Last posts on artificial intelligence

Researchers at Korea Advanced Institute of Science and Technology have developed a system for controlling physical robots using software robots, displayed as virtual-reality avatars.

Article

Simroid

2007-12-04T08:37:47+01:00

Simroid is a robotic dental patient designed by Kokoro Company Ltd as a training tool for dentists.

The simulated patient can follow spoken instructions, closely monitor a dentist’s performance during mock treatments, and react in a human-like way to mouth pain thanks to mouth sensors.

video

Japanese android recognizes and uses body language

2007-10-25T22:45:00+02:00

Japan’s National Institute of Information and Communications Technology (NICT) researchers have developed an autonomous humanoid robot that can recognize and use body language. According to the press release, the android can use nonverbal communication skills such as gestures and touch to facilitate natural interaction with humans. NICT researchers envision future applications of this technology in robots that can work in the home or assist with rescue operations when disaster strikes.

NICT press release (japanese)

NIPS 2007 WORKSHOP: Robotics Challenges for Machine Learning

2007-10-07T22:12:46+02:00

Via Neurobot

Dates: 7-8 December, 2007

Organizers:
Jan Peters (Max Planck Institute for Biological Cybernetics & USC), Marc Toussaint (Technical University of Berlin)

http://www.robot-learning.de
email: nips07@robot-learning.de

Abstract Submission Deadline: October 21, 2007
Acceptance Notification: October 26, 2007

Artificial brain falls for optical illusions

2007-10-01T22:15:29+02:00

Via New Scientist

A computer program that emulates the human brain falls for the same optical illusions humans do.

It suggests the illusions are a by-product of the way babies learn to filter their complex surroundings. Researchers say this means future robots must be susceptible to the same tricks as humans are in order to see as well as us.

For some time, scientists have believed one class of optical illusions result from the way the brain tries to disentangle the colour of an object and the way it is lit. An object may appear brighter or darker, either because of the shade of its colour, or because it is in bright light or shadows.

The brain learns how to tackle this through trial and error when we are babies, the theory goes. Mostly it gets it right, but occasionally a scene contradicts our previous experiences. The brain gets it wrong and we perceive an object lighter or darker than it really is – creating an illusion

Read full article

Japanese seniors bored with robot

2007-09-20T21:25:00+02:00

From Robot.net

According to a Reuters report, Japanese senior citizens quickly become bored with the simple robots so far introduced into nursing homes:

"The residents liked ifbot for about a month before they lost interest. Stuffed animals are more popular." Ifbot is a small robot that can converse, sing, express emotions, and even present trivia quizzes to senior citizens. According to the article the robot has spent most of the past year sitting in a corner, unused. Another robot, Hopis, that looked like a furry pink dog has gone out of production due to poor sales. Hopis was designed to monitor blood sugar, blood pressue, and body temperature. One problem may be that both robots are little more than advanced toys. Neither can help elderly people with day-to-day problems they face such as getting around their house, reading small print, or taking a bath. The elderly have found utilitarian improvements in existing devices more useful: height-adjustable countertops or extra-big control buttons on household gadgets. Whether seniors will find robots that can help with their utilitarian needs more to their liking than fluffy pupbots that sing remains to be seen"

EU researchers implanted an artificial cerebellum inside a robot

2007-09-16T22:39:08+02:00

Roland Piquepaille reports that "An international team of European researchers has implanted an artificial cerebellum - the portion of the brain that controls motor functions - inside a robotic system. This EU-funded project is dubbed SENSOPAC, an acronym for "SENSOrimotor structuring of perception and action for emerging cognition". One of the goals of this project is to design robots able to interact with humans in a natural way. This project, which should be completed at the end of 2009, also wants to produce robots which would act as home-helpers for disabled people, such as persons affected by neurological disorders, such as Parkinson's disease."

SENSOPAC website

Telepresence robot for interpersonal communication with the elderly

2007-09-13T22:32:02+02:00

Developing a Telepresence Robot for Interpersonal Communication with the Elderly in a Home Environment.

Telemed J E Health. 2007 Aug;13(4):407-424

Authors: Tsai TC, Hsu YL, Ma AI, King T, Wu CH

"Telepresence" is an interesting field that includes virtual reality implementations with human-system interfaces, communication technologies, and robotics. This paper describes the development of a telepresence robot called Telepresence Robot for Interpersonal Communication (TRIC) for the purpose of interpersonal communication with the elderly in a home environment. The main aim behind TRIC's development is to allow elderly populations to remain in their home environments, while loved ones and caregivers are able to maintain a higher level of communication and monitoring than via traditional methods. TRIC aims to be a low-cost, lightweight robot, which can be easily implemented in the home environment. Under this goal, decisions on the design elements included are discussed. In particular, the implementation of key autonomous behaviors in TRIC to increase the user's capability of projection of self and operation of the telepresence robot, in addition to increasing the interactive capability of the participant as a dialogist are emphasized. The technical development and integration of the modules in TRIC, as well as human factors considerations are then described. Preliminary functional tests show that new users were able to effectively navigate TRIC and easily locate visual targets. Finally the future developments of TRIC, especially the possibility of using TRIC for home tele-health monitoring and tele-homecare visits are discussed.

