9 accepted papers
We propose a novel unsupervised method to learn pose and part-segmentation of articulated objects with rigid parts. Given two observations of an object in different articulation states, our method learns the geometry and appearance of object parts by using an implicit model from the first observ…
Simplicial complexes can be viewed as high dimensional generalizations of graphs that explicitly encode multi-way ordered relations between vertices at different resolutions, all at once. This concept is central towards detection of higher dimensional topological features of data, features to which…
Humans can easily reason about the sequence of high level actions needed to complete tasks, but it is particularly difficult to instill this ability in robots trained from relatively few examples. This work considers the task of neural action sequencing conditioned on a single reference visual state
Presents corrections to the abstract in the above named paper.
Sensors are routinely mounted on robots to acquire various forms of measurements in spatio-temporal fields. Locating features within these fields and reconstruction (mapping) of the dense fields can be challenging in resource-constrained situations, such as when trying to locate the source of a gas
Sensors are routinely mounted on robots to acquire various forms of measurements in spatiotemporal fields. Locating features within these fields and reconstruction (mapping) of the dense fields can be challenging in resource-constrained situations, such as when trying to locate the source of a gas l
Acoustic source localization (ASL) is an important problem. Despite much attention over the past few decades, rapid and robust ASL still remains elusive. A popular approach is to use a circular array of microphones to record the acoustic signal followed by some form of optimization to deduce the mos…
Humans manipulate fluids intuitively using intuitive approximations of the underlying physical model. In this paper, we explore a general methodology that robots may use to develop and improve strategies for overcoming manipulation tasks associated with appropriately defined loss functions. We focus
SONAR mapping of underwater environments leads to dense point-clouds. These maps have large memory footprints, are inherently noisy and consist of raw data with no semantic information. This paper presents an approach to underwater semantic mapping where known man-made structures that appear in mult…