MIT team places sixth at international DARPA Robotics Challenge
CSAIL team just misses winning the grand prize after programming a 400-lb humanoid robot to lift beams, climb stairs, and drive a car.
Helping robots handle uncertainty
Algorithm for planning multirobot collaborations makes complex models practical.
Faculty highlight: W. Craig Carter
Materials science professor develops algorithms to solve problems across disciplines, strengthens online teaching techniques, and contributes to scientific art.
“Rocket science” for marketing
Startup’s software, designed to plan NASA space missions, now drives more effective online advertising.
Helping robots put it all together
New algorithm lets autonomous robots divvy up assembly tasks on the fly.
To handle big data, shrink it
Algorithm reduces size of data sets while preserving their mathematical properties.
Removing reflections from photos taken through windows
New algorithm exploits multiple reflections in individual images to distinguish reflection from transmission.
MIT engineers hand “cognitive” control to underwater robots
With MIT-developed algorithms, robots plan underwater missions autonomously.
One way to reduce email stress: Re-invent the mailing list
New CSAIL system lets users customize the mailing-list experience by following and blocking users and “upvoting” messages.
Magnifying vibrations in bridges and buildings
Researchers apply computer vision technique to see tiny vibrations in large structures.
Better traffic signals can cut greenhouse gas emissions
Analysis shows that smarter programming of stoplights could improve efficiency of urban traffic.
Reviewing online homework at scale
System clusters similar student programs together, so instructors can identify broad trends.
Better debugger
System to automatically find a common type of programming bug significantly outperforms its predecessors.
Satellite imagery can aid development projects
New image-analysis methods can automate identification of cost-effective sites for grants or microgrids.