Recent Posts

Pages: 1 ... 8 9 [10]
General AI Discussion / Re: image detection at different brightness
« Last post by Don Patrick on February 14, 2017, 01:48:29 PM »
If you convert the RGB values to HSV values (Hue-Saturation-Brightness), you can compare the hue and saturation values of the pixels and ignore the brightness.
Robotics News / ENRICH will test robots in real world radiological and nuclear scenarios
« Last post by Tyler on February 14, 2017, 10:48:27 AM »
ENRICH will test robots in real world radiological and nuclear scenarios
13 February 2017, 4:32 pm

The Zwentendorf Nuclear Power Plant in Austria was completely built but never put into operation. Reactor supervision and decommissioning is one important operational area for robots in the RN domain. There is significant potential for the use of unmanned vehicles in scenarios involving radiological and nuclear (RN) threats. The European Reference Network for Critical Infrastructure Protection (ERNCIP) has therefore established a thematic group on the protection of critical infrastructure from Radiological and Nuclear Threats (RNTs).

The group looks at issues such as standardisation of deployment protocols, response procedures and the use of unmanned systems. Possible threats involve measurement and sampling scenarios that are too risky for humans to carry out, also in the event of criminal or unauthorised acts involving nuclear or other radioactive material. Situations envisaged for the use of unmanned ground vehicles (UGV) are:

  • Reactor supervision and related accidents, such as Chernobyl and Fukushima;
  • Illicit release of radioactive material (radiological dispersion devices and dirty bombs before or after an explosion);
  • Search of sources out of regulatory control;
  • Long-term measurements.
Lessons learned from incidents such as Fukushima and Chernobyl, as well as from decommissioning of old nuclear power plants, show that robots have certain advantages. Robots can operate in areas with high radiation, danger of explosives, for example Boiling Liquid Expanding Vapour Explosions (BLEVE), collapsing structures, Improvised Explosive Devices (IED), booby traps, aggressive chemicals (e.g. Chlortrifluorid) and extreme heat. Additionally, they can manipulate the environment and take samples. Robots can also be used for long-time surveillance of contaminated areas and for monitoring the movements of a threat using real-time data from mobile sensors.

Robotics in the RN domain – applications and standards The ERNCIP RNTs group focusses on possible applications. The identified scenarios can be separated in two categories. First, there are prevention scenarios where unmanned systems can be used to prevent incidents involving radioactive material and deterrence. Second, there are response scenarios where unmanned systems gather information after incidents with radioactive material occurred. We further identified several tasks for unmanned systems:

  • spatial mapping of RN sensor data (exploration, change detection);
  • searching for RN sources (active sensing, isocurves, hotspots);
  • sampling (air, sweep or material sampling);
  • 3D infrastructure mapping (situation awareness & assessment).
Possible applications for robots in the RN domain: taking samples of potentially hazardous materials (left) or measuring and searching for radiological and nuclear sources (right). Another important finding was that no standards, best practices or norms for sampling or taking measurements with unmanned systems have been systematically developed thus far. Therefore, a first set of potential standards for unmanned systems in RN measurement scenarios was compiled. A widely accepted standard collection of frameworks for robot software development is the Robot Operating System (ROS). Further important standards concerning communication with robots and control of unmanned systems are the Battle Management Language (BML), InterOperability Profile (IOP) and Joint Architecture for Unmanned Systems (JAUS). Furthermore, there are efforts for standardisation in the International Electrotechnical Commission (IEC) regarding international standards for RN measurements with unmanned systems.

Trials and competitions – great way to raise interest in RN related robotics The results of the ENRCIP RNTs group pointed to an inherent need for a practical element shaping and enforcing the standardisation process in the robotics community. Unfortunately, it was also obvious that there is currently little to none interest of the academic robotics community in the RN field. There is, however, an effective means to address large robotic communities: the field of robotic competitions. Since robots usable in RN scenarios most probably have to be outdoor/off-road systems, the RNT group, thus, decided to set up an RN scenario at a popular outdoor robotics competition.

