Search
Now showing items 31-40 of 101
Balance control and locomotion planning for humanoid robots using nonlinear centroidal models
(Massachusetts Institute of Technology, 2020)
Balance control approaches for humanoid robots have traditionally relied on low-dimensional models for locomotion planning and reactive balance control. Results for the low-dimensional model are mapped to the full robot, ...
Learning to see the physical world
(Massachusetts Institute of Technology, 2020)
Human intelligence is beyond pattern recognition. From a single image, we are able to explain what we see, reconstruct the scene in 3D, predict what's going to happen, and plan our actions accordingly. Artificial intelligence, ...
Dense visual learning for robot manipulation
(Massachusetts Institute of Technology, 2020)
We would like to have highly useful robots which can richly perceive their world, semantically distinguish its fine details, and physically interact with it sufficiently for useful robotic manipulation. This is hard to ...
Multi-agent coordination under limited communication
(Massachusetts Institute of Technology, 2020)
In this thesis, we present a theory for constructing real-time executives that can reason about communication between agents. In multi-agent coordination problems, different agents have different beliefs about the state ...
A hybrid approach towards on-chip visible lasers
(Massachusetts Institute of Technology, 2020)
In recent years, the world of nanostructured optically active materials has expanded to include organic molecules; colloidal nanocrystals such as quantum dots, quantum rods, and quantum wells or nanoplatelets; perovskite ...
Techniques for enhancing electron microscopy
(Massachusetts Institute of Technology, 2020)
Electron microscopy is a powerful imaging technique that allows us to push the limits of our understanding of materials at the nanoscale. An important limitation in the application of electron microscopy to organic and ...
Image segmentation for highly variable anatomy : applications to congenital heart disease
(Massachusetts Institute of Technology, 2020)
Automated segmentation of medical images can facilitate clinical tasks in diagnosis, patient monitoring, and surgical planning. However, current methods either rely on explicit correspondence detection, or use machine ...
Anomaly detection through explanations
(Massachusetts Institute of Technology, 2020)
Under most conditions, complex machines are imperfect. When errors occur, as they inevitably will, these machines need to be able to (1) localize the error and (2) take appropriate action to mitigate the repercussions of ...
Causal inference : a Tensor's perspective
(Massachusetts Institute of Technology, 2020)
Quantifying the causal effect of an intervention is a ubiquitous problem that spans a wide net of applications. Typically, this quantity is measured through the difference in outcomes under treatment (e.g., novel drug) and ...
On optimization and scalability in deep learning
(Massachusetts Institute of Technology, 2020)
Deep neural networks have achieved significant empirical success in many fields, including computer vision, machine learning, and artificial intelligence. Along with its empirical success, deep learning has been theoretically ...