Social Robotics

This paper presents a system for human-robot communication situated in an ambient assisted living scenario, where the robot performs an order-and-serve-procedure. The interaction is based on different modalities that extract information from the auditory and the visual channel in order to obtain an intuitive and natural dialog. The required interaction dialog structure is represented in first-order logic, which allows to split a complex task into simpler subtasks. The different communication modalities are utilized to conclude these subtasks by determining information about the human interaction partner. The system works in real-time and robust and utilizes emotional feedback to enrich the communication process.

The Pseudo Swarm Implementation aims to demonstrate the concept of swarm intelligence through the use of simulation and actual robotic units in hopes of recreating the complexity of natural systems. The actual swarm robots are modular in design and powered by PIC16f84 microprocessors. Each robot is composed of the motor module and a detachable sensor module. The motor module was constructed first and designed to handle basic movement and the random walk function. The sensor module was then designed afterwards which is capable of interfacing with the motor module through a universal protocol. The simulation platform was accomplished through the use of ActionScript3 to graphically depict the swarm behaviors given certain rules and a controlled environment. The simulation’s purpose is to complement the data by creating robot objects similar to the actual robots and reproducing a larger number of them in a given environment. This work is a comprehensive study on a variation of the of swarm intelligence implementation of how a complex system may be composed of simple units defined by basic state machines.

Human robot interaction (HRI) is core to the design of service robots. The interaction during a service application determines how a user perceives the robot, which affects the user’s experience and how well the user accepts the robot and its services. During the last decade, robotics service applications in close proximity to human users have been a popular research area. Research in related fields such as computer vision has also made significant advances to make available many interaction algorithms for HRI. However, we argue that there is only minimum utilization of these algorithms in the construction of HRI needed in actual service robots, despite their availability. This is partly because these algorithms have inherent limitations and only solve some of the HRI issues required in a complete service scenario in real environments. In this paper, a new general design approach is proposed to utilize modeling languages UML and UMLi to describe a service scenario and model the HRI required in a complete service. These models can be further used to elicit sometimes hidden HRI requirements from limitations in the interaction algorithms used. This approach helps multidisciplinary research to make HRI design decisions early at the design stage and guide implementation by software engineers. A user identification service scenario was designed, implemented and used as the case study of this design approach. It was integrated with a medication reminder application on a robot which was deployed and evaluated with the older people in a retirement village in New Zealand.

As social robotic research advances, robots are improving their abilities in Human-Robot Interaction and, therefore, becoming more human-friendly. While robots are beginning to interact more naturally with humans, new applications and possible uses of social robots are appearing. One of the future applications where robots will be used is entertainment. This paper presents a social robot as a development platform for which several robotic games have been developed. Five of these games are presented and how these games take benefit of the robot’s HRI abilities is detailed.

This paper concerns the development of a lightweight robotic platform which targets at flexibility, scalability, extensibility and environment for intelligence embedment. The platform employs layered architecture and event driven communication paradigm which allows for efficient integration of additional sensory input and actuator control. New intelligent algorithm can be encapsulated into plug-ins and lodged into the platform to leverage the robot intelligence and learning capability. A multi-purpose XML engine is introduced for the control of system communication, business logic, finite state machine execution and decision making. The proposed robotic platform was deployed on a number of robots in our laboratory such as coffee serving robot and receptionist robot. The results show that XRIA is flexible, manageable and works well for different types of robots with required operating performance.

In this paper we present the evaluation results of an exploratory study performed in an open environment with the robot receptionist Olivia. The main focus of the study was to analyze relationships between the robot’s social skills and the perceived overall interaction quality, as well as to determine additional important interaction quality features with potential general validity. Our results show positive correlations between the investigated factors, as the ability to socialize with humans achieved the second highest correlation with the perceived interaction quality. One of the most relevant functional aspects for the interaction quality was found to be the ability to respond fast. Performance abilities, such as speech or object recognition were, surprisingly, considered less important. The voice pleasantness was regarded as one of the most important non-functional aspects being ranked higher than a nice physical appearance.

Gestures play an important role in the communication of social robots. This paper presents an approach to simplify the upper body of the robot, proposing a method resulting in a smaller and cost-effective way of building robots which can perform gestures that are recognizable to humans. A reduced robot model of 10 Degrees of Freedom (DOF) is investigated and the human gestures are mapped directly onto the robots. Results from our user study show that the decrease in DOF does not critically affect human-like gesture motions to significantly affect the perceptions by the human observer. Specifically, some gestures have shown that participants make no mistake in interpreting the robot gestures, suggesting the possibility of its implementation on pre-programmed motion on robotic toys.

