A one-up on motion capture
A new neural network approach captures the characteristics of a physical system’s dynamic motion from video, regardless of rendering configuration or image differences.
Search Stories
Generating new molecules with graph grammar
An efficient machine-learning method uses chemical knowledge to create a learnable grammar with production rules to build synthesizable monomers and polymers.
School of Engineering welcomes new faculty
Seventeen new professors join the MIT community, with research areas ranging from robotics and machine learning to health care and agriculture.
A system for designing and training intelligent soft robots
“Evolution Gym” is a large-scale benchmark for co-optimizing the design and control of soft robots that takes inspiration from nature and evolutionary processes.
Accelerating the discovery of new materials for 3D printing
A new machine-learning system costs less, generates less waste, and can be more innovative than manual discovery methods.
Contact-aware robot design
A novel method to represent robotic manipulators helps optimize complex and organic shapes for future machines.
Intelligent carpet gives insight into human poses
Tactical sensing carpet estimates 3D human poses without the use of cameras, and could improve health monitoring and smart homes.
Tactile textiles sense movement via touch
By measuring a person’s movements and poses, smart clothes developed at MIT CSAIL could be used for athletic training, rehabilitation, or health-monitoring for elder-care facilities.
Researchers’ algorithm designs soft robots that sense
Deep-learning technique optimizes the arrangement of sensors on a robot’s body to ensure efficient operation.
Using artificial intelligence to generate 3D holograms in real-time
A new method called tensor holography could enable the creation of holograms for virtual reality, 3D printing, medical imaging, and more — and it can run on a smartphone.
Automating material-matching for movies and video games
Animators spend hours adding textures to objects. A new machine-learning system simplifies the process.
This 3D printer doesn’t gloss over the details
New system enables realistic variations in glossiness across a 3D-printed surface. The advance could aid fine art reproduction and the design of prosthetics.
Computer-aided creativity in robot design
MIT researchers’ new system optimizes the shape of robots for traversing various terrain types.
MIT Energy Initiative awards eight seed fund grants for early-stage MIT energy research
Annual MITEI awards support research on battery storage, smart grids, and carbon emissions reduction.
How to design and control robots with stretchy, flexible bodies
Optimizing soft robots to perform specific tasks is a huge computational problem, but a new model can help.