Volume 9, Issue 1

People exhibit a robust ability to understand the actions of others around them. In this work, we identify two biologically inspired mechanisms that we hypothesize to be central in the function of action understanding. The first module is a contextual predictor of the observed action, given the goal-directed movement towards objects, and the actions that are allowed to be performed on the object. The second module is a kinematic trajectory parser that validates the previous prediction against a set of learned templates.We model both mechanisms and link them to the environment using the cognitive framework of Dynamic Field Theory and present our first steps into integrating the aforementioned modules into a consistent framework for the purpose of action understanding. The two modules and the combined architecture as awhole are experimentally validated using a recording of an actor performing a series of intentional actions testing the ability of the architecture to understand context and parse actions dynamically. Our initial qualitative results show that action understanding benefits from the combination of the two modules, while any module alone would be insufficient to resolve ambiguity in the perceived actions.

This paper solves the problem of localization for indoor environments using visual place recognition, visual odometry and experience based localization using a camera. Our main motivation is just like a human is able to recall from its past experience, a robot should be able to use its recorded visual memory in order to determine its location. Currently experience based localization has been used in constrained environments like outdoor roads, where the robot is constrained to the same set of locations during every visit. This paper adapts the same technology to wide open maps like halls wherein the robot is not constrained to specific locations. When a robot is turned on in a room, it first uses visual place recognition using histogram of oriented gradients and support vector machine in order to predict which room it is in. It then scans its surroundings and uses a nearest neighbor search of the robot’s experience coupled with visual odometry for localization. We present the results of our approach test on a dynamic environment comprising of three rooms. The dataset consists of approximately 5000 monocular and 5000 depth images.

This article is focused on the multi-robot applied Voronoi tessellation based area partitioning algorithm operation and properties. The selection of main parameters of the algorithm is covered and explanation of the algorithm functionality is given. The subspace area equality and the operation time are taken as main measures of the algorithm operation for experiments where a dependency on the border shape and structure and a number of robots in the group are considered. The experimental data, gained during the study, is summarized mainly in a graphical way.

Robotic telepresence technologies are becoming ever more usable and affordable, as well as increasingly available as consumer products. In the coming years, a significant number of people are likely to encounter the technology for the first time, and many, if not most, of them are going to be “non-technical” users, that is, people who do not have special technical knowledge and skills of IT-professionals. Therefore, understanding how nontechnical users are getting familiar with robotic telepresence technology, how they perceive the technology, learn to control it, and relate it to their everyday work practices, is a topical research issue. This paper reports an empirical study, in which eight non-technical users, office workers who were not IT-professionals, were introduced to robotic telepresence and provided with a practical experience of acting as pilots of a remotely controlled robot. In follow up interviews the participants were asked to reflect on potential uses of the technology in their professional activities. The participants could successfully acquire basic navigation skills and reached a high level of spatial presence, but experienced problems with developing a "new body image”. When reflecting on the potential of the technology for supporting their work, the participants envisioned a number of benefits associated with remote physical mobility. The impact of the technology on the quality of workrelated social interactions was expected to be generally positive but somewhat limited.

While first empirical studies on sexual aspects of human-robot interaction mostly focus on male users’ acceptance, there is no empirical research on how females react to robotic replications of women. To empirically investigate whether robots can evoke the same kind of jealousy-related discomfort as do other women, we conducted an online study in which 848 heterosexual female participants from Germany reacted to the idea that their partner had sexual intercourse with either another woman, a human-like female-looking robot, or a machinelike female-looking robot. The results revealed dimensions in which the jealousy-related discomfort was higher for female competitors compared to the robotic ones (e.g., discomfort caused by the idea of sexual intercourse),whereas in others the robots evoked the same or higher levels of jealousy-related discomfort (e.g., discomfort caused by feelings of inadequacy, discomfort caused by shared emotional and time resources). The variance in the discomfort regarding sexual interactions between one’s partner and robotic competitors could not be explained by personal characteristics (such as self-esteem, subjective physical attractiveness) but rather by technology-related variables (e.g., negative attitude towards robots, a tendency towards anthropomorphism) and the attitude towards sexual nonexclusivity in relationships. The study provides first empirical insights into a question which is of relevance for a responsible handling of sexualized technologies.

This article calls out the common assumption that moral consciousness occurs at the level of individual brains and robots. It explores the alternative, evidence against the assumption, and provides a means to further test the assumption. It also discusses the consequences of making or abandoning this assumption, especially the consequences for the further evolution of robots.