This paper reports on a children-dependent robotic approach to establish asynchronous child assistance with a social rapport network for the purpose of collecting trash from a public space. Our sociable trash box robot (STB) was unable to collect trash by itself. However, it did succeed in conveying its intentions to collect the trash from children. The main purpose of this study is to investigate the effective social cues, behaviors, and other essential factors to facilitate children in their anticipation of the behavior of a sociable trash box robot. The STB engages by using interactive social cues and vocal interactions to build a social coupling with children in order to induce their assistance in collecting trash. We discuss the minimalism designing mechanism of the STB, as well as the effectiveness of the above factors through an experiment which is conducted in a child-centric environment.

In this paper, we present the results of a pilot study of a human robot interaction experiment where the rhythm of the interaction is used as a reinforcement signal to learn sensorimotor associations. The algorithm uses breaks and variations in the rhythm at which the human is producing actions. The concept is based on the hypothesis that a constant rhythm is an intrinsic property of a positive interaction whereas a break reflects a negative event. Subjects from various backgrounds interacted with a NAO robot where they had to teach the robot to mirror their actions by learning the correct sensorimotor associations. The results show that in order for the rhythm to be a useful reinforcement signal, the subjects have to be convinced that the robot is an agent with which they can act naturally, using their voice and facial expressions as cues to help it understand the correct behaviour to learn. When the subjects do behave naturally, the rhythm and its variations truly reflects how well the interaction is going and helps the robot learn efficiently. These results mean that non-expert users can interact naturally and fruitfully with an autonomous robot if the interaction is believed to be natural, without any technical knowledge of the cognitive capacities of the robot.

This paper reports the docking and metaphor effects on persuasion among multi-robot healthcare systems. The goal of our research is to make a robot friend that lives with its users and persuades them to make appropriate healthcare decisions. To realize such a robot friend, we propose a physical approach called docking as well as a contextual approach called metaphor to perform relational inheritance among multi-robot systems. We implemented a multi-robot persuasion system based on the two approaches and verified its effectiveness. The experimental results revealed that users emphasize interpersonal relationships to decide whether to follow the robot’s advice when utilizing the metaphor approach, and that users emphasize robot aggressiveness when utilizing docking approach.

In a robot system, it is important to consider how the outside environment is expressed as a state using sensor information. In this study, we provide a state representation that can express the sensor output changed by environmental change as the same state. It assumes that sensor outputs are probability distributions, and the distances between the distributions of each sensor’s output are used to express a state. To confirm the effectiveness of the proposed state representation, we conducted experiments using a mobile robot. The results confirmed that the proposed representation could recognize similar states using a converted sensor output.

Autonomy is a prime issue on robotics field and it is closely related to decision making. Last researches on decision making for social robots are focused on imitating humans’ mind for taking decisions. Following this approach, we propose a motivational system for decision making using internal (drives) and external stimuli for choosing the right action. Actions will be selected from a finite set of skills in order to keep robot’s needs within an acceptable range.

We present how our motivational decision making is applied to a social robot showing an improvement in robot’s autonomy.

Intuitive learning of new behaviours is one of the important aspects of social robotics. Among various robot learning approaches, recently

Programming by Demonstration (PbD)

has gained significant recognition with a lot of potential. Internal representation of the knowledge is a key design choice in the learning process. Using machine learning techniques such as ANNs, HMMs and NARMAX models, simple skills can be encoded from raw sensory data. However, the abstract symbolic representations have demonstrated greater potential for learning complicated tasks but with less details and require a piece of prior knowledge as well. For a particular application, appropriate choice of the symbols is a key design issue. This paper discusses the choice of the symbols to build a PbD process for typical indoor navigation. The learning results are presented for a few tasks to demonstrate the potential of the proposed approach.

Robot games have been proposed as a way to motivate people to do physical exercises while playing. Although this area is very new, both commercial and scientific robot games have been developed mainly based on interaction with a single user and a robot. The goal of this paper is to describe a generic software framework which can be used to create games where multiple players can play against a mobile robot. The paper shows how an adaptive AI system (D2) developed for real-time strategy (RTS) computer games can be successfully applied in a robotics context using the robotics control framework Player/Stage. D2 is based on Case-Based Planning which learns from demonstration. Using the proposed framework, the paper shows how a robot learns a strategy for an implementation of a simple game.

