Toward sociable robots

This paper explores the topic of social robots—the class of robots that people anthropomorphize in order to interact with them. From the diverse and growing number of applications for such robots, a few distinct modes of interaction are beginning to emerge. We distinguish four such classes: socially evocative, social interface, socially receptive, and sociable. For the remainder of the paper, we explore a few key features of sociable robots that distinguish them from the others. We use the vocal turn-taking behavior of our robot, Kismet, as a case study to highlight these points.     

Toward efficient path-planning for articulated robots

Real-time issues are becoming more and more important in robot programming. When a 6-dof manipulator is used, planning obstacle-avoiding paths is a time-consuming activity, usually done in simulation. We present the geometric models and the reasoning techniques we have implemented while realizing a gross motion planner for a manipulator with six revolute joints. First, construction of a problem-oriented representation of the robot working space is explained. Then, the actual trajectory research carried out in our C-space representation is described. The whole C-space is not calculated; instead, a sequential strategy is used to determine the C-space only for the first two links. Our approximation of the obstacles, which occupy fixed and known positions, greatly speeds the computation, allowing us to reduce the problem to planar geometric reasoning. The work is not limited to theoretical studies or simulations; experiments have been run very thoroughly, with various tests, on a PUMA robot to assess the real efficiency and usability of our software. The method applies to robots in a fixed and known environment. © 3995 John Wiley & Sons, Inc.     

Affective social robots

For human–robot interaction to proceed in a smooth, natural manner, robots must adhere to human social norms. One such human convention is the use of expressive moods and emotions as an integral part of social interaction. Such expressions are used to convey messages such as “I’m happy to see you” or “I want to be comforted,” and people’s long-term relationships depend heavily on shared emotional experiences. Thus, we have developed an affective model for social robots. This generative model attempts to create natural, human-like affect and includes distinctions between immediate emotional responses, the overall mood of the robot, and long-term attitudes toward each visitor to the robot, with a focus on developing long-term human–robot relationships. This paper presents the general affect model as well as particular details of our implementation of the model on one robot, the Roboceptionist. In addition, we present findings from two studies that demonstrate the model’s potential.     

A reference architecture for social robots

Social robotics poses tough challenges to software designers who are required to take care of difficult architectural drivers like acceptability, trust of robots as well as to guarantee that robots establish a personalized interaction with their users. Moreover, in this context recurrent software design issues such as ensuring interoperability, improving reusability and customizability of software components also arise. Designing and implementing social robotic software architectures is a time-intensive activity requiring multi-disciplinary expertise: this makes it difficult to rapidly develop, customize, and personalize robotic solutions. These challenges may be mitigated at design time by choosing certain architectural styles, implementing specific architectural patterns and using particular technologies. Leveraging on our experience in the MARIO project, in this paper we propose a series of principles that social robots may benefit from. These principles lay also the foundations for the design of a reference software architecture for social robots. The goal of this work is twofold: (i) Establishing a reference architecture whose components are unambiguously characterized by an ontology thus allowing to easily reuse them in order to implement and personalize social robots; (ii) Introducing a series of standardized software components for social robots architecture (mostly relying on ontologies and semantic technologies) to enhance interoperability, to improve explainability, and to favor rapid prototyping.     

Modeling and evaluating beat gestures for social robots

Multimedia Tools and Applications - Natural gestures are a desirable feature for a humanoid robot, as they are presumed to elicit a more comfortable interaction in people. With this aim in mind, we...     

Toward the intelligent control of robots

A new adaptive control architecture for the intelligent control of robotic manipulators is developed. The design is capable of utilizing external sensory information for the robot control. To achieve this, first a model reference adaptive control (MRAC) is developed which can be applied to a robot arm in the task space. Then the concept of virtual adaptive model is defined, which is used to formulate a maneuvering strategy in response to the external information. Finally, the virtual model provides the modified reference signals to the MRAC system to control the corresponding modified motion of the robot in the environment. The design does not require any knowledge about the dynamic parameters of the robot or that of the environment.     

Learning proactive behavior for interactive social robots

Learning human–robot interaction logic from example interaction data has the potential to leverage “big data” to reduce the effort and time spent on designing interaction logic or crafting interaction content. Previous work has demonstrated techniques by which a robot can learn motion and speech behaviors from non-annotated human–human interaction data, but these techniques only enable a robot to respond to human-initiated inputs, and do not enable the robot to proactively initiate interaction. In this work, we propose a method for learning both human-initiated and robot-initiated behavior for a social robot from human–human example interactions, which we demonstrate for a shopkeeper interacting with a customer in a camera shop scenario. This was achieved by extending an existing technique by (1) introducing a concept of a customer yield action, (2) incorporating interaction history, represented by sequences of discretized actions, as inputs for training and generating robot behavior, and (3) using an “attention mechanism” in our learning system for training robot behaviors, that learns which parts of the interaction history are more important for generating robot behaviors. The proposed method trains a robot to generate multimodal actions, consisting of speech and locomotion behaviors. We compared this study with the previous technique in two ways. Cross-validation on the training data showed higher social appropriateness of predicted behaviors using the proposed technique, and a user study of live interaction with a robot showed that participants perceived the proposed technique to produce behaviors that were more proactive, socially-appropriate, and better in overall quality.     

