Experimental investigation into influence of negative attitudes toward robots on human–robot interaction

Negative attitudes toward robots are considered as one of the psychological factors preventing humans from interacting with robots in the daily life. To verify their influence on humans‘ behaviors toward robots, we designed and executed experiments where subjects interacted with Robovie, which is being developed as a platform for research on the possibility of communication robots. This paper reports and discusses the results of these experiments on correlation between subjects’ negative attitudes and their behaviors toward robots. Moreover, it discusses influences of gender and experience of real robots on their negative attitudes and behaviors toward robots.

Design and control of a heavy material handling manipulator for agricultural robots

In this paper, we propose a manipulation system for agricultural robots that handle heavy materials. The structural systems of a mobile platform and a manipulator are selected and designed after proposing new knowledge about agricultural robots. Also, the control systems for these structural systems are designed in the presence of parametric perturbation and uncertainty while avoiding conservative results. The validity of both the structural and control systems is confirmed by conducting watermelon harvesting experiments in an open field. Furthermore, an explicit design procedure is confirmed for both the structural and control systems and three key design tools are clarified.

Improving walking-robot performances by optimizing leg distribution

Walking-robot technology has already achieved an important stage of development, as demonstrated in a few real applications. However, walking robots still need further improvement if they are to compete with traditional vehicles. A potential improvement could be made through optimization at design time. A better distribution of the legs around a robot’s body can help decrease actuator size in the design procedure and reduce power consumption during walking as well, which is of vital importance in autonomous robots. This paper, thus, presents a method focused on the distribution of legs around the body to decrease maximum foot forces against the ground, which play heavily in determining robot shape and actuator size. Some experiments have been performed with the SILO6 walking robot to validate the theoretical results.

Does Japan really have robot mania? Comparing attitudes by implicit and explicit measures

Japan has more robots than any other country with robots contributing to many areas of society, including manufacturing, healthcare, and entertainment. However, few studies have examined Japanese attitudes toward robots, and none has used implicit measures. This study compares attitudes among the faculty of a US and a Japanese university. Although the Japanese faculty reported many more experiences with robots, implicit measures indicated both faculties had more pleasant associations with humans. In addition, although the US faculty reported people were more threatening than robots, implicit measures indicated both faculties associated weapons more strongly with robots than with humans. Despite the media’s hype about Japan’s robot ‘craze,’ response similarities suggest factors other than attitude better explain robot adoption. These include differences in history and religion, personal and human identity, economic structure, professional specialization, and government policy. Japanese robotics offers a unique reference from which other nations may learn.

---

Linear estimation of the physical odometric parameters for differential-drive mobile robots

In this paper a calibration technique aimed at identifying the odometric parameters of differential-drive mobile robots is proposed. The algorithm is based on two successive least-squares estimations based on the continuous-time kinematic equations of motion; the time-discretization error, thus, is avoided. The use of the least-squares technique is made possible by working on a linear mapping between the unknowns and the measurements and is not the result of a linearization. Another advantage of the proposed technique is that no specific path is required. The basic technique makes use of video-camera measurements and absolute position readings of the wheels’ encoders; the use of different sensors and measurements of the wheels velocities is also discussed. Experimental results with a mobile robot Khepera II confirm the effectiveness of the proposed technique.

Caregiving robots and ethical reflection: the perspective of interdisciplinary technology assessment

Autonomous robots that are capable of learning are being developed to make it easier for human actors to achieve their goals. As such, robots are primarily a means to an end and replace human actions (or parts of them). An interdisciplinary technology assessment was carried out to determine the extent to which a replacement of this kind makes ethical sense in terms of technology, economics and legal aspects. Proceeding from an ethical perspective, derived from Kant’s formula of humanity, in this article we analyse the use of robots in the care of the elderly or infirm and then examine robot learning in the context of this kind of cooperation.

---

Geodesic Gaussian kernels for value function approximation

The least-squares policy iteration approach works efficiently in value function approximation, given appropriate basis functions. Because of its smoothness, the Gaussian kernel is a popular and useful choice as a basis function. However, it does not allow for discontinuity which typically arises in real-world reinforcement learning tasks. In this paper, we propose a new basis function based on geodesic Gaussian kernels, which exploits the non-linear manifold structure induced by the Markov decision processes. The usefulness of the proposed method is successfully demonstrated in simulated robot arm control and Khepera robot navigation.

