Caterpillars Inspire New Movements in Soft Robots

Some caterpillars have the extraordinary ability to rapidly curl themselves into a wheel and propel themselves away from predators. This highly dynamic process, called ballistic rolling, is one of the fastest wheeling behaviours in nature.

Researchers from Tufts University, Massachusetts, saw this as an opportunity to design a robot that mimics this behaviour of caterpillars and to develop a better understanding of the mechanics behind ballistic rolling.

The study, published on April 27, in IOP Publishing's journalBioinspiration& Biomimetics, also includes a video of both the caterpillar and robot in action and can be found athttp://www.youtube.com/watch?v=wZe9qWi-LUo.

To simulate the movement of a caterpillar, the researchers designed a 10cm long soft-bodied robot, called GoQBot, made out of silicone rubber and actuated by embedded shape memory alloy coils. It was named GoQBot as it forms a"Q" shape before rolling away at over half a meter per second.

The GoQBot was designed to specifically replicate the functional morphologies of a caterpillar, and was fitted with 5 infrared emitters along its side to allow motion tracking using one of the latest high speed 3D tracking systems. Simultaneously, a force plate measured the detailed ground forces as the robot pushed off into a ballistic roll.

In order to change its body conformation so quickly, in less than 100 ms, GoQBot benefits from a significant degree of mechanical coordination in ballistic rolling. Researchers believe such coordination is mediated by the nonlinear muscle coupling in the animals.

The researchers were also able to explain why caterpillars don't use the ballistic roll more often as a default mode of transport; despite its impressive performance, ballistic rolling is only effective on smooth surfaces, demands a large amount of power, and often ends unpredictably.

Not only did the study provide an insight into the fascinating escape system of a caterpillar, it also put forward a new locomotor strategy which could be used in future robot development.

Many modern robots are modelled after snakes, worms and caterpillars for their talents in crawling and climbing into difficult spaces. However, the limbless bodies severely reduce the speeds of the robots in the opening. On the other hand, there are many robots that employ a rolling motion in order to travel with speed and efficiency, but they struggle to gain access to difficult spaces.

Lead author Huai-Ti Lin from the Department of Biology, Tufts University, said:"GoQBot demonstrates a solution by reconfiguring its body and could therefore enhance several robotic applications such as urban rescue, building inspection, and environmental monitoring."

"Due to the increased speed and range, limbless crawling robots with ballistic rolling capability could be deployed more generally at a disaster site such as a tsunami aftermath. The robot can wheel to a debris field and wiggle into the danger for us."

Source

Wii Key to Helping Kids Balance

The Rice engineering students created the new device using components of the popular Nintendo game system to create a balance training system.

What the kids may see as a fun video game is really a sophisticated way to help them advance their skills. The Wii Balance Boards lined up between handrails will encourage patients age 6 to 18 to practice their balance skills in an electronic gaming environment. The active handrails, which provide feedback on how heavily patients depend on their arms, are a unique feature.

Many of the children targeted for this project have cerebral palsy, spina bifida or amputations. Using the relatively inexpensive game console components improves the potential of this system to become a cost-effective addition to physical therapy departments in the future.

Steven Irby, an engineer at Shriners' Motion Analysis Laboratory, pitched the idea to Rice's engineering mentors after the success of last year's Trek Tracker project, a computer-controlled camera system for gait analysis that was developed by engineering students at Rice's Oshman Engineering Design Kitchen (OEDK).

The engineering seniors who chose to tackle this year's new project -- Michelle Pyle, Drew Berger and Matt Jones, aka Team Equiliberators -- hope to have the system up and running at Shriners Hospital before they graduate next month.

"He (Irby) wants to get kids to practice certain tasks in their games, such as standing still, then taking a couple of steps and being able to balance, which is pretty difficult for some of them," Pyle said."The last task is being able to take a couple of steps and then turn around."

"This isn't a measurement device as much as it is a game," Irby said."But putting the two systems together is what makes it unique. The Wii system is not well suited to kids with significant balance problems; they can't play it. So we're making something that is more adaptable to them."

The game requires patients to shoot approaching monsters by hitting particular spots with their feet as they step along the Wii array, computer science student Jesus Cortez, one of the game's creators, explained. The game gets harder as the patients improve, he said, and the chance to rack up points gives them an incentive.

A further step, not yet implemented, would be to program feedback from the handrails into the game. Leaning on the rails would subtract points from the users' scores, encouraging them to improve their postures. The game would also present challenges specific to younger and older children to keep them engaged.

The programming team also includes undergraduate Irina Patrikeeva and graduate student Nick Zhu. Studio arts undergraduate Jennifer Humphreys created the artwork.

The system's components include a PC, the Wii boards (aligned in a frame) and two balance beam-like handrails that read how much force patients are putting on their hands. Communications to the PC are handled via the Wii's native Bluetooth protocol.

