Upload

Loading icon Loading...

This video is unavailable.

CMU LittleDog footplacement learning

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to like LAIRLab's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to dislike LAIRLab's video.

Sign in to YouTube

Sign in with your Google Account (YouTube, Google+, Gmail, Orkut, Picasa, or Chrome) to add LAIRLab's video to your playlist.

Uploaded on Jan 18, 2009

This video shows the LittleDog robot (developed at Boston Dyanmics) attempting to cross a terrain which was much more slippery than expected. Initially it fails. We then teleoperated the robot across the terrain choosing substantially more stable footholds. After training our footstep planner to prefer footholds with similar features we reran the trial. Under the learned footstep costs, our system planned a sequence of footsteps that were significantly more stable, allowing it to successfully traversed the terrain.

Loading icon Loading...

Loading icon Loading...

Loading icon Loading...

Loading icon Loading...

Ratings have been disabled for this video.
Rating is available when the video has been rented.
This feature is not available right now. Please try again later.

Loading icon Loading...

Loading...
Working...
to add this to Watch Later

Add to