Autonomous helicopter learns autorotation


Stanford’s autonomous helicopter group has made some impressive advancements in the field of autonomous helicopter control, including inverted hovering and performing aerobatic stunts. The group uses reinforcement learning to teach its control system various maneuvers and has been very successful in doing so. One of their latest achievements was teaching the bot the emergency landing technique autorotation. Autorotation is used when a helicopter’s engine fails or is disengaged and works by changing the collective pitch to use the airflow from descent to rotate the blades. The group has more flight demonstrations on their YouTube channel.

[via BotJunkie]

Drive a robot in Australia over the web


BP Australia has commissioned an online game where you get to drive robots around an obstacle course. Make no mistake, these are real robots. Actually they are modified versions of the Surveyor SRV-1 vehicles that are popular with research labs, and schools everywhere.

Go to the website, get in queue and pray for no clouds. These babies are solar powered, so you’ll have to try to get in while its day time in Australia. The entire set is built in miniature, so you feel like you’re driving a tank around a city.

[via Robots Dreams]

Google releases keyCzar


Google has released keyCzar, a cryptographic toolkit that supports encryption and authentication for both symmetric and public-key algorithms.

Cryptography is a common problem area for web programmers. keyCzar aims to help alleviate some of the issues by supplying safe defaults, tagging versions, and a simple interface.

[via Zero Day]