Halluc II: 8-legged robot vehicle

2007-07-26T19:05:00+02:00

http://www.epigenetic-robotics.org

Researchers at the Chiba Institute of Technology have developed a robotic vehicle with eight wheels and legs designed to drive or walk over rugged terrain. The agile robot, which the developers aim to put into practical use within the next five years, can move sideways, turn around in place and drive or walk over a wide range of obstacles.

The researchers hope the robot’s abilities will help out with rescue operations, and they would like to see Halluc II’s technology put to use in transportation for the mobility-impaired.

Here’s a short video of the model in action.

RunBot

2007-07-14T16:18:49+02:00

Via Medgadget

Researchers from Germany and the United Kingdom have developed a bipedal walking robot, capable of self-stabilizing via a highly-developed learning process.

From the study abstract:

In this study we present a planar biped robot, which uses the design principle of nested loops to combine the self-stabilizing properties of its biomechanical design with several levels of neuronal control. Specifically, we show how to adapt control by including online learning mechanisms based on simulated synaptic plasticity. This robot can walk with a high speed (>3.0 leg length/s), self-adapting to minor disturbances, and reacting in a robust way to abruptly induced gait changes. At the same time, it can learn walking on different terrains, requiring only few learning experiences. This study shows that the tight coupling of physical with neuronal control, guided by sensory feedback from the walking pattern itself, combined with synaptic learning may be a way forward to better understand and solve coordination problems in other complex motor tasks.

The paper: Adaptive, Fast Walking in a Biped Robot under Neuronal Control and Learning (Manoonpong P, Geng T, Kulvicius T, Porr B, Worgotter F (2007) Adaptive, Fast Walking in a Biped Robot under Neuronal Control and Learning. PLoS Comput Biol 3(7): e134)

Using a Robot to Teach Human Social Skills

2007-07-11T21:26:52+02:00

Via KurzweilAI

A humanoid robot designed to teach autistic children social skills has begun testing in British schools. Known as KASPAR (Kinesics and Synchronisation in Personal Assistant Robotics), the $4.33 million bot smiles, simulates surprise and sadness

Read full article

Epigenetic Robotics 2007 (Extended Deadline)

2007-07-06T16:16:28+02:00

Via NeuroBot

5-7 November 2007, Piscataway, NJ, USA

Seventh International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems

Email: epirob07@epigenetic-robotics.org

Location:
Rutgers, The State University of New Jersey,
Piscataway, NJ, USA

*Extended* Submission Deadline: 1 August 2007

First DARPA Limb Prototype

2007-04-29T18:59:31+02:00

From the DARPA press release

(via Medgadget)

An international team led by the Johns Hopkins University Applied Physics Laboratory (APL) in Laurel, Md., has developed a prototype of the first fully integrated prosthetic arm that can be controlled naturally, provide sensory feedback and allows for eight degrees of freedom--a level of control far beyond the current state of the art for prosthetic limbs. Proto 1, developed for the Defense Advanced Research Projects Agency (DARPA) Revolutionizing Prosthetics Program, is a complete limb system that also includes a virtual environment used for patient training, clinical configuration, and to record limb movements and control signals during clinical investigations.

The DARPA prosthetics program is an ambitious effort to provide the most advanced medical and rehabilitative technologies for military personnel injured in the line of duty. Over the last year, the APL-led Revolutionizing Prosthetics 2009 (RP 2009) team has worked to develop a prosthetic arm that will restore significant function and sensory perception of the natural limb. Proto 1 and its virtual environment system were delivered to DARPA ahead of schedule, and Proto 1 was fitted for clinical evaluations conducted by team partners at the Rehabilitation Institute of Chicago (RIC) in January and February.

"This progress represents the first major step in a very challenging program that spans four years and involves more than 30 partners, including government agencies, universities, and private firms from the United States, Europe, and Canada," says APL's Stuart Harshbarger, who leads the program. "The development of this first prototype within the first year of this program is a remarkable accomplishment by a highly talented and motivated team and serves as validation that we will be able to implement DARPA's vision to provide, by 2009, a mechanical arm that closely mimics the properties and sensory perception of a biological limb."

APL, which was responsible for much of the design and fabrication of Proto 1, and other team members are already hard at work on a second prototype, expected to be unveiled in late summer. It will have more than 25 degrees of freedom and the strength and speed of movement approaching the capabilities of the human limb, combined with more than 80 individual sensory elements for feedback of touch, temperature, and limb position.