The group also identified a huge gap between what the R&D community is able to deliver, the existing industry state of the art and the user requirements (if properly determined). This includes the complete absence, non-observance or non-compliance of standards, best practices and norms. Naturally, the R&D community does not have a focus on standardisation, manageability, sustainability, robustness or reliability. Again, robotic competitions can be used as method to bring together users, academia and industry. The users can visualise their needs in the form of real world scenarios to be tackled by the R&D community and industry. At the same time, the industry is able to mingle with the R&D community. Thus, a constructive way to push forward unmanned systems in RN scenarios might be the utilisation of trials and challenges.

The European Land Robot Trial 2016 took place in Eggendorf, Austria. For the first time, a RN task with real radiation sources was included and attracted robot teams from all over the world. In 2016, the European Land Robot Trial (ELROB) was hosted by the Austrian Army in the Tritolwerk in Eggendorf. The Tritolwerk is an old ordnance factory, now used for CBRNE training and training for emergency services. These premises gave the perfect setting for a very special scenario: Reconnoitring of urban structures with a focus on radiological and nuclear measuring and mapping. This was the first real world live scenario with strong radiation sources (Co60, 2,8GBq each) on a robotics competition ever! The task involved detecting an unknown number of hidden radiation sources. The robotic systems had to measure the radiation, display measurements to the operator, acquire imagery and mark the sources in an online-built map representation. Ten teams participated in the scenario. Since this was the first try of such a scenario, the expectations were curbed. However, the teams performed reasonably well, and most presented RN readings. It turned out that many teams did not have enough background knowledge on radiation detection to produce suitable results.

European Robotics Hackathon – fully focused on RN tasks Based on these circumstances a new robotic trial, the first European Robotics Hackathon (EnRicH) was created and will take place in June 2017. The scenario at EnRicH is inspired by the radiological reconnaissance task at ELROB 2016 and has a similar setting, indoor search for radiation sources and 3D mapping, but with an additional manipulation task. The event will be accompanied by a R&D workshop which is planned and conducted by the ERNCIP RNTs task group. The workshop has a focus on standards for unmanned systems in the RN field of application. The EnRicH hackathon will take place in the inoperative nuclear power plant (NPP) in Zwentendorf, Austria. The boiling water reactor of NPP Zwentendorf has been fully completed but never put into operation. In Zwentendorf areas are easily accessible which in other NPPs can only be visited under severe difficulties. In an active nuclear power plant extensive safety precautions are needed for human personnel due to the high level of radioactivity. Instead, in the NPP Zwentendorf engineers have transformed the plant and turbine halls into a training centre. Repair and dismantling measures but also critical incidents and disaster scenarios can be trained under realistic conditions.

Naturally, a nuclear power plant contains areas which cannot be safely entered by human personnel on one hand, due to inherent radiation like in the reactor building, and on the other hand due to technical problems or accidents leading to an unpredictable and uncontrolled radioactive contamination of parts of the plant. In any case, a robotic system doing an exploration of the scene would be helpful. This is the basic setting for the newly created European Robotics Hackathon.

In EnRicH, the exploration task consists of three sub-tasks: first, a digital 3D map of the area of interest has to be built; second, radiation and its sources must be detected, measured and marked inside a digital map; and, third, if a system is equipped with a manipulator device, some radioactive material has to be handled. All collected information has to be passed on to a reach back team for further evaluation.

The interior of the Zwentendorf Nuclear Power Plant provides the setting for the first European Robotics Hackathon (EnRicH). Robots will have to build a conventional 3D map of the scene, measure and map radiation sources, and manipulate hazardous material. During the trial, major challenges are waiting for the participating systems and teams: First, severe mobility problems are caused by the typical interior of a power plant with elements like low or no light, closed doors, dead ends and blockings, sharp turns or steep stairs. Second, major difficulties for any kind of communication approach can be expected due to massive concrete walls and metal interiors. However, as a fall-back solution the organizers provide a standard wireless communication infrastructure for the teams. And, finally, due to the active radiation sources inside the scenario nobody will be allowed to accompany the robots, making robustness an essential prerequisite for the systems. However, the scene will be equipped with cameras, allowing some basic supervision for the operators from outside.