The students said their prototype cost far less than the$2,000 they'd budgeted. Rice supplied the computer equipment and LabVIEW software they needed to create the diagnostic software that interfaces with Shriners' existing systems, and they purchased the Wii Balance Boards on eBay.

"Small force plates that people commonly use for such measurements cost at least a couple of grand, but Wii boards -- and people have done research on this -- give you a pretty good readout of your center of balance for what they cost," Pyle said.

Jones, who is building the final unit for delivery to Shriners, said he wants patients to see the Wii boards."We're putting clear acrylic over the boards so there aren't any gaps that could trip up the younger ones," he said."We wanted to use a device that's familiar to them, but they might not be convinced it's a Wii board unless they can see it."

Source

Artificial Intelligence for Improving Data Processing

Within this framework, five leading scientists presented the latest advances in their research work on different aspects of AI. The speakers tackled issues ranging from the more theoretical such as algorithms capable of solving combinatorial problems to robots that can reason about emotions, systems that use vision to monitor activities, and automated players that learn how to win in a given situation."Inviting speakers from groups of references allows us to offer a panoramic view of the main problems and the techniques open in the area, including advances in video and multi-sensor systems, task planning, automated learning, games, and artificial consciousness or reasoning," the experts noted.

The participants from the AVIRES (The Artificial Vision and Real Time Systems) research group at the University of Udine gave a seminar on the introduction of data fusion techniques and distributed artificial vision. In particular, they dealt with automated surveillance systems with visual sensor networks, from basic techniques for image processing and object recognition to Bayesian reasoning for understanding activities and automated learning and data fusion to make high performance system. Dr.Simon Lucas, professor at the Essex University and editor in chief of IEEE Transactions on Computational Intelligence and AI in Games and a researcher focusing on the application of AI techniques on games, presented the latest trends in generation algorithms for game strategies. During his presentation, he pointed out the strength of UC3M in this area, citing its victory in two of the competitions held at the international level during the most recent edition of the Conference on Computational Intelligence and Games.

In addition, Enrico Giunchiglia, professor at the University of Genoa and former president of the Council of the International Conference on Automated Planning and Scheduling (ICAPS), described the most recent work in the area of logic satisfaction, which is rapidly growing due to its applications in circuit design and in task planning

Artificial Intelligence (IA) is as old as computer science and has generated ideas, techniques and applications that permit it to solve difficult problems. The field is very active and offers solutions to very diverse sectors. The number of industrial applications that have an AI technique is very high, and from the scientific point of view, there are many specialized journals and congresses. Furthermore, new lines of research are constantly being open and there is a still great room for improvement in knowledge transfer between researchers and industry. These are some of the main ideas gathered at the 4th International Seminar on New Issues on Artificial Intelligence), organized by the SCALAB group in the UC3M Computer Engineering Department at the Leganés campus of this Madrid university.

The future of Artificial Intelligence

This seminar also included a talk on the promising future of AI."The tremendous surge in the number of devices capable of capturing and processing information, together with the growth of the computing capacity and the advances in algorithms enormously boost the possibilities for practical application," the researchers from the SCALAB group pointed out. Among them we can cite the construction of computer programs that make life easier, which take decisions in complex environments or which allow problems to be solved in environments which are difficult to access for people," he noted. From the point of view of these research trends, more and more emphasis is being placed on developing systems capable of learning and demonstrating intelligent behavior without being tied to replicating a human model.

AI will allow advances in the development of systems capable of automatically understanding a situation and its context with the use of sensor data and information systems as well as establishing plans of action, from support applications to decision making within dynamic situations. According to the researchers, this is due to the rapid advances and the availability of sensor technology which provides a continuous flow of data about the environment, information that must be dealt with appropriately in a node of data fusion and information. Likewise, the development of sophisticated techniques for task planning allow plans of action to be composed, executed, checked for correct execution, and rectified in case of some failure, and finally to learn from mistakes made.

This technology has allowed a wide range of applications such as integrated systems for surveillance, monitoring and detecting anomalies, activity recognition, teleassistence systems, transport logistic planning, etc. According to Antonio Chella, Full Professor at the University of Palermo and expert in Artificial Consciousness, the future of AI will imply discovering a new meaning of the word"intelligence." Until now, it has been equated with automated reasoning in software systems, but in the future AI will tackle more daring concepts such as the incarnation of intelligence in robots, as well as emotions, and above all consciousness.

Source

Technique for Letting Brain Talk to Computers Now Tunes in Speech

In a new study, scientists from Washington University demonstrated that humans can control a cursor on a computer screen using words spoken out loud and in their head, holding huge applications for patients who may have lost their speech through brain injury or disabled patients with limited movement.

By directly connecting the patient's brain to a computer, the researchers showed that the computer could be controlled with up to 90% accuracy even when no prior training was given.