"There is still significant work to be done to determine how best to control this number of degrees of freedom, and ultimately how to incorporate sensory feedback based on these sensory inputs within the human nervous system," Harshbarger says. "The APL team is already driving a virtual model of Proto 2 with data recorded during the clinical evaluation of Proto 1, and the team is working to identify a robust set of grasps that can be controlled by a second patient later this year."
Another exciting development is the functional demonstration of Injectable MyoElectric Sensor (IMES) devices--very small injectable or surgically implantable devices used to measure muscle activity at the source verses surface electrodes on the skin that were used during testing of the first prototype.

Evolution of visually guided behavior in artificial agents

2007-04-27T13:06:11+02:00

Evolution of visually guided behavior in artificial agents.

Network. 2007 Mar;18(1):11-34

Authors: Boots B, Nundy S, Purves D

Recent work on brightness, color, and form has suggested that human visual percepts represent the probable sources of retinal images rather than stimulus features as such. Here we investigate the plausibility of this empirical concept of vision by allowing autonomous agents to evolve in virtual environments based solely on the relative success of their behavior. The responses of evolved agents to visual stimuli indicate that fitness improves as the neural network control systems gradually incorporate the statistical relationship between projected images and behavior appropriate to the sources of the inherently ambiguous images. These results: (1) demonstrate the merits of a wholly empirical strategy of animal vision as a means of contending with the inverse optics problem; (2) argue that the information incorporated into biological visual processing circuitry is the relationship between images and their probable sources; and (3) suggest why human percepts do not map neatly onto physical reality.

Seventh International Conference on Epigenetic Robotics

2007-04-22T22:17:30+02:00

Seventh International Conference on Epigenetic Robotics: Modeling Cognitive Development in Robotic Systems

Call for Papers: Epigenetic Robotics 2007

5-7 November 2007, Piscataway, NJ, USA

Location: Rutgers, The State University of New Jersey, Piscataway, NJ, USA

MOBI

2007-04-11T23:05:33+02:00

From Networked Performance

MOBI (Mobile Operating Bi-directional Interface), by Graham Smith, is a human sized telepresence robot that users remotely control to move through distant environments, see through its camera eye, talk through its speakers and hear via its microphone ear. Simultaneously a life sized image of themselves is projected onto the robots LCD face, creating a robotic avatar. MOBI allows people to "explore far away art shows, attend distant presentations and make public appearences from anywhere on earth, thus helping to reduce air travel and reduce global warming". MOBI is at DEAF 07.

Graham Smith is a leading expert in the fields of telepresence, virtual reality, videoconferencing and robotics. He has worked with leading Canadian high tech companies for more than 14 years, including Nortel, Vivid Effects, VPL, BNR and IMAX. Graham initiated and headed the Virtual Reality Artist Access Program at the world-renowned McLuhan Program at the University of Toronto, and has lectured internationally. He holds numerous patents in the field of telepresence and panoramic imaging, and was recognized in Macleans magazine as one of the top 100 Canadians to watch.

Socially assistive robotics for post-stroke rehabilitation

2007-03-16T21:46:57+01:00

Journal of NeuroEngineering and Rehabilitation

Maja J Matari

Background: Although there is a great deal of success in rehabilitative robotics applied to patient recovery post stroke, most of the research to date has dealt with providing physical assistance. However, new rehabilitation studies support the theory that not all therapy need be hands-on. We describe a new area, called socially assistive robotics, that focuses on non-contact patient/user assistance. We demonstrate the approach with an implemented and tested post-stroke recovery robot and discuss its potential for effectiveness. Results: We describe a pilot study involving an autonomous assistive mobile robot that aids stroke patient rehabilitation by providing monitoring, encouragement, and reminders. The robot navigates autonomously, monitors the patient's arm activity, and helps the patient remember to follow a rehabilitation program. We also show preliminary results from a follow-up study that focused on the role of robot physical embodiment in a rehabilitation context. Conclusion: We outline and discuss future experimental designs and factors toward the development of effective socially assistive post-stroke rehabilitation robots.

Robot/computer-assisted motivating systems for personalized, home-based, stroke rehabilitation