Masahiro Mori is a well-known Japanese robotics scholar whose notion of Uncanny Valley is worldly famous. Mori is also an initiator of the Robot Contest and a student of Buddhism and a practitioner of Zen. He constructs his original Buddhist philosophy of robotics throughout his career. His robotics work and his learning of Buddhism develop together side by side in an interesting intertwined manner. This paper will take up the issues such as the ethical personality, quality of minds, and experiences of engineers as key components in and for an “ethical design” of robots by examining Mori’s Buddhist philosophy of robotics. This paper is divided into four sections. After an introductory part, in the second section, we will explore Mori’s view of Zen as aspiritual source for technological creativity. In Section 3, we will examine his view into a robot-contest as a location of a realized teaching of Buddhism, especially, in relationship to the Diamond Sūtra, in order to see Mori’s educational contribution. In Section 4, we will examine how Mori became engaged to learn and practice Buddhism and came to the realization of Buddhahood in relation to robotics.

Autonomous robots are here and military leaders have typically sought to understand the human-machine relationship as a matter of trust - a human-machine engineering problem with a largely technical solution. This paper argues that engineering is merely one part of the challenge and that trust in robotics and automation ought to be understood in a much broader socio-psychological context, defined by a power process, the capacity of soldiers to endure subjection to technology and the extent to which automation impinges upon one’s autonomy or otherwise impacts the soldier’s wellbeing.

In the backdrop of increasingly intelligent machines, important issues of law have been raised by the use of robots that operate autonomous from human supervisory control. In particular, when systems operating with autonomous robot’s damage property or injure humans, it may be difficult to determinewho’s at fault and therefore liable under current legal schemes. This paper reviews product liability and negligence tort law which may be used to allocate liability for robots that damage property or cause injury. Further, the paper concludes with a discussion of different approaches to allocating liability in an age of increasingly intelligent and autonomous robots directed by sophisticated algorithms, analytical, and computational techniques

Semi-autonomous machines, autonomous machines and robots inhabit closed, semi-closed and open environments. There they encounter domestic animals, farm animals, working animals and/or wild animals. These animals could be disturbed, displaced, injured or killed. Within the context of machine ethics, the School of Business FHNW developed several design studies and prototypes for animal-friendly machines,which can be understood as moral machines in the spirit of this discipline. They were each linked with an annotated decision tree containing the ethical assumptions or justifications for interactions with animals. Annotated decision trees are seen as an important basis in developing moral machines. They are not without problems and contradictions, but they do guarantee well-founded, secure actions that are repeated at a certain level. This article documents completed and current projects, compares their relative risks and benefits, and makes proposals for future developments in machine ethics. The findings in this article and proposals for the future hope to systemically promote animal well-being and prevent animal suffering in encounters between machines and animals.

We argue that ethically significant behavior of autonomous systems should be guided by explicit ethical principles determined through a consensus of ethicists. Such a consensus is likely to emerge in many areas in which intelligent autonomous systems are apt to be deployed and for the actions they are liable to undertake, as we are more likely to agree on how machines ought to treat us than on how human beings ought to treat one another. Given such a consensus, particular cases of ethical dilemmas where ethicists agree on the ethically relevant features and the right course of action can be used to help discover principles needed for ethical guidance of the behavior of autonomous systems. Such principles help ensure the ethical behavior of complex and dynamic systems and further serve as a basis for justification of this behavior. To provide assistance in discovering ethical principles, we have developed GenEth, a general ethical dilemma analyzer that, through a dialog with ethicists, uses inductive logic programming to codify ethical principles in any given domain. GenEth has been used to codify principles in a number of domains pertinent to the behavior of autonomous systems and these principles have been verified using an Ethical Turing Test, a test devised to compare the judgments of codified principles with that of ethicists.

Automatic gaze estimation not based on commercial and expensive eye tracking hardware solutions can enable several applications in the fields of human computer interaction (HCI) and human behavior analysis. It is therefore not surprising that several related techniques and methods have been investigated in recent years. However, very few camera-based systems proposed in the literature are both real-time and robust. In this work, we propose a real-time user-calibration-free gaze estimation system that does not need person-dependent calibration, can deal with illumination changes and head pose variations, and can work with a wide range of distances from the camera. Our solution is based on a 3-D appearance-based method that processes the images from a built-in laptop camera. Real-time performance is obtained by combining head pose information with geometrical eye features to train a machine learning algorithm. Our method has been validated on a data set of images of users in natural environments, and shows promising results. The possibility of a real-time implementation, combined with the good quality of gaze tracking, make this system suitable for various HCI applications.