Patients with a temporary surgical implant have used regions of the brain that control speech to"talk" to a computer for the first time, manipulating a cursor on a computer screen simply by saying or thinking of a particular sound.

"There are many directions we could take this, including development of technology to restore communication for patients who have lost speech due to brain injury or damage to their vocal cords or airway," says author Eric C. Leuthardt, MD, of Washington University School of Medicine in St. Louis.

Scientists have typically programmed the temporary implants, known as brain-computer interfaces, to detect activity in the brain's motor networks, which control muscle movements.

"That makes sense when you're trying to use these devices to restore lost mobility -- the user can potentially engage the implant to move a robotic arm through the same brain areas he or she once used to move an arm disabled by injury," says Leuthardt, assistant professor of neurosurgery, of biomedical engineering and of neurobiology,"But that has the potential to be inefficient for restoration of a loss of communication."

Patients might be able to learn to think about moving their arms in a particular way to say hello via a computer speaker, Leuthardt explains. But it would be much easier if they could say hello by using the same brain areas they once engaged to use their own voices.

The research appears April 7 inThe Journal of Neural Engineering.

The devices under study are temporarily installed directly on the surface of the brain in epilepsy patients. Surgeons like Leuthardt use them to identify the source of persistent, medication-resistant seizures and map those regions for surgical removal. Researchers hope one day to install the implants permanently to restore capabilities lost to injury and disease.

Leuthardt and his colleagues have recently revealed that the implants can be used to analyze the frequency of brain wave activity, allowing them to make finer distinctions about what the brain is doing. For the new study, Leuthardt and others applied this technique to detect when patients say or think of four sounds:

• oo, as in few
• e, as in see
• a, as in say
• a, as in hat

When scientists identified the brainwave patterns that represented these sounds and programmed the interface to recognize them, patients could quickly learn to control a computer cursor by thinking or saying the appropriate sound.

In the future, interfaces could be tuned to listen to just speech networks or both motor and speech networks, Leuthardt says. As an example, he suggests that it might one day be possible to let a disabled patient both use his or her motor regions to control a cursor on a computer screen and imagine saying"click" when he or she wants to click on the screen.

"We can distinguish both spoken sounds and the patient imagining saying a sound, so that means we are truly starting to read the language of thought," he says."This is one of the earliest examples, to a very, very small extent, of what is called 'reading minds' -- detecting what people are saying to themselves in their internal dialogue."

"We want to see if we can not just detect when you're saying dog, tree, tool or some other word, but also learn what the pure idea of that looks like in your mind," he says."It's exciting and a little scary to think of reading minds, but it has incredible potential for people who can't communicate or are suffering from other disabilities."

The next step, which Leuthardt and his colleagues are working on, is to find ways to distinguish what they call"higher levels of conceptual information."

The study identified that speech intentions can be acquired through a site that is less than a centimetre wide which would require only a small insertion into the brain. This would greatly reduce the risk of a surgical procedure.

Source

Device Enables Computer to Identify Whether User Is Male or Female

The Spanish Patent and Trademark Office has awarded the Universidad Politécnica de Madrid and the Universidad Rey Juan Carlos Spanish patent ES 2 339 100 B2 for the device.

Thanks to the new algorithm, devices can be built to measure television or advertising video audiences by gathering demographic information about spectators (dynamic marketing). The new device is also useful for conducting market research at shopping centres, stores, banks or any other business using cameras to count people and extract demographic information. Another application is interactive kiosks with a virtual vendor, as the device automatically extracts information about the user, such as the person's gender, to improve interaction.

A step forward in gender recognition from facial images

This research, the results of which were published in IEEE Transactions on Pattern Analysis and Machine Intelligence, demonstrates that linear techniques are just as good as support vector machines (SVM) for the gender recognition problem. The developed technique is applicable in devices that have low computational resources, like telephones or intelligent cameras.

The study concludes that linear methods are useful for training with databases that contain a small number of images, as well as for outputting gender classifiers that are as fast as boosting-based classifiers. However, boosting- or SVM-based methods will require more training images to get good results. Finally, SVM-based classifiers are the slowest option. Additionally, the experimental evidence suggests that there is a dependency among different demographic variables like gender, age or ethnicity.

Device for demographic face classification

The invention is a device equipped with a camera that captures digital images and is connected to an image processing system. The image processing system trims each face detection image to the size of 25x25 pixels. An elliptical mask (designed to eliminate background interference) is then applied to the image, and it is equalized and classified.

The device advances the state of the art by using a classifier based on the most efficient linear classification methods: principal component analysis (PCA), followed by Fisher's linear discriminant analysis (LDA) using a Bayesian classifier in the small dimensional space output by the LDA. For PCA+LDA to be competitive, the crucial step is to select the most discriminant PCA features before performing LDA.

One of the major research areas in informatics is the development of machines that interact with users in the same way as human beings communicate with each other. This research is a step further in this direction.

Source