Emergent songs by social robots

This paper reports the first results of an innovative approach to modelling music cognition based on the emergent behaviour of interacting autonomous systems. A group of interactive autonomous singing robots were programmed to develop a shared repertoire of songs from scratch, after a period of spontaneous creations, adjustments and memory reinforcements. The robots interact with each other by means of vocal-like sounds. They use real sounds as opposed to software simulation. They are furnished with a physical model of the vocal tract, which synthesises vocal singing-like intonations, and a listening mechanism, which extracts pitch sequences from audio signals. The robots learn to imitate each other by babbling heard intonation patterns in order to evolve vectors of motor control parameters to synthesise the imitations. Models of the basic mechanisms underlying the emergence of songs are of great interest for musicians looking for hitherto unexplored ways to create music with interactive machines.     

Robust multiperson detection and tracking for mobile service and social robots

This paper proposes an efficient system which integrates multiple vision models for robust multiperson detection and tracking for mobile service and social robots in public environments. The core technique is a novel maximum likelihood (ML)-based algorithm which combines the multimodel detections in mean-shift tracking. First, a likelihood probability which integrates detections and similarity to local appearance is defined. Then, an expectation-maximization (EM)-like mean-shift algorithm is derived under the ML framework. In each iteration, the E-step estimates the associations to the detections, and the M-step locates the new position according to the ML criterion. To be robust to the complex crowded scenarios for multiperson tracking, an improved sequential strategy to perform the mean-shift tracking is proposed. Under this strategy, human objects are tracked sequentially according to their priority order. To balance the efficiency and robustness for real-time performance, at each stage, the first two objects from the list of the priority order are tested, and the one with the higher score is selected. The proposed method has been successfully implemented on real-world service and social robots. The vision system integrates stereo-based and histograms-of-oriented-gradients-based human detections, occlusion reasoning, and sequential mean-shift tracking. Various examples to show the advantages and robustness of the proposed system for multiperson tracking from mobile robots are presented. Quantitative evaluations on the performance of multiperson tracking are also performed. Experimental results indicate that significant improvements have been achieved by using the proposed method.     

Toward a user-guided manipulation framework for high-DOF robots with limited communication

This paper presents our progress toward a user-guided manipulation framework for high degree-of-freedom robots operating in environments with limited communication. The system we propose consists of three components: (1) a user-guided perception interface that assists the user in providing task-level commands to the robot, (2) planning algorithms that autonomously generate robot motion while obeying relevant constraints, and (3) a trajectory execution and monitoring system which detects errors in execution. We report quantitative experiments performed on these three components and qualitative experiments of the entire pipeline with the PR2 robot turning a valve for the DARPA robotics challenge. We also describe how the framework was ported to the Hubo2+ robot with minimal changes which demonstrates its applicability to different types of robots.     

Exploring influencing variables for the acceptance of social robots

In order to introduce social robots successfully, we must first understand the underlying reasons whereupon potential users accept these robots to reside within their own homes. An extensive literature review has been conducted and provides an overview of variables influencing the acceptance of social robots categorized by utilitarian variables, hedonic variables, user characteristics, social normative beliefs and control beliefs. In a user study, in which 60 participants interacted with a social robot, both the robot itself and the interaction experience the users had with the robot were evaluated. The results indicate that especially the variables of usefulness, adaptability, enjoyment, sociability, companionship and perceived behavioral control are important evaluating the user acceptance of social robots. Hence, the present study contributes to human–robot interaction research by designating the variables that lead to social robot acceptance. Subsequently, this study may serve as a onset in developing an integral model which takes into consideration the relevant determinants of social robot acceptance.     

Humans and humanoid social robots in communication contexts

As humanoid social robots are developed rapidly in recent years and experimented in social situations, comparing them to humans provides insights into practical as well as philosophical concerns. This study uses the theoretical framework of communication constraints, derived in human–human communication research, to compare whether people apply social-oriented constraints and task-oriented constraints differently to human targets versus humanoid social robot targets. A total of 230 students from the University of Hawaii at Manoa participated in the study. The participants completed a questionnaire, which determined their concern for the five communication constraints (feelings, non-imposition, disapproval, clarity, and effectiveness) in situations involving humans or robots. The results show people were more concerned with avoiding hurting the human’s feelings, avoiding inconveniencing the human interactive partner, and avoiding being disliked by the human and less concerned with avoiding hurting the robot’s feelings, avoiding inconveniencing the robot partner, and avoiding being disliked by the robot. But people did not differ in their concerns of the two task-oriented constraints (clarity and effectiveness) in response to humans versus humanoid robots. The results of the research suggest that people are more likely to emphasize the social-oriented constraints in communication with humans.     

