The PDA used in this application is the iPAQ 3850 pocket PC. It is provided with a StrongARM 32-bit RISC processor working at 260 MHz, eith 64Mb of RAM. It communicates with the robot via serial interface. A Flycam-CF camera is connected to the iPAQ via a Compact Flash Memory card slot, through the pocket PC expansion Pack.
CONVERSAY and ELAN software development kits (SDKs) provide speech recognition and speech synthesis of spoken English. Vision and speech processing are performed by the pocket PC.
The operating system (OS) and development tools used for our applications are Microsoft Pocket PC 2002, and embedded Visual C++. The SDKs used for speech recognition, speech synthesis and camera data acquisition are available only for PocketPC 2002 OS. Transition of our application to free OS such as Linux will be considered when more open source codes will be available for speech processing and camera data acquisition for PDAs.
Robota is a mini humanoid robot of 5 degrees of freedom. It is 45 cm high, for a weight of about 1500gr. It has five maxon-A DC motor with clutch to drive its two legs, two arms and head, 5 associated potentiometers, as well as 6 switches. Robota’s motors are driven by a PIC 16F84A microcontroller. The PocketPC interfaces the motor and sensor cards via RS232 serial connection. Motor and sensor cards are interfaced through SPI protocol.
The Robota project aims at developing an educational high-tech toy that exploits multi-modal means of human-robot interaction, such as speech and vision.
Blog about Robotics Introduction, news of the robot, information about the robot, sharing knowledge about the various kinds of robots, shared an article about robots, and others associated with the robot
Robot’s Languages Acquisition Using PocketPC
The developing a language learning game for the iPAQ 3850 PocketPC, in this application, the robot can learn, through a simple imitation game, a vocabulary to describe its body features and its perception of external objects. A built-in imitation module allows the robot to imitate the user motion of the arm and the face. The robot associates the user’s vocal utterance with visual perceptions of movement with the motor commands execution during the imitation.
Social interactions have structure that can be exploited to simplify the implementation of the language acquisition game. It has implemented two fundamental means of human social interaction: imitation and turn taking. Imitation is an attentional mechanism. Through the imitation game, the user can force the robot to go to through a specific set of perceptions. The imitation game is used by the teacher, e.g. to lead the robot to perceive the action of lifting up the arm or to watch a specific of object by looking in a specific direction. The imitation game focuses the robot’s attention on the relevant visual features, reducing importantly the amount of storage required for visual representation, and, therefore, increasing the speed of learning.
Turn taking allows clearing separating the act of learning and the act of repeating. In the architecture of the application, the learning phase, during the robot whish imitates the user and acquire knowledge, and the retrieval phase, during which the robot reproduces what it has learned, are clearly separated. The two key-sentences “Listen!” and “Try it now!” are used to switch the robot’s controller into either the learning mode or the rehearsal mode, respectively.
Social interactions have structure that can be exploited to simplify the implementation of the language acquisition game. It has implemented two fundamental means of human social interaction: imitation and turn taking. Imitation is an attentional mechanism. Through the imitation game, the user can force the robot to go to through a specific set of perceptions. The imitation game is used by the teacher, e.g. to lead the robot to perceive the action of lifting up the arm or to watch a specific of object by looking in a specific direction. The imitation game focuses the robot’s attention on the relevant visual features, reducing importantly the amount of storage required for visual representation, and, therefore, increasing the speed of learning.
Turn taking allows clearing separating the act of learning and the act of repeating. In the architecture of the application, the learning phase, during the robot whish imitates the user and acquire knowledge, and the retrieval phase, during which the robot reproduces what it has learned, are clearly separated. The two key-sentences “Listen!” and “Try it now!” are used to switch the robot’s controller into either the learning mode or the rehearsal mode, respectively.
Control Architecture of the Robota
Speech Module
Speech module sentences and the word from the speech stream are extracted by the CONVERSARY Automatic Speech Recognition (ASR) engine, using pre-programmed syntactic rules. The syntax is described as a set of rules. Multiple sentences can then describe same meaning. In the system only the subset of keywords are kept for further processing by the learning module. For example, when the user says “This is your face”, the ASR detects the use of an indexed grammar. In the present example, the grammar, encoded by the programmer, specifies that “This is your” is always followed by a noun, here “face”. Among the list of nouns that the ASR programmed to recognize, the word “face” is in this example is keyword that is extracted and processed for learning. The advantage of the syntax definition instead of a list of sentences is that the description is shorter, use less computational power, and can generalize sentences. The user then can omit unimportant words without perturbing the system.
