Publications

• E. Herbst, X. Ren, D. Fox. "Object Segmentation from Motion with Dense Feature Matching". Accepted to Workshop on Semantic Perception, Mapping and Exploration at ICRA 2012.

  → Most object-level 3-D vision papers these days seem to rely on sparse feature matching (usually SIFT). However, plenty of household objects, like dishware, don't have distinctive local features. We use a robot to find these objects in scenes.

• C. Matuszek, E. Herbst, L. Zettlemoyer, D. Fox. "Learning to Parse Natural Language Commands to a Robot Control System". Accepted to International Symposium on Experimental Robotics (ISER), 2012.

  → Learn a parser that takes English navigation directions to commands in a lambda-calculus-like language. Because the intermediate language isn't bound to any particular map, a robot can use these commands to navigate in environments it didn't get training data in.

• E. Herbst, X. Ren, D. Fox. "RGB-D Object Discovery Via Multi-Scene Analysis". International Conference on Intelligent Robots and Systems (IROS), 2011.

  → Use our surface differencing model for object discovery. Most of the novelty is that we're doing object discovery on very dense 3-D data. Project page.

• E. Herbst, P. Henry, X. Ren, D. Fox. "Toward Object Discovery and Modeling via 3-D Scene Comparison". International Conference on Robotics and Automation (ICRA), 2011.

  → Use differences between two static scenes viewed with an RGBD camera to find movable objects. The obvious 3-D-distance measure doesn't account for occlusions, so breaks much of the time; we use a ray-casting approach. Project page.

• P. Henry, M. Krainin, E. Herbst, X. Ren, D. Fox. "RGB-D Mapping: Using Kinect-Style Depth Cameras for Dense 3-D Modeling of Indoor Environments". International Journal of Robotics Research (IJRR), 2012.
• P. Henry, M. Krainin, E. Herbst, X. Ren, D. Fox. "RGB-D Mapping: Using Depth Cameras for Dense 3-D Modeling of Indoor Environments". International Symposium on Experimental Robotics (ISER), 2010.
• P. Henry, M. Krainin, E. Herbst, X. Ren, D. Fox. "RGB-D Mapping: Using Depth Cameras for Dense 3-D Modeling of Indoor Environments". Robotics: Science and Systems (RSS) Workshop on Advanced Reasoning with Depth Cameras, 2010.

  → Over the last year multiple companies have developed RGBD cameras that measure depth as well as color. We use the extra information to improve on visual SLAM. Project page.

• K. Wampler, E. Andersen, E. Herbst, Y. Lee, Z. Popovic. "Character Animation in Two-player Adversarial Games". ACM Transactions on Graphics (TOG), 2010. Presented at SIGGRAPH 2011.

  → Solve Markov games for animation of two characters in an adversarial situation involving physical motion. Use a motion graph to constrain the explosion of possible moves so we can do lookahead for smart approximate policy solving. Project page.

• E. Herbst, S. Seitz, S. Baker. "Occlusion Reasoning for Temporal Interpolation using Optical Flow". Tech report # UW-CSE-09-08-01, 2009.

  → An optical-flow-based algorithm to smoothly interpolate between two images, assuming constant (but not necessarily small) motion. Adding occlusion and depth-ordering reasoning. Project page.

• B. Fransen, E. Herbst, A. Harrison, W. Adams, J. Trafton. "Real-Time Face and Object Tracking". IEEE International Conference on Intelligent Robots and Systems (IROS), 2009.

  → Put a 3-d motion model and a projection model into the inverse compositional image alignment algorithm [S. Baker, I. Matthews, "Equivalence and Efficiency of Image Alignment Algorithms", CVPR 2001] and do face tracking.

• P. Koehn, H. Hoang, C. Callison-Burch, M. Federico, N. Bertoldi, B. Cowan, W. Shen, C. Moran, R. Zens, C. Dyer, O. Bojar, A. Constantin, E. Herbst. "Moses: Open Source Toolkit for Statistical Machine Translation". Association for Computational Linguistics, 2007.

  → Result of the 2006 NSF Workshop on Human Language Technologies. We wrote a phrase-based decoder from scratch. I worked on the phrase sequence model and on error analysis.

• L. Mueller, T. Solow, N. Taylor, E. Skwarecki, R. Buels, J. Binns, C. Lin, M. Wright, R. Ahrens, Y. Wang, E. Herbst, E. Keyder, N. Menda, D. Zamir, S. Tanksley. "The SOL Genomics Network: a Comparative Resource for Solanaceae Biology and Beyond". Plant Physiology, v138, 2005.

  → I worked at a bioinformatics lab as an undergrad. My research was on efficiently training an HMM-based classifier for signal peptides in plant proteins. I also did a lot of web scripting.

• M. Livingston, E. Herbst. "Interactive Operations for Understanding Embedded Sensor Domains". ACM Symposium on Interactive 3D Graphics and Games (I3D), 2005.
• M. Livingston, E. Herbst. "Interactive Operations for Visualization of Ad-Hoc Sensor System Domains". IEEE Conference on Mobile Ad-Hoc and Sensor Systems, 2005.

  → Displaying the coverage and connectivity of sensor networks and modeling their interaction with interesting objects--for example, magnetometers and vehicles--and the effect of changes to network structure on ground coverage.