Hence, the problems of robots in hazardous operations and emergency response, especially when involving RN components, are diverse. Trials like ELROB and EnRicH reveal many remaining technical challenges, such as communication, sensors, situational awareness, mobility/locomotion and robustness, which often accrue from the fact that these systems have not been used and tested enough. There are still a lot of lessons to be learned.

If you liked this article, you may also be interested in:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Source: Robohub

To visit any links mentioned please view the original article, the link is at the top of this post.
General AI Discussion / Re: image detection at different brightness
« Last post by yotamarker on February 14, 2017, 05:52:20 AM »
what 20 things ? link please
Robotics News / Robotic cleaning market growing exponentially
« Last post by Tyler on February 14, 2017, 04:50:44 AM »
Robotic cleaning market growing exponentially
13 February 2017, 10:43 am

iRobot Braava jet 240. Source: The International Federation of Robotics forecast that the global market for vacuum cleaning robots, lawn-mowing robots and other household cleaning robots will grow at a compound annual growth rate (CAGR) of 33% through 2019. Other research reports say the market will reach $2.5 billion by 2020 at a CAGR of 15%.

iRobot America’s biggest provider, iRobot, in their earnings disclosure delivered this week, reported very strong sales in the United States; 2016 sales were up more than 35% over a record 2015. Total units shipped in fiscal 2015 were 2,436,000 compared to 2,174,000 units in fiscal 2014. International shipments in 2015 represented 10.77% of revenue but increased only 1.5% over 2014. No unit data was released for fiscal 2016.

iRobot’s stock steadily doubled over the 12 months although it took a $7 dive on the date of the earnings report.

The increase in domestic home robots revenue was primarily attributable to increased sales as a result of significant investments in advertising media and national promotions as well as the launch of Roomba 980. International home robots revenue growth slowed compared to fiscal 2014 as a result of negative macroeconomic conditions, specifically in Japan and Russia, offset by a significant growth increase in China.
iRobot is eyeing Asia for growth and recently launched a $290 Braava jet mopping robot customized for China. iRobot has also acquired the iRobot related distribution business of privately-held Sales On Demand Corporation (SODC) based in Tokyo, Japan. The acquisition, which is expected to close in April 2017, will enable iRobot to get closer to Japanese consumers and retail partners, and thus allow the company to better address Japanese market needs.

The Chinese market Mother’s Day, Father’s Day and, in China, Singles Day are big shopping holidays. Singles Day is held on November 11th (11/11). [November 11 was chosen for the annual holiday because no other date has as many 1’s, or “singles”.] On that date in 2016 Ecovacs popular robot vacuum Deebot outsold TVs to emerge as the top-selling home electronic appliance on Tmall, a business-to-customer platform of Alibaba, the online sales network. Ecovacs reported that their online sales exceeded $47 million which equates to approximately 188,000 units.

David Qian, who is in charge of Ecovacs’ international business, said: “After decades of development, the household robot industry is, in fact, still in its infancy. Future domestic robots will become multifunctional. Just cleaning floors will be not enough.”

“China’s swelling middle class has a rising demand for domestic cleaning, home security and surveillance robots,” said Luo Jun, CEO of the Asian Manufacturing Association. “Robots can make doing housework interesting and cool,” said Liu De, co-founder and vice-president of Xiaomi.
As a consequence, both domestic and foreign enterprises are scrambling to participate in the market. Chinese home appliance firms such as Haier Group and TCL Corp are eyeing the market with similar products, making the market increasingly crowded. Chinese smartphone vendor Xiaomi Corp launched a smart vacuum cleaner last September. Priced at $246, the machine is equipped with 12 sensors and a central processing unit. Instead of bouncing around the room and haphazardly picking up debris, Xiaomi said it can automatically measure the size of the room and map the best routes to do cleaning.

iRobot is planning to quadruple its presence in the Chinese market after setting up its Chinese headquarters in Shanghai last September.

“The global household robots market is growing about 25 percent annually, but in China, the growth rate is close to 70 or 100 percent,” said Colin Angle, chairman and CEO of iRobot.
Other vendors and trends Prominent companies besides Ecovacs and iRobot operating in the market are Dyson Ltd., Infinuvo, Koninklijke Philips N.V., LG Electronics Inc., Neato Robotics Inc., Intellibot Robotics, Yujin Robot, and Samsung Electronics to name just a few.

