IROS 2017: Feature discovery and visualization of robot mission data using convolutional autoencoders and Bayesian nonparametric topic modeling

Abstract: We introduce a novel unsupervised machine learning framework that incorporates the ability of convolutional autoencoders to discover features from images that directly encode spatial informa…

Read more

Phytoplankton Hotspot Prediction With an Unsupervised Spatial Community Model

Many interesting natural phenomena are sparsely distributed and discrete. Locating the hotspots of such sparsely distributed phenomena is often difficult because their density gradient is likely to b…

Read more

Robot Systems

Robots with alternative locomotion design can assist us in observing previously inaccessible environments. Here are some examples of our prior work. MARE: Marine Autonomous Robotic Explorer MARE is a…

Read more

Sensing the world, abstractly.

We want our robots to sense the world at varying levels of abstraction. From raw sensor value, to terrain type, to habitat type. ROST is a technique for semantic modeling of high bandwidth streaming s…

Read more

Interactive Exploration of Mission Data

ROST can automatically characterize large image datasets, identify various scene components and detect context aware anomalies. These automatically annotated datasets can then be visualized using vari…

Read more

Soundscape Characterization

This work explores the problem of automatic discovery of different acoustic regions in the world, as experienced by a mobile robot. We use a temporally smoothed variant of Latent Dirichlet Allocation…

Read more

Curious Exploration Robots

There is a need for autonomous exploration robots because vast majority of our oceans are unexplored, and direct human exploration of the deep sea is an expensive and extremely dangerous endeavor. O…

Read more