Vision Module
The vision module of Robota grabs images of the upper part of the user’s body, including the head, arms, and shoulders. It tracks the vertical movements of both arms and the horizontal movements or rotation of the head. Tracking of the arms is based on luminosity and optical flow detection. The luminosity is extracted from the pixels RGB color intensity.
Speech module sentences and the word from the speech stream are extracted by the CONVERSARY Automatic Speech Recognition (ASR) engine, using pre-programmed syntactic rules. The syntax is described as a set of rules. Multiple sentences can then describe same meaning. In the system only the subset of keywords are kept for further processing by the learning module. For example, when the user says “This is your face”, the ASR detects the use of an indexed grammar. In the present example, the grammar, encoded by the programmer, specifies that “This is your” is always followed by a noun, here “face”. Among the list of nouns that the ASR programmed to recognize, the word “face” is in this example is keyword that is extracted and processed for learning. The advantage of the syntax definition instead of a list of sentences is that the description is shorter, use less computational power, and can generalize sentences. The user then can omit unimportant words without perturbing the system.
Vision Module
The vision module of Robota grabs images of the upper part of the user’s body, including the head, arms, and shoulders. It tracks the vertical movements of both arms and the horizontal movements or rotation of the head. Tracking of the arms is based on luminosity and optical flow detection. The luminosity is extracted from the pixels RGB color intensity.
Robot Probo for Medical Therapy in Hospitals
Recently more robots are being created to interact with human beings in order to satisfy certain social needs. From this point of view it has been developed a social robot named Probo, intended to comfort and emotionally interact with hospitalized children. The robot will be employed in the hospital, as a tele-interface for entertainment, communication and medical assistance. Therefore it requires the ability to express emotions, in order to do so, an emotional interface is developed to fully configure the display of emotions. The emotions, represented as a vector in an emotion space, are mapped to the degrees of freedom used in the robot. A 3D virtual model is created, providing realistic visual feedback to evaluate the design choices for the facial expressions.
The name Probo is derived from the word Proboscidea, the order containing only one family of living animals. The main aspects are a huggable appearance, an attractive trunk or proboscis, and an interactive belly-screen. The internal mechanics of the robot will be covered with foam and a removable fur-jacket.
The development of the Probo is to bring some solutions to the problems and special needs of hospitalized children. A hospitalization has a serious physical and mental influence, particularly on children.
In medical applications, Animal Assisted Therapy (AAT) and Animal Assisted Activity are becoming commonly used in hospitals. AAT and AAA are expected to have useful psychological, physiological and social effects. Therefore the use of robots instead of animals has more advantages and has a better chance to be allowed in hospitals. Recently pet robots are utilized just for these purposes, Termed Robot-Assisted Therapy (RAT).
The name Probo is derived from the word Proboscidea, the order containing only one family of living animals. The main aspects are a huggable appearance, an attractive trunk or proboscis, and an interactive belly-screen. The internal mechanics of the robot will be covered with foam and a removable fur-jacket.
The development of the Probo is to bring some solutions to the problems and special needs of hospitalized children. A hospitalization has a serious physical and mental influence, particularly on children.
In medical applications, Animal Assisted Therapy (AAT) and Animal Assisted Activity are becoming commonly used in hospitals. AAT and AAA are expected to have useful psychological, physiological and social effects. Therefore the use of robots instead of animals has more advantages and has a better chance to be allowed in hospitals. Recently pet robots are utilized just for these purposes, Termed Robot-Assisted Therapy (RAT).
A Tele-Interface of Robot Probo
Robot Probo can be employed as a tele-interface focusing on entertainment, communication and medical assistance. A touch screen in the v=belly of the robot creates a window to the outside world and opens up a way to implement new and existing computer applications.
Entertainment
Young children have a need for distraction and entertainment, providing them with a robotic user interface (RUI) will extend the possibilities of interactive game playing and include the capability of emotional feedback.
Communication
Hospitalized children are sometimes placed in a social isolated environment, strongly reducing the communication with friends and family. The robot can function as the perfect interface to contact other using standard videoconferencing techniques. The eyes of the robot will house the cameras, whereas the screen in the belly will display the image, resulting in the possibility to do interactive video communication.
Medical Assistance
The robot interface can be used by medical staff to make the children easy about medical routines or operation by providing appropriate information via their pal Probo. Probo can accompany the child to comfort it during difficult medical procedures. To unknown environment will be first explored and exanimations. By using predefine scenarios with pictures, video and sound Probo. Can pre-experience, by using its emotions, the medical routine together with the child fear,
Entertainment
Young children have a need for distraction and entertainment, providing them with a robotic user interface (RUI) will extend the possibilities of interactive game playing and include the capability of emotional feedback.