At CES in Las Vegas in January, one could see that the current consumer products fad seems to have shifted gears from big TVs to robots. CES may well become the goto tradeshow for consumer oriented robotic start-ups. Smart devices for the home offering compatibility with Amazon’s Alexa, Google Home and Apple’s HomeKit were all crowd pleasers but one could see Amazon everywhere. By opening up their Alexa Voice Service, its now being integrated into cars (Ford, VW), smartphones (Huawei), robot vacuums (LG), remotes (DirectTV) and LG refrigerators. Voice activation that works – as Amazon’s Alexa and Siri are proving – is becoming real and offers a new selling point for techies and other early adopters of robotic vacuums and other home products.

Source: Robohub

To visit any links mentioned please view the original article, the link is at the top of this post.
Robotics News / 5 global problems that AI could help us solve
« Last post by Tyler on February 13, 2017, 10:49:22 PM »
5 global problems that AI could help us solve
10 February 2017, 10:30 am

There’s a great deal of concern over artificial intelligence; what it means for our jobs, whether robots will one day replace us in the workplace, whether it will one day lead to robot wars. But current research projects show that artificial intelligence (AI) can also be used for the greater good. Here are five global problems that machine learning could help us solve.

1. Healthcare

One of the biggest benefits of AI is its ability to trawl through massive amounts of data in record time. This helps researchers pinpoint areas of focus for their own research.

For example, a recent ground-breaking discovery on the disease Amyotrophic Lateral Sclerosis (ALS), was made through a partnership between Barrow Neurological Institute and the artificial intelligence company IBM Watson Health.

IBM Watson, the artificial intelligence computer, reviewed thousands of pieces of research and was able to identify new genes linked to ALS.

“Traditional research tools are fast becoming inadequate to help data scientists and researchers keep pace with any global problems that AI could help us solve and find relevant insights among the now billions of documents which are spread all over the world,” said the company in a press release.

“The discovery gives ALS researchers new insights that will pave the way for the development of new drug targets and therapies to combat one of the world’s most devastating and deadly diseases.”

Another promising use for AI within healthcare is its ability to predict the outcome of drug treatments. For instance, cancer patients are often given the same drug, and then monitored to see the effectiveness of that drug. AI could use data to predict which patients could benefit from using a particular drug, providing a highly personalized approach, and saving valuable time and money.

Image: Bloomberg 2. Making driving safer

Despite the crashes involving self-driving cars that have hit the headlines this year, this area of AI could dramatically reduce deaths and injuries on our roads.

According to a report by Stanford University, not only will self-driving cars reduce traffic related deaths and injuries, but they could bring about changes in our lifestyles as well. We will have more time to work or entertain ourselves during commutes, and we may have more choice over where we base ourselves:

“The increased comfort and decreased cognitive load with self-driving cars and shared transportation may affect where people choose to live,” the report says.

3. Transforming how we learn

Earlier this year, students at Georgia Tech university in the US were startled to discover that their helpful teaching assistant had in fact been a robot all along. After initial teething problems, the robot started answering the students’ questions with 97% certainty.

The university designed the robot after their research showed that one of the main factors behind students dropping out is a lack of support.

People learn differently, at different speeds and with different starting points. Artificial intelligence could usher in a future where we all learn in a much more personalised way. But no education system in the world can afford a tutor for every child, so this is where AI might be able to step in. Artificial tutors, made to look and sound as much like humans as possible, could take the lead in delivering personalised education.

4. Help us be smarter about energy

Artificial intelligence could help us be smarter about our energy consumption. In fact, this is already happening.

Image: Google DeepMind Google and other tech giants have enormous data centres that require a massive amount of energy to run the servers and keep them cool. Google has used its artificial intelligence platform Deep Mind to predict when its data centres will get too hot. Cooling systems are only activated when required. AI has saved Google around 40% in energy costs at its server farms.

5. Helping wildlife

As in the case of healthcare, being able to analyse massive amounts of data can transform wildlife conservation.