A method for combining odometry and distance sensor information for effective obstacle avoidance of autonomous mobile robots

In this paper, a concept for virtual sensors is proposed for efficient avoidance of obstacles during the motion of robots. The virtual sensor yields new data by combining encoder values and real distance data, and derives new sensor data that includes the mobility of the robot. Simulation on Windows XP is executed to illustrate the proposed approach with actually acquired distance from virtual and actual sensors. To facilitate comparison with the alternative results developed in this paper, we refer to the conventional artificial potential field method using actual distance. Data from virtual sensors show smoother and safer motion in obstacle avoidance traces in regards to obstacle and robot mobility.     

Expressing and interpreting emotional movements in social games with robots

This paper provides a framework for recording, analyzing and modeling of 3 dimensional emotional movements for embodied game applications. To foster embodied interaction, we need interfaces that can develop a complex, meaningful understanding of intention—both kinesthetic and emotional—as it emerges through natural human movement. The movements are emulated on robots or other devices with sensory-motor features as a part of games that aim improving the social interaction skills of children. The design of an example game platform that is used for training of children with autism is described since the type of the emotional behaviors depends on the embodiment of the robot and the context of the game. The results show that quantitative movement parameters can be matched to emotional state of the embodied agent (human or robot) using the Laban movement analysis. Emotional movements that were emulated on robots using this principle were tested with children in the age group 7–9. The tests show reliable recognition on most of the behaviors.     

Non-anthropomorphic robots as social entities on a neurophysiological level

The mirror-neuron-system (MNS) is involved in the perception of actions of humans and anthropomorphic robots. The current study investigates whether social interaction with a non-anthropomorphic robot is sufficient for a response of the MNS.Fifty-seven participants observed movements of a vacuum cleaning robot before and after it was handled by its owner. The robot was either humanized, being treated aggressively (n = 30), or it was treated as an object (n = 27). Electroencephalographic mu-activity is used as an index of MNS activity, because both are inversely correlated. Activity within the 8–13 Hz band was measured at central (mu-activity) and occipital (alpha-activity) electrodes. Further, the level of aggressiveness displayed by the robot's owner, and the participants' compassion were rated on visual analog scales.Mu-activity showed medium-sized correlations with rated aggressiveness and compassion: The more aggressive the action towards the robot was perceived (r = −.379, p = .004), and the more compassion was felt for the robot (r = −.339, p = .010), the less pronounced mu-activity was at electrode C3 in response to the robot's movement.Thus social interaction with a non-anthropomorphic robot might establish the robot as a social entity and is sufficient to activate the human MNS.     

Getting to know each other—Artificial social intelligence for autonomous robots

This paper proposes a research direction to study the development of ‘artificial social intelligence’ of autonomous robots which should result in ‘individualized robot societies’. The approach is highly inspired by the ‘social intelligence hypothesis’, derived from the investigation of primate societies, suggesting that primate intelligence originally evolved to solve social problems and was only later extended to problems outside the social domain. We suggest that it might be a general principle in the evolution of intelligence, applicable to both natural and artificial systems. Arguments are presented why the investigation of social intelligence for artifacts is not only an interesting research issue for the study of biological principles, but may be a necessary prerequisite for those scenarios in which autonomous robots are integrated into human societies, interacting and communicating both with humans and with each other. As a starting point to study experimentally the development of robots' ‘social relationships’, the investigation of collection and use of body images by means of imitation is proposed. A specific experimental setup which we use to test the theoretical considerations is described. The paper outlines in what kind of applications and for what kind of robot group structures social intelligence might be advantageous.     

融合评分和社会化标签的两阶段深度推荐方法

当前融合评分和标签的推荐方法对两种数据的挖掘程度有限,且大多数局限在提取浅层的线性特征层面.深度学习技术被成功应用于推荐方法,然而数据的稀疏性导致学习的潜在特征效果不好,因此,提出一种融合评分和社会化标签的两阶段深度推荐方法.首先,利用堆叠降噪自编码器分别从评分和社会化标签中提取用户、项目的潜在特征;其次,将学习的潜在特征进行拼接作为用户、项目完整的潜在特征,并与原始评分相结合构建监督学习数据集;最后,将构建的数据集作为BP神经网络的输入以训练评分预测模型.为降低训练误差,通过联合训练的方式进行参数学习.基于MovieLens、Last.FM数据集的实验表明,该方法与几种基准方法相比有更好的推荐性能.     

Toward a conversational model for counsel robots: how different question types elicit different linguistic behaviors

Intelligent Service Robotics - In recent years, robots have been playing the role of counselor or conversational partner in everyday dialogues and interactions with humans. For successful...