This paper describes a bio-inspired algorithm for motion computation based on V1 (Primary Visual Cortex) andMT (Middle Temporal Area) cells. The behavior of neurons in V1 and MT areas contain significant information to understand the perception of motion. From a computational perspective, the neurons are treated as two dimensional filters to represent the receptive fields of simple cells that compose the complex cells. A modified elaborated Reichardt detector, adding an output exponent before the last stage followed by a re-entry stage of modulating feedback from MT, (reciprocal connections of V1 and MT) in a hierarchical framework, is proposed. The endstopped units, where the receptive fields of cells are surrounded by suppressive regions, are modeled as a divisive operation. MT cells play an important role for integrating and interpreting inputs from earlier-level (V1).We fit a normalization and a pooling to find the most active neurons for motion detection. All steps employed are physiologically inspired processing schemes and need some degree of simplification and abstraction. The results suggest that our proposed algorithm can achieve better performance than recent state-of-the-art bio-inspired approaches for real world images.

In order to be acceptable and able to “camouflage” into their physio-social context in the long run, robots need to be not just functional, but autonomously psycho-affective as well. This motivates a long term necessity of introducing behavioral autonomy in robots, so they can autonomously communicate with humans without the need of “wizard” intervention. This paper proposes a technique to learn robot speech models from human-robot dialog exchanges. It views the entire exchange in the Automated Planning (AP) paradigm, representing the dialog sequences (speech acts) in the form of action sequences that modify the state of the world upon execution, gradually propelling the state to a desired goal. We then exploit intra-action and inter-action dependencies, encoding them in the form of constraints. We attempt to satisfy these constraints using aweighted maximum satisfiability model known as MAX-SAT, and convert the solution into a speech model. This model could have many uses, such as planning of fresh dialogs. In this study, the learnt model is used to predict speech acts in the dialog sequences using the sequence labeling (predicting future acts based on previously seen ones) capabilities of the LSTM (Long Short Term Memory) class of recurrent neural networks. Encouraging empirical results demonstrate the utility of this learnt model and its long term potential to facilitate autonomous behavioral planning of robots, an aspect to be explored in future works.

Spoken language is one of the most efficientways to instruct robots about performing domestic tasks. However, the state of the environment has to be considered to plan and execute actions successfully. We propose a system that learns to recognise the user’s intention and map it to a goal. A reinforcement learning (RL) system then generates a sequence of actions toward this goal considering the state of the environment. A novel contribution in this paper is the use of symbolic representations for both input and output of a neural Deep Q-network (DQN), which enables it to be used in a hybrid system. To show the effectiveness of our approach, the Tell-Me-Dave corpus is used to train an intention detection model and in a second step an RL agent generates the sequences of actions towards the detected objective, represented by a set of state predicates. We show that the system can successfully recognise command sequences fromthis corpus aswell as train the deep- RL network with symbolic input.We further show that the performance can be significantly increased by exploiting the symbolic representation to generate intermediate rewards.

In this work, we study how learning in a special environment such as a museum can influence the behavior of robots. More specifically, we show that online learning based on interaction with people at a museum leads the robots to develop individual preferences. We first developed a humanoid robot (Berenson) that has the ability to head toward its preferred object and to make a facial expression that corresponds to its attitude toward said object. The robot is programmed with a biologically-inspired neural network sensory-motor architecture. This architecture allows Berenson to learn and to evaluate objects. During experiments, museum visitors’ emotional responses to artworks were recorded and used to build a database for training. A similar database was created in the laboratory with laboratory objects. We use those databases to train two simulated populations of robots. Each simulated robot emulates the Berenson sensory-motor architecture. Firstly, the results show the good performance of our architecture in artwork recognition in the museum. Secondly, they demonstrate the effect of training variability on preference diversity. The response of the two populations in a new unknown environment is different; the museum population of robots shows a greater variance in preferences than the population of robots that have been trained only on laboratory objects. The obtained diversity increases the chances of success in an unknown environment and could favor an accidental discovery.

In this paper, we examine trust in a human-robot medical interaction. We focus on the influence of transparency and robot adaptability on people’s trust in a human-robot blood pressure measuring scenario. Our results show that increased transparency, i.e. robot explanations of its own actions designed to make the process and robot behaviors and capabilities accessible to the user, has a consistent effect on people’s trust and perceived comfort. In contrast, robot adaptability, i.e., the opportunity to adjust the robot’s position according to users’ needs, influences users’ evaluations of the robot as trustworthy only marginally. Our qualitative analyses indicate that this is due to the fact that transparency and adaptability are complex factors; the investigation of the interactional dynamics shows that users have very specific needs, and that adaptability may have to be paired with responsivity in order to make people feel in control.