2007-03-16T21:45:03+01:00

Journal of NeuroEngineering and Rehabilitation

Michelle J Johnson, Xin Feng, Laura M Johnson and Jack M Winters

Background: There is a need to improve semi-autonomous stroke therapy in home environments often characterized by low supervision of clinical experts and low extrinsic motivation. Our distributed device approach to this problem consists of an integrated suite of low-cost robotic/computer-assistive technologies driven by a novel universal access software framework called UniTherapy. Our design strategy for personalizing the therapy, providing extrinsic motivation and outcome assessment is presented and evaluated. Methods: Three studies were conducted to evaluate the potential of the suite. A conventional force-reflecting joystick, a modified joystick therapy platform (TheraJoy), and a steering wheel platform (TheraDrive) were tested separately with the UniTherapy software. Stroke subjects with hemiparesis and able-bodied subjects completed tracking activities with the devices in different positions. We quantify motor performance across subject groups and across device platforms and muscle activation across devices at two positions in the arm workspace. Results: Trends in the assessment metrics were consistent across devices with able-bodied and high functioning strokes subjects being significantly more accurate and quicker in their motor performance than low functioning subjects. Muscle activation patterns were different for shoulder and elbow across different devices and locations. Conclusion: The Robot/CAMR suite has potential for stroke rehabilitation. By manipulating hardware and software variables, we can create personalized therapy environments that engage patients, address their therapy need, and track their progress. A larger longitudinal study is still needed to evaluate these systems in under-supervised environments such as the home.

Grand challenges proposed by the U.K. Computing Research Committee

2007-02-25T12:18:42+01:00

Re-blogged from KurzweilAI.net

Grand challenges proposed by the U.K. Computing Research Committee include a project to unify cognitive science, artificial intelligence, and robotics.

One sign of success would be a robot capable of functioning at the level of a 2- to 5-year-old child. Another milestone could be a robot capable of autonomously helping a disabled person around a house without explicit preprogramming about its environment.

Other challenge is intended to create more dependable computers and associated software systems, which oversee the bulk of the world's financial transactions, regulate life-saving instruments, and manage the delivery of products.

Read Original Article>>

Cognitive robotics

2007-01-21T23:47:38+01:00

Via Mind Hacks

Memoirs of a Postgrad has an interesting analysis of cognitive robotics - the science of developing 'cognitive agents'

Research Positions in the Devlopment of Artificial Companions - Edinburgh

2007-01-15T23:25:36+01:00

Via Usability News

Deadine: 20 January 2007
Centre for interaction Design, Napier University, Edinburgh
Salary Level Research Associate (Grade IA)
£20,645 - £30,902 p.a. (dependent on experience)

Opportunities exist for talented individuals to join Napier University’s team, led by Professor David Benyon, to work on a €12 million EU funded project, COMPANIONS. This project concerns the development of persistent, intelligent agents that work with people to help carry out activities within digital space. Napier’s work focus is the interaction design of these companions.

An Interaction Designer is required to undertake field work, analysis, prototyping and evaluation of systems using a variety of media such as video and Flash animation. The Interaction Designer will be a creative individual who can contribute to the interface, functionality, affective characteristics and embodiment of the companions.

A Conceptual Modeller or software engineer is needed for the development of a meta-data schemata for the mark-up of behaviours, language processing and modality selection. This will result in a COMPANIONS mark-up language.

For either position, the successful applicant will require a higher degree (or significant industry experience) in human-centred computing or interaction design. She or he should have good writing, team working, creative and communication skills, and have experience with techniques appropriate to the position.

Part time or short term contract positions may also be available. In addition, two fully funded PhD studentships (worth approx. £12000 p.a.) may be associated with the project.

Informal inquiries should be directed to the COMPANIONS research fellow Dr Oli Mival, o.mival@napier.ac.uk. Full applications in the form of a CV and covering letter should be received by 20th January 2007, electronically to c.thomson@napier.ac.uk or by post to Cheryl Thomson, Faculty of Engineering, Computing and Creative Industries, Napier University, 10, Colinton road, Edinburgh EH14 1DJ.

Call for Articles for: Encyclopedia of Artificial Intelligence

2007-01-15T22:45:23+01:00

Via Neurodudes

From the call for articles

Editors: Juan R. Rabuñal, Julián Dorado & Alejandro Pazos

Nature has always been a source of inspiration for science problem solving. Areas such as Pharmacy, Physics or Aeronautics use biological concepts to reach beyond their current limits.

As far as Computing Science and - more specifically, Artificial Intelligence (AI) - is concerned, the use of biological concepts is highly reliable for achieving good results. At the early stages of AI (1950s), Artificial Neural Networks (ANN) - quite successful as classification and pattern recognition systems - were developed by using the structure of the nervous system as a basis. After these systems, biology has inspired the development of other techniques - among which the evolutionary systems are the most promising ones when dealing with new problems that use a vast amount of data - such as Biomedical Computing or weather forecasting.

Both the techniques based in cell or natural organisms performance, as well as those based on evolutionary theories, have a wide success record when applied to real problems. These types of techniques currently represent a very active area of research, as not only a high number of companies use them, but also many related high level scientific congresses are being held annually on these techniques.

Coverage
To meet this need, currently we are in the process of editing the "Encyclopedia of Artificial Intelligence " that will provide comprehensive coverage and definitions of the most important issues, concepts, trends and technologies in Artificial Intelligence. This important new publication will be distributed worldwide among academic and professional institutions and will be instrumental in providing researchers, scholars, students and professionals with access to the latest knowledge related to Artificial Intelligence techniques.