Ethical regulations on robotics in Europe

There are only a few ethical regulations that deal explicitly with robots, in contrast to a vast number of regulations, which may be applied. We will focus on ethical issues with regard to “responsibility and autonomous robots”, “machines as a replacement for humans”, and “tele-presence”. Furthermore we will examine examples from special fields of application (medicine and healthcare, armed forces, and entertainment). We do not claim to present a complete list of ethical issue nor of regulations in the field of robotics, but we will demonstrate that there are legal challenges with regard to these issues.

---

Fault detection in autonomous robots based on fault injection and learning

In this paper, we study a new approach to fault detection for autonomous robots. Our hypothesis is that hardware faults change the flow of sensory data and the actions performed by the control program. By detecting these changes, the presence of faults can be inferred. In order to test our hypothesis, we collect data from three different tasks performed by real robots. During a number of training runs, we record sensory data from the robots while they are operating normally and after a fault has been injected. We use back-propagation neural networks to synthesize fault detection components based on the data collected in the training runs. We evaluate the performance of the trained fault detectors in terms of number of false positives and time it takes to detect a fault. The results show that good fault detectors can be obtained. We extend the set of possible faults and go on to show that a single fault detector can be trained to detect several faults in both a robot’s sensors and actuators. We show that fault detectors can be synthesized that are robust to variations in the task, and we show how a fault detector can be trained to allow one robot to detect faults that occur in another robot.

Multi-robot deployment and coordination with Embedded Graph Grammars

This paper presents a framework for going from specifications to implementations of decentralized control strategies for multi-robot systems. In particular, we show how the use of Embedded Graph Grammars (EGGs) provides a tool for characterizing local interaction and control laws. This paper highlights some key implementation aspects of the EGG formalism, and develops and discusses experimental results for a hexapod-based multi-robot system, as well as a multi-robot system of wheeled robots.

Extending obstacle avoidance methods through multiple parameter-space transformations

Obstacle avoidance methods approach the problem of mobile robot autonomous navigation by steering the robot in real-time according to the most recent sensor readings, being suitable to dynamic or unknown environments. However, real-time performance is commonly gained by ignoring the robot shape and some or all of its kinematic restrictions which may lead to poor navigation performance in many practical situations. In this paper we propose a framework where a kinematically constrained and any-shape robot is transformed in real-time into a free-flying point in a new space where well-known obstacle avoidance methods are applicable. Our contribution with this framework is twofold: the definition of generalized space transformations that cover most of the existing transformational approaches, and a reactive navigation system where multiple transformations can be applied concurrently in order to optimize robot motion decisions. As a result, these transformations allow existing obstacle avoidance methods to perform better detection of the surrounding free-space, through “sampling” the space with paths compatible with the robot kinematics. We illustrate how to design these space transformations with some examples from our experience with real robots navigating in indoor, cluttered, and dynamic scenarios. Also, we provide experimental results that demonstrate the advantages of our approach over previous methods when facing similar situations.

An autonomous educational mobile robot mediator

So far, most of the applications of robotic technology to education have mainly focused on supporting the teaching of subjects that are closely related to the Robotics field, such as robot programming, robot construction, or mechatronics. Moreover, most of the applications have used the robot as an end or a passive tool of the learning activity, where the robot has been constructed or programmed. In this paper, we present a novel application of robotic technologies to education, where we use the real world situatedness of a robot to teach non-robotic related subjects, such as math and physics. Furthermore, we also provide the robot with a suitable degree of autonomy to actively guide and mediate in the development of the educational activity. We present our approach as an educational framework based on a collaborative and constructivist learning environment, where the robot is able to act as an interaction mediator capable of managing the interactions occurring among the working students. We illustrate the use of this framework by a 4-step methodology that is used to implement two educational activities. These activities were tested at local schools with encouraging results. Accordingly, the main contributions of this work are: i) A novel use of a mobile robot to illustrate and teach relevant concepts and properties of the real world; ii) A novel use of robots as mediators that autonomously guide an educational activity using a collaborative and constructivist learning approach; iii) The implementation and testing of these ideas in a real scenario, working with students at local schools.

Dealing with internal and external perturbations on walking robots

Up to now, walking robots have been working outdoors under favorable conditions and using very large stability margins to cope with natural environments and intrinsic robot dynamics that can cause instability in these machines when they use statically-stable gaits. The result has been very slow robots prone to tumble down in the presence of perturbations. This paper proposes a novel gait-adaptation method based on the maximization of the Normalized Dynamic Energy Stability Margin. This method enables walking-machine gaits to adapt to internal (robot dynamics) and external (environmental) perturbations, including the slope of the terrain, by finding the gait parameters that maximize robot stability. The adaptation method is inspired in the natural gait adaptation carried out by humans and animals to balance external forces or the effect of sloping terrain. Experiments with the SILO4 quadruped robot are presented and show how robot stability is more robust when the proposed approach is used for different external forces and sloping terrains. Using the proposed gait-adaptation approach the robot is able to withstand external forces up to 58% the robot weight and 25-degree slopes.

