The curse of variety in transportation systems
Assistant Professor Cathy Wu is addressing traffic control problems by leveraging deep reinforcement learning.
Download RSS feed: News Articles / In the Media / Audio
Assistant Professor Cathy Wu is addressing traffic control problems by leveraging deep reinforcement learning.
Researchers develop a machine-learning technique that can efficiently learn to control a robot, leading to better performance with fewer data.
Luca Carlone and Jonathan How of MIT LIDS discuss how future robots might perceive and interact with their environment.
A new AI-based approach for controlling autonomous robots satisfies the often-conflicting goals of safety and stability.
A new study finds human supervisors have the potential to reduce barriers to deploying autonomous vehicles.
Through the Multidisciplinary University Research Initiative, the US Department of Defense supports research projects in areas of critical importance to national defense.
A new machine-learning model makes more accurate predictions about ocean currents, which could help with tracking plastic pollution and oil spills, and aid in search and rescue.
The MIT Energy Initiative’s Spring Symposium highlights the vast potential of offshore turbines in decarbonizing the grid.
The system they developed eliminates a source of bias in simulations, leading to improved algorithms that can boost the performance of applications.
Widely recognized leader in statistics and machine learning to succeed Munther Dahleh.
Principal Research Scientist Audun Botterud tackles a range of cross-cutting problems — from energy market interactions to designing batteries — to get closer to a decarbonized power grid.
With the right building blocks, machine-learning models can more accurately perform tasks like fraud detection or spam filtering.
Researchers create a trajectory-planning system that enables drones working together in the same airspace to always choose a safe path forward.
Associate Professor Tamara Broderick and colleagues build a “taxonomy of trust” to identify where confidence in the results of a data analysis might break down.
By keeping data fresh, the system could help robots inspect buildings or search disaster zones.