To ensure that this publication has the most current and relevant coverage of all topics related to Artificial Intelligence, we are asking sholars well-known for their particular area of research, to contribute short articles of 1,500-3,500 words on any of the following topics.

The University of Washington Neural Systems Lab have created a humanoid robot you can control with your thoughts.

2007-01-15T20:52:18+01:00

Via Mind Hacks

Researchers at the University of Washington Neural Systems Lab have created a humanoid robot you can control with your thoughts via a EEG-based non-invasive brain-computer interface.

Link to Neural Systems Lab robot info page

The euCognition network

2007-01-11T19:55:00+01:00

thx to Giuseppe Riva

The principal goal of the euCognition network is to leverage added-value from existing work through interaction and to use this to encourage further contributions from new participants. A key objective of the network is to foster interaction between all the many different scientific sectors involved in this multi-disciplinary area and to help create truly inter-disciplinary perspectives. The network activities will cover the four key issues of:

Outreach
Scientific Outlook
Education
On-line Resources for the Community

You can get a good idea of the goals of the network and the way it works from the euCognition website

Researchers Use Wikipedia To Make Computers Smarter

2007-01-10T21:55:00+01:00

Using Wikipedia, Technion researchers have developed a way to give computers knowledge of the world to help them "think smarter," making common sense and broad-based connections between topics just as the human mind does.

Scientists have designed and built an immersive table tennis simulation that allows a human to compete against a compute

2007-01-07T23:19:02+01:00

Scientists have designed and built an immersive table tennis simulation that allows a human to compete against a computer..

Evolved Virtual Creatures

2006-12-30T13:35:00+01:00

Via Suicide Bots

From the Evolved Virtual Creatures website

This video shows results from a research project involving simulated Darwinian evolutions of virtual block creatures. A population of several hundred creatures is created within a supercomputer, and each creature is tested for their ability to perform a given task, such the ability to swim in a simulated water environment. Those that are most successful survive, and their virtual genes containing coded instructions for their growth, are copied, combined, and mutated to make offspring for a new population. The new creatures are again tested, and some may be improvements on their parents. As this cycle of variation and selection continues, creatures with more and more successful behaviors can emerge.

The creatures shown are results from many independent simulations in which they were selected for swimming, walking, jumping, following, and competing for control of a green cube.

Download movie from the Internet Archive

swimming

Recent trends in robot-assisted therapy environments

2006-12-22T00:13:09+01:00

Recent trends in robot-assisted therapy environments to improve real-life functional performance of affected limbs.

J Neuroengineering Rehabil. 2006 Dec 18;3(1):29

Authors: Johnson MJ

ABSTRACT: Upper and lower limb robotic tools for neuro-rehabilitation are effective in reducing motor impairment but they are limited in their ability to improve real world function. There is a need to improve functional outcomes after robot-assisted therapy. Improvements in the effectiveness of these environments may be achieved by incorporating into their design and control strategies important elements key to inducing motor learning and cerebral plasticity such as mass-practice, feedback, task-engagement, and complex problem solving. This special issue presents nine articles. The novel strategies covered in this issue encourage more natural movements through the use of virtual reality and real objects and faster motor learning through the use of error feedback to guide acquisition of natural movements that are salient to real activities. In addition, several articles describe novel systems and techniques that use of custom and commercial games combined with new low-cost robot systems and a humanoid robot to embody the supervisory presence of the therapy as possible solutions to exercise compliance in under-supervised environments such as the home.

A Smarter Computer to Pick Stocks

2006-11-28T23:41:40+01:00

Wall Street is adopting nonlinear decision making processes akin to how a brain operates, including neural networks, and genetic algorithms, and other advanced computer-science techniques.

Black Starfish

2006-11-22T08:50:36+01:00

Via the Neurophilosopher

Josh Bongard, Victor Zykov and Hod Limpton of Cornell University’s Computational Synthesis Laboratory have designed and built the Black Starfish, a four-legged robot which “automatically synthesizes a predictive model of its own topology (where and how its body parts are connected) through limited yet self-directed interaction with its environment, and then uses this model to synthesize successful new locomotive behavior before and after damage.”

Iris recognition technology for mobile phones

2006-11-06T23:23:43+01:00

Re-blogged from Pink Tentacle

Oki Electric announced the development of iris recognition technology for camera-equipped mobile phones. Unlike Oki’s previous iris recognition technology that relies on infrared cameras for the iris scan, the new technology uses ordinary cellphone cameras. With plans to make the technology commercially available in March 2007, Oki hopes to boost the security of cellphone payment systems. According to Oki, any camera-equipped cellphone or PDA can perform iris recognition once the special software is installed. Identification accuracy is said to be high, with only 1 in 100,000 scans resulting in error, and the system can tell the difference between flesh-and-blood eyes and photographs.

