Nov 142016
 

Osram Scanning LIDARLIDAR (LIght Detecting And Ranging) sensors play a critical role in almost all autonomous and semiautonomous vehicles. Using lasers and relatively simple time of flight calculations, LIDAR can very accurately measure distances and generate detailed 3D maps of environments, but traditionally the best performing systems have been large and very expensive. German lighting manufacturer Osram Opto Semiconductors unveiled their new 4 channel LIDAR package last week, and its price and size is set to shake up the market.

Continue reading »

Mar 042006
 

Boston Dynamics' BigDog

Defense contractor Boston Dynamics has recently posted video of its BigDog four-legged robot pack mule in action. Funded by DARPA, BigDog is being developed for the US military to carry heavy gear for soldiers across terrain that is not suitable for vehicles. Measuring a little over 3 feet long by 2.5 feet high and weighing 165 pounds, it is indeed closer in size to a large canine than a pack mule. Nonetheless, BigDog seems up to the challenge. It can walk at speeds of up to 3.3 mph, climb 35 degree slopes and carry loads of 120 lbs, following a simple path autonomously or more complicated routes under remote control.

Feb 152006
 
Stanley the Stanford University Volkswagen

Stanley the Stanford University Volkswagen

Fresh off their 1st place finish at Darpa’s Grand Challenge 2005 and not content to rest on their laurels, the robotics experts from Stanford University have announced their next goal is to develop an autonomous vehicle capable of driving from San Francisco City Hall to downtown Los Angeles, at highway speeds no less! Gizmodo.com has a summary today of an article published last weekend by the Palo Alto Online News revealing this ambitious goal. Sebastian Thrun, director of the Stanford Artificial Intelligence Lab, spoke with the publication recently offering some insight into Stanley’s fate and the direction of Stanford’s robot vehicle development program.

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 »