Communication
Hospitalized children are sometimes placed in a social isolated environment, strongly reducing the communication with friends and family. The robot can function as the perfect interface to contact other using standard videoconferencing techniques. The eyes of the robot will house the cameras, whereas the screen in the belly will display the image, resulting in the possibility to do interactive video communication.
Medical Assistance
The robot interface can be used by medical staff to make the children easy about medical routines or operation by providing appropriate information via their pal Probo. Probo can accompany the child to comfort it during difficult medical procedures. To unknown environment will be first explored and exanimations. By using predefine scenarios with pictures, video and sound Probo. Can pre-experience, by using its emotions, the medical routine together with the child fear,
The Robotics Revolution Constantly Changing
The state of robotic is constantly changing, but there is one barrier that will continue to impede its success if not addressed. For most commercial robots, only the “technically elite” are currently able to create the robot control policies they want, while the rest of the population must make do using the built-in policies (such as those on the iRobot Roomba, Wow Wee Robotic line of Robosapiens) included by the robot’s creators. Through lifelong robot learning, the aim to provide users of consumer robot technologies with a medium for transforming desired behavior into robot control policies. Specifically, given the same situational awareness, a robot should make a decision similar to the one the creator of the policy would make. While several paradigms exist for such policy transfer, it remains confronted by a human robot divide.
This divide refers to the disparity between the needs and ideas of users in society, the population with a diverse set of technical abilities and creative design sensibilities, and their ability to instantiate robot control to meet their desired ends. If a personal robotic revolution is to come, similar to that of personal computing, there will need to exist applications that will make new forms of personal expression tangible, enhance personal productivity, and put this technology into the hand of users (analogues to the spreadsheets, web authoring, 3D virtual world, etc on the PC).
This divide refers to the disparity between the needs and ideas of users in society, the population with a diverse set of technical abilities and creative design sensibilities, and their ability to instantiate robot control to meet their desired ends. If a personal robotic revolution is to come, similar to that of personal computing, there will need to exist applications that will make new forms of personal expression tangible, enhance personal productivity, and put this technology into the hand of users (analogues to the spreadsheets, web authoring, 3D virtual world, etc on the PC).
Wii Remote Robot of Nintendo
Released in December 2006, the Nintendo Wii Remote (Wiimote) is an inertial control interface for videogames that is fundamentally different from traditional gamepad/keyboard/mouse devices. The primary innovation of the Wiimote is its ability to localize itself within 2 rotational and 3 translational degrees of freedom. This localization is performed with a reasonable degree of accuracy which is well complemented by the Wiimote’s economical feasibility and compelling aesthetic. Rotational localization occurs with the help of three inertial sensors (accelerometers/gravimeters) that measure the direction of gravity along roll, pitch and yaw axes.
Translational localization is performed through triangulation against infrared light (IR) emitted an external “sensor bar”. The IR is sensed by the Wiimote through a built-in IR-sensitive chip. In addition, a Wiimote can receive input from 12 traditional gamepad buttons that can be used in complement with its localization.
The Wiimote communicates with other devices using the Bluetooth wireless communication. There are certain events that cause the Wiimote to send a packet of updated state information to its connected device. Those events include button presses, button releases, changes in the data from the accelerometers or the IR sensor, and changes in Wiimote extension devices. The Nunchuk is one such extension. It physically connects to the Wiimote and adds a second set of 3 accelerometers along with 2 trigger-style buttons and an analog joystick. This combined Wiimote/Nunchuk interface allows for two-handed user input.
Translational localization is performed through triangulation against infrared light (IR) emitted an external “sensor bar”. The IR is sensed by the Wiimote through a built-in IR-sensitive chip. In addition, a Wiimote can receive input from 12 traditional gamepad buttons that can be used in complement with its localization.
The Wiimote communicates with other devices using the Bluetooth wireless communication. There are certain events that cause the Wiimote to send a packet of updated state information to its connected device. Those events include button presses, button releases, changes in the data from the accelerometers or the IR sensor, and changes in Wiimote extension devices. The Nunchuk is one such extension. It physically connects to the Wiimote and adds a second set of 3 accelerometers along with 2 trigger-style buttons and an analog joystick. This combined Wiimote/Nunchuk interface allows for two-handed user input.
Subscribe to:
Posts (Atom)
