Documentation is Hard, Let the SkunkWorks Project Show You How to Do It Well

Documentation can be a bit of a nasty word, but it’s certainly one aspect of our own design process that we all wish we could improve upon. As an award-winning …read more Continue reading Documentation is Hard, Let the SkunkWorks Project Show You How to Do It Well

Little Lamp To Learn Longer Leaps

Reinforcement learning is a subset of machine learning where the machine is scored on their performance (“evaluation function”). Over the course of a training session, behavior that improved final score is positively reinforced gradually building towards an optimal solution. [Dheera Venkatraman] thought it would be fun to use reinforcement learning …read more

Continue reading Little Lamp To Learn Longer Leaps

Pixar Style Robots Are Treasure Trove Of Building Tricks

[Alonso Martinez] is an artist working on virtual characters at Pixar so it’s no wonder that his real life robots, Mira and Gertie,  have personalities that make them seem like they jumped straight out of a Pixar movie. But what we really like are the tricks he’s used inside to bring them to life that are sure to get reused for the same or other things.

For example, Mira’s head can rotate in yaw, pitch and roll. To figure out how to make it do that he recalled having a joystick called the Microsoft Sidewinder Pro that had force feedback. …read more

Continue reading Pixar Style Robots Are Treasure Trove Of Building Tricks