Humans should be able to trust that they can safely interact with their home companion robot. However, robots can exhibit occasional mechanical, programming or functional errors. We hypothesise that the severity of the consequences and the timing of a robot’s different types of erroneous behaviours during an interaction may have different impacts on users’ attitudes towards a domestic robot. First, we investigated human users’ perceptions of the severity of various categories of potential errors that are likely to be exhibited by a domestic robot. Second, we used an interactive storyboard to evaluate participants’ degree of trust in the robot after it performed tasks either correctly, or with ‘small’ or ‘big’ errors. Finally, we analysed the correlation between participants’ responses regarding their personality, predisposition to trust other humans, their perceptions of robots, and their interaction with the robot. We conclude that there is correlation between the magnitude of an error performed by a robot and the corresponding loss of trust by the human towards the robot. Moreover we observed that some traits of participants’ personalities (conscientiousness and agreeableness) and their disposition of trusting other humans (benevolence) significantly increased their tendency to trust a robot more during an emergency scenario.

The interest towards robots for elderly care has been growing in the last years. Systems aiming to integrate robot interactive components and the user’s activity recognition system are increasing as well. This work presents an activity aware intelligent system that supports user in his/her daily life tasks. The proposed system aims to integrate three important aspects into a smart house application (environment monitoring, user activity recognition and user friendly interaction). The information gathered from sensors across the environment is structured as the state of the environment in a compacted form called activity frame. This specific frame is used by a predictor (based on the decision tree method), in order to recognize the activities that have been performed by the user inside his/her domestic environment. The recognized activity is used by an user-interactive component, which uses the predicted behavior as a guideline for its interaction planner. The presented activity recognition system was tested with the data provided by different smart home projects, and the recognition rate for the proposed predictor has high recognition rate compared to other similar ones. The architecture described by the sensory network allows the system to be easily implemented in real time in a smart house context.

Human-robot interaction in social robotics applications could be greatly enhanced by robotic behaviors that incorporate emotional body language. Using as our starting point a set of pre-designed, emotion conveying animations that have been created by professional animators for the Pepper robot, we seek to explore how humans perceive their affect content, and to increase their usability by annotating them with reliable labels of valence and arousal, in a continuous interval space. We conducted an experiment with 20 participants who were presented with the animations and rated them in the two-dimensional affect space. An inter-rater reliability analysis was applied to support the aggregation of the ratings for deriving the final labels. The set of emotional body language animations with the labels of valence and arousal is available and can potentially be useful to other researchers as a ground truth for behavioral experiments on robotic expression of emotion, or for the automatic selection of robotic emotional behaviors with respect to valence and arousal. To further utilize the data we collected, we analyzed it with an exploratory approach and we present some interesting trends with regard to the human perception of Pepper’s emotional body language, that might be worth further investigation.

Handshaking is a fundamental part of human physical interaction that is transversal to various cultural backgrounds. It is also a very challenging task in the field of Physical Human-Robot Interaction (pHRI), requiring compliant force control in order to plan the arm’s motion and for a confident, but at the same time pleasant grasp of the human user’s hand. In this paper,we focus on the study of the hand grip strength for comfortable handshakes and perform three sets of physical interaction experiments between twenty human subjects in the first experiment, thirty-five human subjects in the second one, and thirty-eight human subjects in the third one. Tests are made with a social robot whose hands are instrumented with tactile sensors that provide skin-like sensation. From these experiments, we: (i) learn the preferred grip closure according to each user group; (ii) analyze the tactile feedback provided by the sensors for each closure; (iii) develop and evaluate the hand grip controller based on previous data. In addition to the robot-human interactions, we also learn about the robot executed handshake interactions with inanimate objects, in order to detect if it is shaking hands with a human or an inanimate object. This work adds physical human-robot interaction to the repertory of social skills of our robot, fulfilling a demand previously identified by many users of the robot.