HAL

2006-11-01T22:20:00+01:00

Via Engadget

HAL (short for Hybrid Assistive Limb) is a robotic suite designed "to expand and improve physical capabilities of human being".

The system, a brainchild of Yoshiyuki Sankai, engineering professor at Tsukuba University, is getting ready for mass production, Engadget reports. The robotic suite could be used in applications such as "walking assistance and rehabilitation, nursing, factory work and disaster relief."

HAL is originally developed to help elderly or disabled people walk around with their own legs and HAL-3 achieved the primary goal in 2000.
In 2005, the latest model HAL-5 was given upper body limbs as well as weight saving and more compact POWER units, longer life battery and much smaller control unit and spectacularly designed outer shells.

HAL is a robot suit which can expand and improve physical capabilities of human being. By wearing HAL-5 and you can hold up to 40 kg load by arms and can increase the maximum weight of leg press from 100 kg to 180 kg.

Vision-body link tested in robot experiments

2006-10-30T14:46:26+01:00

Re-blogged from KurzweilAI.net

"Embodied cognition" experiments involving real and simulated robots suggest that the relationship between physical movement and sensory input could be crucial to developing more intelligent machines...

Read the full article

PaPeRo Robot Childcare In Japan

2006-10-27T22:02:13+02:00

Via Technovelgy

NEC and NTT have jointly produced PaPeRo (short for Partner-type Personal Robot), the latest of a series of domestic robots. PaPeRo uses a camera in each eye to navigate and has image recognition capabilities to track and identify individual children. Further, it is equipped with a mobile phone that allows parents to control him at distance, as well as to talk to children directly or with text messages

Vision-body link tested in robot experiments

2006-10-27T22:01:23+02:00

Via New Scientist Tech

Tests involving real and simulated robots suggest the relationship between physical movement and sensory input could be crucial to create smarter machines...

Read the full story

Japan to invest US$17.4 million in robotics research

2006-10-02T11:00:00+02:00

Japan’s Ministry of Economy, Trade and Industry (METI) will invest over 2 billion yen (US$17.4 million) to support the development of intelligent robots that rely on their own decision-making skills in the workplace.

The objective of METI’s robot budget is to support the development of key artificial intelligence technology for robots over the next 5 years, with the goal of introducing intelligent robots to the market by 2015.

Robots for ageing society

2006-09-18T14:20:00+02:00

The CIRT consortium, composed by Tokyo University and a group of 7 companies (Toyota, Olympus, Sega, Toppan Printing, Fujitsu, Matsushita, and Mitsubishi), has started a project to develop robotic assistants for Japan’s aging population.

The robots envisioned by the project should support the elderly with housework and serve as personal transportation capable of replacing the automobile.

The Ministry of Education, Culture, Sports, Science and Technology (MEXT) will be the major sponsor of the research, whose total cost is expected to be about 1 billion yen (US$9 million) per year.

Post-doc position in Neural Information Processing available at Ulm University (Germany)

2006-08-21T13:05:00+02:00

From the Neuro-IT mailing list

The Department of Neural Information Processing at the University of Ulm invites applications for a post-doc (or PhD student) position to begin November 1 2006, or later.

The Institute for Neural Information Processing at the University of Ulm (Germany) has two full professors, 4 postdocs and about 12 students and researchers in different areas of neural network research. Ongoing work includes mobile autonomous robots, computer vision, neural modelling, and pattern recognition.

Successful applicants will be expected to conduct research involving:

- pattern recognition or sensor fusion with artificial neural networks, or
- information processing in networks of spiking neurons, or
-large associative memory systems with possible applications in autonomous vehicles, bioinformatics, medicine, speech or vision, or modelling and recognition of emotions.

Post-doc candidates should have a recent PhD-degree for example in computer science, physics, mathematics or electrical engineering.

They will have some small teaching obligations, so some knowledge of German would be useful.

Applications for PhD-work are also possible. In this case the applicants should already have some experience in one of the fields mentioned above.

The appointment will be for at least 2 years. Salary will be BAT IIa (details depend on age and family status).

See for application details http://www.informatik.uni-ulm.de/neuro/

The Talented Mr. Ripley

2006-08-08T14:07:49+02:00

Via Thinking Meat

Ripley is a robot designed by Deb Roy of the Cognitive Machines Group at MIT's Media Lab.

This robot was designed for learning about the environment by moving and touching objects in it. The underlying theoretical framework is the "Grounded Situation Model". In this approach, developed by Deb Roy and his colleague Nikolaos Mavridis, "the robot updates beliefs about its physical environment and body, based on a mixture of linguistic, visual and proprioceptive evidence. It can answer basic questions about the present or past and also perform actions through verbal interaction".

