of multiple fixed cameras—and give the first steps towards having autonomous aerial table tennis robotic players. Specifically, we focus on the task of hitting a ping pong ball thrown at a commercial drone, equipped with a light cardboard racket and an onboard camera. We adopt a general framework for learning complex robot tasks and show that, in spite of the perceptual and actuation limitations of our system, the overall approach enables the quadrotor system to successfully respond to balls served by a human user.

Geometry Friends (GF) is a physics-based platform game, used in one of the AI competitions of the IEEE CIG Conference in 2013 and 2014. The game engages two characters, a circle and a rectangle, in a cooperative challenge involving collecting a set of objects in a 2D platform world. In this work, we propose a novel learning approach to the control of the circle character that circumvents the excessive specialization to the public levels in the competition observed in the other existing solutions for GF. Our approach proposes a method that partitions solving a level of GF into three sub-tasks: solving one platform (SP1), deciding the next platform to solve (SP2) and moving from one platform to another (SP3). We use reinforcement learning to solve SP1 and SP3 and a depth-first search to solve SP2. The quality of the agent implemented was measured against the performance of the winner of the Circle Track of the 2014 GF Game AI Competition, CIBot. Our results show that our agent is able to successfully overcome the over-specialization to the public levels, showing comparatively better performance on the private levels.

In this paper we present a collaborative artificial intelligence (AI) module for a turn-based, multiplayer, environmental awareness game. The game is a version of the EnerCities serious game, modified in the context of a European-Union project to support sequential plays of an emphatic robotic tutor interacting with two human players in a social and pedagogical manner. For that purpose, we created an AI module capable of informing the game-playing and pedagogical decision-making of the robotic tutor. Specifically, the module includes an action planner capable of, together with a game simulator, perform forward-planning according to player preferences and current game values. Such predicted values are also used as an alert system to inform the other players of near consequences of current behaviors and advise alternative, sustainable courses of action in the game. The module also incorporates a social component that continuously models the game preferences of each player and automatically adjusts the tutor's strategy so to follow the group's “action tendency”. The proposed AI module is therefore used to inform about important aspects of the game state and also the human players actions. In this paper we overview the properties and complexity of this collaborative version of the game and detail the AI module and its components. We also report on the successes of using the proposed module for controlling the behavior of a robotic tutor in several experimental studies, including the interaction with children playing collaborative EnerCities.

This paper describes a new game AI competition that engages participants in the creation of agents for a cooperative platform puzzle game. The agents face the challenge of acting in a dynamic environment, with friction and gravity, as they coordinate actions to solve cooperative puzzles. Hence, agents need to devise cooperative plans to solve the puzzles in the most efficient way and to coordinate their actions to perform joint actions in real-time. The core of the competition is the cooperative track that requires the development of two distinct agents, but we also include a single player track for participants that want to craft the basic skills of the agent without the complexity of cooperation. In particular, to cope with understanding the topology of a level in order to define a plan for solving the puzzle or to define mechanisms to act well in the physics-based game environment. We present the results of the 2014 competition held at IEEE Conference on Computational Intelligence in Games, in Dortmund, and discuss some future directions of research.

Several agent-based frameworks have been proposed to investigate the possible reasons that lead humans to act in the interest of others while giving up individual gains. In this paper we propose a novel framework for analyzing this phenomenon based on the notions of social importance (SI) and local discrimination. We analyze such mechanism in the context of a “favors game” where a recipient agent can “claim” a favor to a donor agent, which may in turn “confer” its request at the expense of a certain cost. We perform several agent-based simulations and study both the conditions under which cooperation occurs and the dynamics of the relationships formed within a population. The results of our study indicate that the SI mechanism can promote cooperation in populations where all individuals share a common social predisposition towards the favors game, and also in initially mixed-strategy populations evolving by means of mutation and natural selection. We also show that the framework predicts the emergence of a conservative strategy that makes individuals to be “cautious” when interacting with “acquaintances”.

Recently, a novel framework has been proposed for intrinsically motivated reinforcement learning (IMRL) in which a learning agent is driven by rewards that include not only information about what the agent must accomplish in order to “survive”, but also additional reward signals that drive the agent to engage in other activities, such as playing or exploring, because they are “inherently enjoyable”. In this paper, we investigate the impact of intrinsic motivation mechanisms in multiagent learning scenarios, by considering how such motivational system may drive an agent to engage in behaviors that are “socially aware”. We show that, using this approach, it is possible for agents to learn individually to acquire socially aware behaviors that tradeoff individual well-fare for social acknowledgment, leading to a more successful performance of the population as a whole.

In this paper, we propose a reinforcement learning approach to address multi-robot cooperative navigation tasks in infinite settings. We propose an algorithm to simultaneously address the problems of learning and coordination in multi-robot problems. The proposed algorithm extends those existing in the literature, allowing to address simultaneous learning and coordination in problems with an infinite state-space. We also present the results obtained in several test scenarios featuring multi-robot navigation situations with partial observability.

In this paper we build an imitation learning algorithm for a humanoid robot on top of a general world model provided by learned object affordances. We consider that the robot has previously learned a task independent affordance-based model of its interaction with the world. This model is used to recognize the demonstration by another agent (a human) and infer the task to be learned. We discuss several important problems that arise in this combined framework, such as the influence of an inaccurate model in the recognition of the demonstration. We illustrate the ideas in the paper with some experimental results obtained with a real robot.

This paper explores how robotic teammates can enhance and promote cooperation in collaborative settings. It presents a user study in which participants engaged with two fully autonomous robotic partners to play a game together, named "For The Record", a variation of a public goods game. The game is played for a total of five rounds and in each of them, players face a social dilemma: to cooperate i.e., contributing towards the team's goal while compromising individual benefits, or to defect i.e., favouring individual benefits over the team's goal. Each participant collaborates with two robotic partners that adopt opposite strategies to play the game: one of them is an unconditional cooperator (the pro-social robot), and the other is an unconditional defector (the selfish robot). In a between-subjects design, we manipulated which of the two robots criticizes behaviours, which consists of condemning participants when they opt to defect, and it represents either an alignment or a misalignment of words and deeds by the robot. Two main findings should be highlighted (1) the misalignment of words and deeds may affect the level of discomfort perceived on a robotic partner; (2) the perception a human has of a robotic partner that criticizes him is not damaged as long as the robot displays an alignment of words and deeds.