Legal safeguards for privacy and data protection in ambient intelligence

To get the maximum benefit from ambient intelligence (AmI), we need to anticipate and react to possible drawbacks and threats emerging from the new technologies in order to devise appropriate safeguards. The SWAMI project took a precautionary approach in its exploration of the privacy risks in AmI and sought ways to reduce them. It constructed four “dark scenarios” showing possible negative implications of AmI, notably for privacy protection. Legal analysis of the depicted futures showed the shortcomings of the current legal framework in being able to provide adequate privacy protection in the AmI environment. In this paper, the authors, building upon their involvement in SWAMI research as well as the further advancement of EU privacy analysis, identify various outstanding issues regarding the legal framework that still need to be resolved in order to deal with AmI in an equitable and efficacious way. This article points out some of the lacunae in the legal framework and postulates several privacy-specific safeguards aimed at overcoming them.

---

A unified learning framework for object detection and classification using nested cascades of boosted classifiers

In this paper a unified learning framework for object detection and classification using nested cascades of boosted classifiers is proposed. The most interesting aspect of this framework is the integration of powerful learning capabilities together with effective training procedures, which allows building detection and classification systems with high accuracy, robustness, processing speed, and training speed. The proposed framework allows us to build state of the art face detection, eyes detection, and gender classification systems. The performance of these systems is validated and analyzed using standard face databases (BioID, FERET and CMU-MIT), and a new face database (UCHFACE).

Interacting with mobile services: an evaluation of camera-phones and visual tags

We present a study of using camera-phones and visual-tags to access mobile services. Firstly, a user-experience study is described in which participants were both observed learning to interact with a prototype mobile service and interviewed about their experiences. Secondly, a pointing-device task is presented in which quantitative data was gathered regarding the speed and accuracy with which participants aimed and clicked on visual-tags using camera-phones. We found that participants’ attitudes to visual-tag-based applications were broadly positive, although they had several important reservations about camera-phone technology more generally. Data from our pointing-device task demonstrated that novice users were able to aim and click on visual-tags quickly (well under 3 s per pointing-device trial on average) and accurately (almost all meeting our defined speed/accuracy tradeoff of 6% error-rate). Based on our findings, design lessons for camera-phone and visual-tag applications are presented.

---

Mobile robot team forming for crystallization of proteins

The process of protein crystallization is explained using the theory of robotics, particularly path planning of mobile robots. Path planning is a procedure which specifies motion trajectories of multiple mobile robots to form a robotic team with a desired pattern. Since protein crystals consist of a large number of protein molecules which come together to form a 3D lattice of uniform structure, it is hypothesized that each protein behaves like a mobile robot and takes adequate path to form a robotic team (crystal). Based on this hypothesis, it is shown that trajectories of the proteins should be simple and local, which generates three rules of motion for the protein robots, i.e., (a) each protein searches for its nearest neighbor, (b) each protein takes the shortest path to approach the nearest neighbor, and (c) multiple proteins may form a sub-team of proteins. It is then proven mathematically that the planned path according to the three rules is stable and able to crystallize the proteins. Interaction forces at the molecular level are analyzed to show that the simple and local motion of the proteins is physically warranted. Computer simulation and experimental results are presented to validate the new theory.

The 2007 IEEE CEC simulated car racing competition

This paper describes the simulated car racing competition that was arranged as part of the 2007 IEEE Congress on Evolutionary Computation. Both the game that was used as the domain for the competition, the controllers submitted as entries to the competition and its results are presented. With this paper, we hope to provide some insight into the efficacy of various computational intelligence methods on a well-defined game task, as well as an example of one way of running a competition. In the process, we provide a set of reference results for those who wish to use the simplerace game to benchmark their own algorithms. The paper is co-authored by the organizers and participants of the competition.

---

Embedding new data points for manifold learning via coordinate propagation

In recent years, a series of manifold learning algorithms have been proposed for nonlinear dimensionality reduction. Most of them can run in a batch mode for a set of given data points, but lack a mechanism to deal with new data points. Here we propose an extension approach, i.e., mapping new data points into the previously learned manifold. The core idea of our approach is to propagate the known coordinates to each of the new data points. We first formulate this task as a quadratic programming, and then develop an iterative algorithm for coordinate propagation. Tangent space projection and smooth splines are used to yield an initial coordinate for each new data point, according to their local geometrical relations. Experimental results and applications to camera direction estimation and face pose estimation illustrate the validity of our approach.