Using assistive robots for educational applications requires robots to be able to adapt their behavior specifically for each child with whom they interact.Among relevant signals, non-verbal cues such as the child’s gaze can provide the robot with important information about the child’s current engagement in the task, and whether the robot should continue its current behavior or not. Here we propose a reinforcement learning algorithm extended with active state-specific exploration and show its applicability to child engagement maximization as well as more classical tasks such as maze navigation. We first demonstrate its adaptive nature on a continuous maze problem as an enhancement of the classic grid world. There, parameterized actions enable the agent to learn single moves until the end of a corridor, similarly to “options” but without explicit hierarchical representations.We then apply the algorithm to a series of simulated scenarios, such as an extended Tower of Hanoi where the robot should find the appropriate speed of movement for the interacting child, and to a pointing task where the robot should find the child-specific appropriate level of expressivity of action. We show that the algorithm enables to cope with both global and local non-stationarities in the state space while preserving a stable behavior in other stationary portions of the state space. Altogether, these results suggest a promising way to enable robot learning based on non-verbal cues and the high degree of non-stationarities that can occur during interaction with children.

As robots become more and more capable and autonomous, there is an increasing need for humans to understand what the robots do and think. In this paper, we investigate what such understanding means and includes, and how robots can be designed to support understanding. After an in-depth survey of related earlier work, we discuss examples showing that understanding includes not only the intentions of the robot, but also desires, knowledge, beliefs, emotions, perceptions, capabilities, and limitations of the robot. The term understanding is formally defined, and the term communicative actions is defined to denote the various ways in which a robot may support a human’s understanding of the robot. A novel model of interaction for understanding is presented. The model describes how both human and robot may utilize a first or higher-order theory of mind to understand each other and perform communicative actions in order to support the other’s understanding. It also describes simpler cases in which the robot performs static communicative actions in order to support the human’s understanding of the robot. In general, communicative actions performed by the robot aim at reducing the mismatch between the mind of the robot, and the robot’s inferred model of the human’s model of the mind of the robot. Based on the proposed model, a set of questions are formulated, to serve as support when developing and implementing the model in real interacting robots.

With the aging of the population worldwide, humanoid robots are being used with an older population, e.g., stroke patients and people with dementia. There is a growing body of knowledge on how people interact with robots, but limited information on the difference between young and old adults in their preferences when interacting with humanoid robots and what factors influence these preferences.We developed a gamified robotic platform of a cognitive-motor task.We conducted two experiments with the following aims: to test how age, location of touch interaction (touching the robot’s tablet or hand), and embodied presence of a humanoid robot affect the motivation of different age-group users to continue performing a cognitive-motor task. A total of 60 participants (30 old adults and 30 young adults) took part in two experiments with the humanoid Pepper robot (Softbank robotics). Both old and young adults reported they enjoyed the interaction with the robot as they found it engaging and fun, and preferred the embodied robot over the non-embodied computer screen. This study highlights that in order for the experience of the user to be positive a personalization of the interaction according to the age, the needs of the user, the characteristics, and the pace of the task is needed.

We discuss the process of building semantic maps, how to interactively label entities in them, and how to use them to enable context-aware navigation behaviors in human environments. We utilize planar surfaces, such as walls and tables, and static objects, such as door signs, as features for our semantic mapping approach. Users can interactively annotate these features by having the robot follow him/her, entering the label through a mobile app, and performing a pointing gesture toward the landmark of interest. Our gesture-based approach can reliably estimate which object is being pointed at, and detect ambiguous gestures with probabilistic modeling. Our person following method attempts to maximize future utility by search for future actions assuming constant velocity model for the human. We describe a method to extract metric goals from a semantic map landmark and to plan a human aware path that takes into account the personal spaces of people. Finally, we demonstrate context awareness for person following in two scenarios: interactive labeling and door passing.We believe that future navigation approaches and service robotics applications can be made more effective by further exploiting the structure of human environments.

Within human Intent Recognition (IR), a popular approach to learning from demonstration is Inverse Reinforcement Learning (IRL). IRL extracts an unknown reward function from samples of observed behaviour. Traditional IRL systems require large datasets to recover the underlying reward function. Object affordances have been used for IR. Existing literature on recognizing intents through object affordances fall short of utilizing its true potential. In this paper, we seek to develop an IRL system which drives human intent recognition along with the capability to handle high dimensional demonstrations exploiting the capability of object affordances. An architecture for recognizing human intent is presented which consists of an extended Maximum Likelihood Inverse Reinforcement Learning agent. Inclusion of Symbolic Conceptual Abstraction Engine (SCAE) along with an advisor allows the agent to work on Conceptually Abstracted Markov Decision Process. The agent recovers object affordance based reward function from high dimensional demonstrations. This function drives a Human Intent Recognizer through identification of probable intents. Performance of the resulting system on the standard CAD-120 dataset shows encouraging result.