This paper describes the state-of-the art of an elderly companion robot project, aimed towards the development of personal service robots for the elderly population. We propose a behavior adaptation method that reads interaction signals from the old people, and then adjust interaction output such as daily dialogues, news and whether broadcasting, motion speed and navigation-assist. The method uses detecting the user’s speech command, touch-screen input, head position and body posture as subconscious signals that indicate a user’s interaction preference. A study with the elderly companion robot that has six interaction behaviors has been conducted. The study result of 8 subjects preliminary suggests that the proposed mechanism enables adaptation to individual preferences.

In this paper we introduce a speech-based information system for a humanoid robot that is able to adapt its information presentation strategy to different brain patterns of its user. Brain patterns are classified from electroencephalographic (EEG) signals and correspond to situations of low and high mental workload. The robot selects an information presentation style that best matches the detected patterns. The complete system of recognition and adaptation is tested in an evaluation study with ten participants. We achieve a mean recognition rate of 80% and show that an adaptive information presentation strategy improves user satisfaction in comparison to static strategies.

In this paper, a human robot interface called mind robotic rehabilitation is developed for regular training of neurological rehabilitation for stroke patients. The mind robotic rehabilitation is developed based on non-invasive motor imagery brain computer interface (BCI) technology. The use of a spatial filtering algorithm, common spatial pattern (CSP), is proposed for extracting features that maximize the discrimination of two different brain states, left hand movement imagination and right hand movement imagination, during motor imagery of the subject. Furthermore, we find that a feature fusion of feature vectors from both CSP and autoregressive (AR) spectral analysis can obviously improve the performance of the BCI. Quadratic discriminant analysis (QDA) is applied to the combined feature vectors and classifies the vectors into left or right motor imagery category. For evaluation of the proposed BCI, we compare the performance of the proposed method against methods using single feature extraction algorithm, i.e. CSP only or AR spectral analysis only, under an equivalent experiment environment and using the same classifier to estimate the classification accuracy. It is found that feature fusion significantly improves BCI performance.

Aiming to overcome the serious disadvantages of two kinds of under-actuated fingers: coupled finger and self-adaptive finger, this paper proposed a novel grasping mode, called Coupled and Self-Adaptive (COSA) grasping mode, which includes 2 stages: firstly coupled and then self-adaptive grasping. A 2-joint COSA finger with double tendons mechanisms (called COSA-GRS finger), is designed based on the COSA grasping mode. The new finger unit has the advantages of coupled finger and self-adaptive fingers. Using the COSA finger, a humanoid multi-fingered hand can be designed. The new hand will be more similar to human hand in appearance and actions, able to more dexterously and stably grasp different objects than tradition coupled or self-adaptive under-actuated hands.

Gesture-changeable under-actuated (GCUA) function is presented to make robot hand grasp objects dexterously and achieve humanoid manipulations with low dependence on control system. Based on GUCA function, GCUA Hand II is developed, which has 5 fingers and 14 DOFs. All the fingers use similar tendon mechanisms to achieve GCUA function which includes traditional under-actuated (UA) grasping motion and special pre-bending (PB) motion. With GCUA Hand II, a humanoid robot upper limb system is developed, which has two 3-DOF arms actuated by stepper motors and two 14-DOF hands actuated by DC motors. The control system includes four parts: computer, motion controller based on FPGA, driver module, and user module, which can control the upper limb system to do various movements dexterously and exactly. The control system and spatial motion program are designed. This system has a great prospect in the field of robotics and rehabilitation engineering.

In state of the art robotics, high positioning accuracy is achieved by using solid and stiff components as well as powerful drives. But in the field of social robotics, for example humanoid robots, it is often not possible using this approach due to special boundary conditions like design-space, weight-limitations, power-storage and many more.By contrast human beings are able to achieve remarkable high positioning accuracy despite of low mass, low power consumption and relatively simple mechanics. One approach to obtain this accuracy is to temporarily create additional supporting structures by interacting with the direct environment, for example supporting the heel of the hand on a table for writing. This article deals with the essential idea of applying this method correspondingly into the field of robotics. Using different simulations the influence on stiffness and positioning accuracy is examined. It turned out that blocking of even one degree of freedom can lead to a significant improvement regarding stiffness and therefore positioning accuracy.