For instance, by tracking animal movements, we can see where they go, and what habitats we need to protect. This study uses computing power to figure out the best places to create wildlife corridors for wolverines and grizzly bears in Montana. Wildlife corridors are continuous areas of protected land that link zones of biological significance that the animals can use to move safely through the wilderness.


Using artificial intelligence is not without its challenges, however. One of the biggest of these is – how do we keep the systems safe? Algorithms are based on data, so any change to that data will change the behaviour and outcomes.

“Almost anything bad you can think of doing to a machine-learning model can be done right now,” said one expert at a recent AI conference in Spain. “And defending it is really, really hard.”

This post was originally published on

You might also enjoy the following articles:

See all the latest robotics news on Robohub, or sign up for our weekly newsletter.

Source: Robohub

To visit any links mentioned please view the original article, the link is at the top of this post.
General AI Discussion / Re: image detection at different brightness
« Last post by LOCKSUIT on February 13, 2017, 09:06:32 PM »
You can do the like 20 things (I mentioned some) BUT just a bit not too much, and still recognize it after all that!
General AI Discussion / Re: image detection at different brightness
« Last post by yotamarker on February 13, 2017, 08:33:14 PM »
I tried something similar I tried to increase the threshold of the outline
pixels in D darker images  but I didn't know by how much to do it
so the images didn't match they got closer in similarity but no match.

gigidi gigidi goo
General Chat / Re: Take turns saying what AI will do once created!
« Last post by LOCKSUIT on February 13, 2017, 07:40:31 PM »
Well fellas....

You know how I've been telling you's how I have Human Intelligence/ AGI?


I now have SuperIntelligence/ ASI
General AI Discussion / Re: image detection at different brightness
« Last post by LOCKSUIT on February 13, 2017, 05:50:31 PM »
In an image editor you can make the picture brighter/ darker.
General AI Discussion / Re: image detection at different brightness
« Last post by yotamarker on February 13, 2017, 05:45:53 PM »
and how can I make the duplicate brighter ? the brightness comes from outside the sun
the light bulb.

Pages: 1 ... 8 9 [10]


Please login or register.

Login with username, password and session length
mini a.i puzzles
by Freddy (General AI Discussion)
Today at 09:45:52 PM
trivia questions
by yotamarker (General AI Discussion)
Today at 07:54:30 PM
Robot Message in a Bottle
by (Home Made Robots)
Today at 04:04:21 AM
by LOCKSUIT (Graphics)
February 24, 2017, 10:26:32 PM
Auto-Food-Drone type delivery
by Art (General Chat)
February 24, 2017, 06:52:28 PM
Galton Machines or Bean Machines
by Freddy (General AI Discussion)
February 24, 2017, 03:13:07 AM
3D Printing
by Art (General Chat)
February 23, 2017, 12:51:23 PM
by keghn (General AI Discussion)
February 22, 2017, 11:03:11 PM
Robust bipedal Cassie to transform robot mobility
by Tyler (Robotics News)
February 24, 2017, 04:48:44 PM
Artificial intelligence: Understanding how machines learn
by Tyler (Robotics News)
February 24, 2017, 10:49:13 AM
Hard at work: A review of the Laevo Exoskeleton
by Tyler (Robotics News)
February 23, 2017, 04:48:12 PM
Shell Ocean Discovery XPRIZE: Semi-finalists set sail on a journey to illuminate the ocean
by Tyler (Robotics News)
February 22, 2017, 10:48:25 PM
Drones for good 2.0: How WeRobotics is redefining the use of unmanned systems in developing countries
by Tyler (Robotics News)
February 22, 2017, 04:48:07 PM
At what point should an intelligent machine be considered a person?
by Tyler (Robotics News)
February 22, 2017, 10:48:24 AM
Ocado evaluating robotic manipulation for online shopping orders
by Tyler (Robotics News)
February 21, 2017, 10:50:46 PM
Motor control systems: Bode plots and stability
by Tyler (Robotics News)
February 21, 2017, 04:48:52 PM

Users Online

19 Guests, 1 User
Users active in past 15 minutes:

Most Online Today: 50. Most Online Ever: 208 (August 27, 2008, 08:24:30 AM)