Mar 222006
 

In a press release put out this morning, California-based Evolution Robotics announced that they will be licensing their ViPR (Visual Pattern Recognition) and Northstar position tracking technologies for use in WowWee’s next generation of hi-tech consumer robots and entertainment products. WowWee, who manufactures the immensely popular Robosapien and Roboraptor robots, has recently been making a conscientious effort to steer the perception of their products from remote-controlled toys to autonomous, intelligent robots. In addition to eliminating the remote controls that shipped with early models, WowWee believes that Evolution’s vision and indoor navigation systems can also play a big role in achieving that goal. The strategic alliance also marks the first time Evolution’s technology will be available in mass-market, consumer robots.

Continue reading »

Dec 162005
 
Sony's QRIO humanoid robot

source: AFP

Hot on the heels of Honda’s Asimo update announced this past Tuesday, Sony today introduced the world to the newest version of their humanoid robot, QRIO. The enhancements to the QRIO include an additional camera mounted in its forehead, mechanical improvements to its arms and hands, and better machine vision algorithms and AI. Like its Honda counterpart, QRIO is now able to recognize faces, colors, and stationary and moving objects.

During its debut in Ginza, Japan this morning, the 60 cm, 7.5 kg QRIO strode out on to the stage wiggling its hips in sync to the music in the background.

Continue reading »

Dec 132005
 

Asimo serves coffee

Honda Motor Co. introduced the second-generation Asimo today. While walking and obstacle avoidance were considered highlights of the previous model, the new Asimo includes many advancements that science fiction has groomed us to expect from humanoid robots. The five-year old Asimo can now handle simple office tasks like greeting visitors and showing them to meeting areas, walking with a tray of drinks, and pushing a 10 kg cart. The new model is even capable of running at speeds of up to 3.7 mph.

Continue reading »

Dec 092005
 

Although there have been many advances in machine vision, most relatively simple robots are still not able to maneuver around objects at high speeds because they are unable to quickly judge their distance from the objects. In order to tackle this problem researchers from Stanford University have developed a new algorithm that many said was impossible: it will allow robots to calculate distances from a single, still image. The algorithm was developed by a team led by computer science Assistant Professor Andrew Ng and was presented at the Neural Information Processing Systems Conference held in Vancouver this week.

Continue reading »