In this paper, two nonlinear control methods including adaptive learning control and adaptive robust control are designed for a robotic manipulator with time-varying uncertainties. We first present an adaptive learning control by incorporated learning control approaches into an adaptive control system to handle periodic uncertainties with known periods. We explore Lyapunov functional method to design the controller such that the convergence of tracking errors can be ensured. If the periods of uncertaines are unknown or uncertainties are non-periodic, an adaptive robust control is further designed to guarantee that the solution trajectory is finite and arbitrarily close to the desired trajectory by choosing design parameters in the controller. The efficacy of the proposed nonlinear controllers has been demonstrated in a two-link robot manipulator.

In this paper, motion synchronization control of bilateral tele-operation system is investigated. Compared with previous passivity framework, the communication delays are assumed to be time-varying. By feedback linearization, the nonlinear dynamics of the tele-operation system is transformed into two sub-systems: local master/slave position control and delayed motion synchronization. We propose new control strategies based on linear matrix inequalities (LMI) and adaptive parameters show that the master-slave tele-operation system is stable under specific LMI conditions. Finally, the simulations are performed to show the effectiveness of the proposed method.

Recently, a robot mediated therapy was given attention in support of the education and rehabilitation of children with autism. In this paper, we design and develop a robot assisted test-bed system, which provides efficient observations and analysis methods for children with autism during a free play session with robots. The test-bed system consists of a portable handheld device and a remote server. The handheld device helps a therapist to input and analyze observed results of children’s play, and the remote server stores recorded video and audio information using a database program. For the robot platforms for proposed test-bed system, we use animal-type devices, which are familiar and effective for children with autism. The observed interaction between the robot and children is transmitted in real-time to the remote server. Thereafter, if it is needed, this system can provide the therapist with analyzed monitoring information for further educational treatments. For the actual service trial of the proposed system, we have implemented a specialized kindergarten for children with autism and performed several experiments. Results show that the proposed test-bed system provides not only easy and quantitative observation methods, but also efficient analyses for monitoring positive interactions between children with autism and robot systems.

In this paper, we report the effectiveness of a therapeutic humanoid robot for children with autism to improve his/her imitation skill. In order to realize this system, a robot has to provide two functions: mimicking and evaluating the child’s motion in real time. The former function is achieved by selecting key frames using the Q-Learning approach to remove noisy camera data. The latter is established via a cluster-based framework on Mixture Gaussian and Expectation-Maximization algorithm using parameters which are converted by Principal Component Analysis. Practical experiments are shown in which autistic children interact with a robot and are trained by executing specific tasks for improving imitation skill.

The work presented in this paper is part of our investigation in the ROBOSKIN project. The paper presents the completion of the first phase towards skin-based robot assisted play that included a literature review, exploratory studies and building play scenarios. The review highlights aspects of the social and the sensory impairments of children with autism, and provides the background knowledge and context for developing tactile human-robot play scenarios that are appropriate to this specific user group. The paper reports on higher-level user requirements for skin based interaction for these children alongside their exploratory studies with the humanoid robot KASPAR. This is followed by the presentation of an initial play scenario that is based on turn taking and imitation games, together with the related educational and therapeutic objectives relevant for children with autism.

Social Robots are believed to have great potential for long term care. The uptake of Social Robots in daily care provision will depend on demonstrated added value of such systems in practice. To assess the added value, the availability of a technical system as such is insufficient. Interventions need to be defined describing the goal, target group, environment and how care staff should act to pursue effective application of a robot system. For the seal robot Paro three such interventions have been developed in collaboration with psycho-geriatric care professionals. The interventions provide information on the aims of PARO application in daily care for psycho-geriatric patients and describe concrete outcomes to monitor the added value of robot interventions. The developed interventions also outline the application of PARO in care for a subsequent randomized clinical trial (RCT).

Research tends to show a reduced playfulness in children with intellectual disabilities. This hampers engagement in play which in turn is a threat to participation in children’s most important occupation, potentially inhibiting health and well-being. The reported study evaluates short-term effects of the IROMEC robot toy supporting play in an occupational therapy intervention for children with intellectual disabilities. Three young children took part in this single-subject design study in which the robot intervention alternated with traditional toys guided by the responsible occupational therapists. Evaluation was performed through Test of Playfulness (ToP), the IROMEC evaluation questionnaire and qualitative evaluation by the therapists. Results indicated large differences within subject in ToP, gradually increasing IROMEC questionnaire scores, qualitative results indicated appreciation of the robot potential for therapists and children. Long term effect evaluation should verify these positive indications resulting from use of this innovative social robot for children with intellectual disabilities.