This story on NPR reports about the project, and includes an interview with Deb Roy.

From the MIT's Media Lab website

We have constructed a 7 degree-of-freedom robot, Ripley, to investigate connections between natural language semantics, perception, and action. Our goal is to enable Ripley to perform collaborative manipulation tasks mediated by natural spoken dialogue. Key issues include representation and learning of spatial language, object and temporal reference, and physical actions / verbs. Furthermore, a "Grounded Situation Model" representation has been designed for Ripley, as well as associated processes, and a cognitive architecture was implemented through numerous intercommunicating modules.

Links to Ripley video clips (from the MIT Media Lab website):

Ripley imagines and remembers [high resolution (12M) | low resolution (440K)]

Ripley tracks faces [high resolution (6M) | low resolution (280K)]

Ripley imagines objects [high resolution (13.5M) | low resolution (826k)]

Ripley grasping objects [high resolution (201M) | low resolution (23M)]

Ripley changing perspectives [.mov, 17M)]

Training HMM model to pick up [.mov, 844K)]

HMM model generating pick up [.mov, 791K)]

e-CIRCUS

2006-08-05T11:48:54+02:00

Via Science Daily

The project e-Circus (Education through Characters with emotional Intelligence and Role-playing Capabilities that Understand Social interaction) aims to develop synthetic characters that interact with pupils in a virtual school, to support social and emotional learning in the real classroom. This will be achieved through virtual role-play with synthetic characters that establish credible and empathic relations with the learners.

The project consortium, which is funded under the EU 6th Framework Program, includes researchers from computer science, education and psychology from the UK, Portugal, Italy and Germany. Teachers and pupils will be included in the development of the software as well as a framework for using it in the classroom context. The e-Circus software will be tested in schools in the UK and Germany in 2007, evaluating not only the acceptance of the application among teachers and pupils but also whether the approach, as an innovative part of the curriculum, actually helps to reduce bullying in schools.

Virtual bots teach each other

2006-08-03T21:11:57+02:00

From New Scientist Tech

"Robots that teach one another new words through interaction with their surroundings have been demonstrated by UK researchers. The robots, created by Angelo Cangelosi and colleagues at Plymouth University, UK, currently exist only as computer simulations. But the researchers say their novel method of communication could someday help real-life robots cooperate when faced with a new challenge. They could also help linguists understand how human languages develop, they say..."

Continue to read the full article on New Scientist

Watch the video

The Huggable

2006-08-02T12:05:00+02:00

Via Siggraph2006 Emerging Technology website

The Huggable is a robotic pet developed by MIT researchers for therapy applications in children's hospitals and nursing homes, where pets are not always available. The robotic teddy has full-body sensate skin and smooth, quiet voice coil actuators that is able to relate to people through touch. Further features include "temperature, electric field, and force sensors which it uses to sense the interactions that people have with it. This information is then processed for its affective content, such as, for example, whether the Huggable is being petted, tickled, or patted; the bear then responds appropriately".

The Huggable has been unveiled at the Siggraph2006 conference in Boston. From the conference website:

Enhanced Life
Over the past few years, the Robotic Life Group at the MIT Media Lab has been developing "sensitive skin" and novel actuator technologies in addition to our artificial-intelligence research. The Huggable combines these technologies in a portable robotic platform that is specifically designed to leave the lab and move to healthcare applications.

Goals
The ultimate goal of this project is to evaluate the Huggable's usefulness as a therapy for those who have limited or no access to companion-animal therapy. In collaboration with nurses, doctors, and staff, the technology will soon be applied in pilot studies at hospitals and nursing homes. By combining Huggable's data-collection capabilities with its sensing and behavior, it may be possible to determine early onset of a person's behavior change or detect the onset of depression. The Huggable may also improve day-to-day life for those who may spend many hours in a nursing home alone staring out a window, and, like companion-animal therapy, it could increase their interaction with other people in the facility.

Innovations
The core technical innovation is the "sensitive skin" technology, which consists of temperature, electric-field, and force sensors all over the surface of the robot. Unlike other robotic applications where the sense of touch is concerned with manipulation or obstacle avoidance, the sense of touch in the Huggable is used to determine the affective content of the tactile interaction. The Huggable's algorithms can distinguish petting, tickling, scratching, slapping, and poking, among other types of tactile interactions. By combining the sense of touch with other sensors, the Huggable detects where a person is in relation to itself and responds with relational touch behaviors such as nuzzling.

Most robotic companions use geared DC motors, which are noisy and easily damaged. The Huggable uses custom voice-coil actuators, which provide soft, quiet, and smooth motion. Most importantly, if the Huggable encounters a person when it tries to move, there is no risk of injury to the person.

