We present black-box techniques for learning how to interleave the execution of multiple heuristics in order to improve average-case performance. In our model, a user is given a s...
Matthew J. Streeter, Daniel Golovin, Stephen F. Sm...
In multi-robot settings, activity recognition allows a robot to respond intelligently to the other robots in its environment. Conditional random fields are temporal models that ar...
Humans have an amazing ability to perceive depth from a single still image; however, it remains a challenging problem for current computer vision systems. In this paper, we will p...
We describe an application of machine learning to the problem of geomorphic mapping of planetary surfaces. Mapping landforms on planetary surfaces is an important task and the fi...
Tomasz F. Stepinski, Soumya Ghosh, Ricardo Vilalta
We consider the problem of grasping novel objects in cluttered environments. If a full 3-d model of the scene were available, one could use the model to estimate the stability and...