This research explores interactive games using hand and face tracking with a robot as a tool for autism therapy. The robot is equipped with a head and two arms, each with two degrees of freedom, and a camera. We trained a classifier to detect human hands and subsequently, used this classifier along with a standard face tracker to create two interactive games. In the first game the robot waits for the child to initiate an interaction by raising one or both hands. In the second game, the robot initiates interactions. These games are designed to increase attention, promote turn-taking skills and encourage child-led verbal and non-verbal communication through simple imitative play. This research makes two specific contributions: (1) We present a low-cost robot design which measures and adapts to a child’s actions during interactive games and, (2) we train and test a hand detector, based on Haar-like features, which is usable in various kinds of human-robot interactions.

This paper reviews theoretical perspectives and empirical evidence speaking in favor of a close link between action control and perceptual selection in humans. Results from behavioural studies, neuro-imaging, human electrophysiology as well as single-cell studies in monkeys are described. These data as well as theories are brought forward to argue that close connection between action and perception should be considered in designs of artificial systems. Examples of such systems are described and the application of those approaches to robotics is stressed.

This paper reports the application of results from human- social agent interaction experiments to inform the design of a social robot to monitor levels of pollutive gasses in the air. Next to licensed environmental agents and immobile chemical sensors, mobile technologies such as robotic agents are needed to collect complaints and smell descriptions from humans in urban industrial areas. These robots will interact with members of the public and ensure responsiveness and accuracy of responses. For robots to be accepted as representative environmental monitoring agents and for people to comply to robot instructions in the case of a calamity, social skills will be important. In this paper we will describe the intelligent environment the environmental robot is part of and discuss preliminary work on the effects of robot empathic and touch behaviors on human responses to robots. These and future findings will inform the design of social monitoring robot behaviors in public settings.

It is amazing that human beings can attend to the interest from a simple glimpse of scenes. Similarly, it is also important for social robots to determine its attention autonomously so as to behave human-likely and naturally. In this paper, we propose a technique to model this biological ability by searching saliency regions in a fast and reliable way. The salient regions are detected based on information entropy and biological color sensitivity. The information entropy evaluates the level of knowledge and energy contained, and the color sensitivity measures the biological stimulation to eyes of the presented scene. The performance of the detector is studied on natural scenes. The experiments proved the effectiveness of the detector and the important properties of invariance to transformation and illumination.

When interacting with robots we show a plethora of affective reactions typical of natural communications. Indeed, emotions are embedded on our communications and represent a predominant communication channel to convey relevant, high impact, information. In recent years more and more researchers have tried to exploit this channel for human robot (HRI) and human computer interactions (HCI). Two key abilities are needed for this purpose: the ability to display emotions and the ability to automatically recognize them. In this work we present our system for the computer based automatic recognition of emotions and the new results we obtained on a small dataset of quasi unconstrained emotional videos extracted from TV series and movies. The results are encouraging showing a recognition rate of about 74%.

This paper proposes a method to objectively assess the degree of sensory transfer in a visuo-tactile Sensory Substitution task. Using a special purpose single taxel-based device, users discover with tact some virtual objects of increasing geometrical complexity, while EEG signals are recorded. Successful reconstruction, as well as cognitive load and brain programming, are found to be associated with relative activation/deactivation of specific EEG bands, and to the users’ exploration strategies, which allows us to objectively assess the perceived degree of complexity of the reconstruction task. Our metrics also provide an evaluation tool for the design of devices useful for the navigation of visually impaired people.

Social interaction between humans takes place in the spatial dimension on a daily basis. We occupy space for ourselves and respect the dynamics of spaces that are occupied by others. In human-robot interaction, the focus has been on other topics so far. Therefore, this work applies a spatial model to a humanoid robot and implements an attention system that is connected to it. The resulting behaviors have been verified in an on-line video study. The questionnaire revealed that these behaviors are applicable and result in a robot that has been perceived as more interested in the human and shows its attention and intentions to a higher degree.

In this paper we explore the persuasive effects of social feedback provided by a robotic agent, on behavioral change. In lab experiments, participants had the opportunity to conserve energy while carrying out washing tasks with a simulated washing machine. Three experiments tested the effect of positive and negative social feedback and compared these effects to more widely used factual feedback. Results of these studies indicate that social feedback has stronger persuasive effects than factual feedback (Experiment 1) and factual-evaluative feedback (Experiment 2). In addition, an effect of feedback valence was found, demonstrating more conservation actions following negative feedback (social or factual) as compared to positive feedback. Interestingly, especially negative social feedback had the strongest persuasive effects (Experiment 1, 2, & 3), and task similarity enhanced the effects of negative feedback (Experiment 3). These findings have several implications for theory and design of persuasive robotic agents.