Another core technical innovation is the Huggable' combination of 802.11g networking with a robotic companion. This allows the Huggable to be much more than a fun, interactive robot. It can send live video and data about the person's interactions to the nursing staff. In this mode, the Huggable functions as a team member working with the nursing home or hospital staff and the patient or resident to promote the Huggable owner's overall health.

Vision
As poorly staffed nursing homes and hospitals become larger and more overcrowded, new methods must be invented to improve the daily lives of patients or residents. The Huggable is one of these technological innovations. Its ability to gather information and share it with the nursing staff can detect problems and report emergencies. The information can also be stored for later analysis by, for example, researchers who are studying pet therapy.

The speed of sight

2006-07-29T20:45:00+02:00

Via Medgadget

According to estimates by University of Pennsylvania researchers, information transmission of the human retina is as fast as a regular Ethernet connection:

Using an intact retina from a guinea pig, the researchers recorded spikes of electrical impulses from ganglion cells using a miniature multi-electrode array. The investigators calculate that the human retina can transmit data at roughly 10 million bits per second. By comparison, an Ethernet can transmit information between computers at speeds of 10 to 100 million bits per second...
The guinea pig retina was placed in a dish and then presented with movies containing four types of biological motion, for example a salamander swimming in a tank to represent an object-motion stimulus. After recording electrical spikes on an array of electrodes, the researchers classified each cell into one of two broad classes: "brisk" or "sluggish," so named because of their speed.

The researchers found that the electrical spike patterns differed between cell types. For example, the larger, brisk cells fired many spikes per second and their response was highly reproducible. In contrast, the smaller, sluggish cells fired fewer spikes per second and their responses were less reproducible.

But, what's the relationship between these spikes and information being sent? "It's the combinations and patterns of spikes that are sending the information. The patterns have various meanings," says co-author Vijay Balasubramanian, PhD, Professor of Physics at Penn. "We quantify the patterns and work out how much information they convey, measured in bits per second."

Calculating the proportions of each cell type in the retina, the team estimated that about 100,000 guinea pig ganglion cells transmit about 875,000 bits of information per second. Because sluggish cells are more numerous, they account for most of the information. With about 1,000,000 ganglion cells, the human retina would transmit data at roughly the rate of an Ethernet connection, or 10 million bits per second.

Read the press release

Robot Doppelgänger

2006-07-24T21:05:00+02:00

Hiroshi Ishiguro, director of the Intelligent Robotics Lab at Osaka University in Japan, has created a robot clone of himself. The robot, dubbed “Geminoid HI-1”, looks and moves exactly like him, and sometimes takes his place in meetings and classes.

Link to Wired article on Ishiguro's android double.

BACS project

2006-07-19T20:14:04+02:00

BACS (Bayesian Approach to Cognitive Systems), is an Integrated Project under the 6th Framework Program of the European Commission which has been allocated EUR 7.5 million in funding.

The BACS project brings together researchers and commercial companies working on artificial perception systems potentially capable of dealing with complex tasks in everyday settings.

From the project's website:

Contemporary robots and other cognitive artifacts are not yet ready to autonomously operate in complex real world environments. One of the major reasons for this failure in creating cognitive situated systems is the difficulty in the handling of incomplete knowledge and uncertainty.

By taking up inspiration from the brains of mammals, including humans, the BACS project will investigate and apply Bayesian models and approaches in order to develop artificial cognitive systems that can carry out complex tasks in real world environments. The Bayesian approach will be used to model different levels of brain function within a coherent framework, from neural functions up to complex behaviors. The Bayesian models will be validated and adapted as necessary according to neuro-physiological data from rats and humans and through psychophysical experiments on humans. The Bayesian approach will also be used to develop four artificial cognitive systems concerned with (i) autonomous navigation, (ii) multi-modal perception and reconstruction of the environment, (iii) semantic facial motion tracking, and (iv) human body motion recognition and behavior analysis. The conducted research shall result in a consistent Bayesian framework offering enhanced tools for probabilistic reasoning in complex real world situations. The performance will be demonstrated through its applications to driver assistant systems and 3D mapping, both very complex real world tasks.

Computers learn common sense

2006-07-17T23:49:39+02:00

Via The Engineer, July 11, 2006

BBN Technologies has been awarded $5.5 million in funding from the Defense Advanced Research Projects Agency (DARPA) for the first phase of "Integrated Learner," which will learn plans or processes after being shown a single example.

The goal is to combine specialised domain knowledge with common sense knowledge to create a reasoning system that learns as well as a person and can be applied to a variety of complex tasks. Such a system will significantly expand the kinds of tasks that a computer can learn.

Read the full article

Rheo Knee

2006-06-18T18:12:10+02:00

MIT's Media Lab researchers have developed a prosthetic "Rheo Knee" that uses AI to replicate the workings of a biological human joint and "bio-hybrids," surgical implants that allow an amputee to control an artificial leg by thinking..