The interaction between human and robot is a critical issue for increasing the acceptance of robot as a companion in everyday life. Understanding the nature of communication pattern between human receptionists and visitors is essential in answering questions to facilitate the design of dialogue for a robot receptionist.

Methods:

A controlled observation which involved 6 receptionists and 10 visitors was carried out. Conversations between two parties were transcribed and coded with Interaction Process Analysis coding scheme, and keyword and dialog pattern were analyzed subsequently.

Results and Discussions:

Some frequently used terms and patterns of communication were found during the conversations. One of the key findings is the importance of differentiation of pragmatic and literal meanings of a statement in designing a dialogue for a robot receptionist. Suggested keywords could be used as a reference for similar statements while a robot receptionist is suggested to adopt some of the communication patterns found in the conversations.

Future Works:

Communications are typically complicated and this study can be served as a pilot in establishing a guideline for designing dialogues for robot receptionists.

There is a growing trend of social robots to move into the human environment. This research is set up to find the trends within social robotic designs. A sample of social robotic designs is drawn to investigate on whether there are more legged social robots than social robots with wheeled. In addition we investigate whether social robots use legs or wheels for locomotion, and which continent produces the most social robotic designs. The the results show that there are more legged robots, most robots use them for locomotion and Asia is the continent that produces most social robots. It can be concluded that there is a trend that social robots are more and more designed to have legs instead of wheels. Asia has more different social robotic designs to cater to different needs of human.

Synthetic skins with humanlike characteristics, such as a warm touch, may be able to ease the social stigma associated with the use of prosthetic hands by enabling the user to conceal its usage during social touching situations. Similarly for social robotics, artificial hands with a warm touch have the potential to provide touch that can give comfort and care for humans. With the aim of replicating the warmth of human skin, this paper describes (i) the experiments on obtaining the human skin temperature at the forearm, palm and finger, (ii) embedding and testing a flexible heating element on two types of synthetic skins and (iii) implementing a power control scheme using the pulse-width modulation to overcome the limitations of operating at different voltage levels and sources. Results show that the surface temperature of the human skin can be replicated on the synthetic skins.

Social robots need to recognize the objects indicated by people to work in real environments. This paper presents the entrainment of human pointing gestures during interaction with a robot and investigated what robot gestures are important for such entrainment. We conducted a Wizard-of-Oz experiment where a person and a robot referred to objects and evaluated the entrainment frequency. The frequency was lowest when the robot just used pointing gestures, and the frequency was highest when it used both gazing and pointing gestures. These result suggest that not only robot pointing gestures but also gazing gestures affect entrainment. We conclude that the entrainment of pointing gestures might improve a robot’s ability to recognize them.

In this paper will be presented an heterogeneous colony of robots capable to cooperate with people as effective partners to provide different kind of support among various working environments, such as museums, offices or trade fairs. Many systems have been integrated in order to develop robots capable to assists humans during the visit of the site, to guide them and to give information about the environment. According to the drama’s theory, each robot has a different character, something like a personality, so, each of them will interact with people in a different way. Robots show also emotional, non trivial, behaviours using an LSA conceptual space capable to synthesize the different emotional states that each robot can express.

This paper presents a novel approach of object detection and localization for service robots, which combines color-based and gradient-based detectors and automatically adapts the color model according to the variation of lighting conditions. Exploiting complementary visual features, the fusion of color-based and gradient-based detectors can achieve both robust detection and accurate localization. In real world environment, the color-based detection according to an offline-learned general model may fail. From a new linear color variation model proposed in this paper, our approach can generate a specific model for the target object in the image and achieve self-adaptation of color detector for robust detection and accurate localization. The experiments show that the proposed method can significantly increase the detection rate for target object in various real world environments.

Many robotic systems have been developed for assisting rehabilitating stroke patients. Their failure lies on the system design’s inability to motivate the patients to voluntarily conduct different activities that could stretch the impaired arm to its limit and help improve its condition. This paper presents the development of a robotic arm which allows the stroke patients’ active involvement in their rehabilitation through real-time biofeedback. It also evaluates the condition of the patients based on their performance and sends this feedback so therapists or doctors can monitor patients’ improvements. This project espoused a recommended strategy on patient motivation, that is, to embed therapy within the framework that provides patients with monitoring and interaction with therapists. Initiated for the needs of Filipino stroke patients, this paper presents its acceptability in the light of Filipino values.