Yun Jiang

I'm a Ph.D. student in Department of Computer Science at Cornell University. My advisor is Prof. Ashutosh Saxena. My primary research interests are: machine learning and its applications to manipulation for personal robots. Check out our Robot Learning Lab for some awesome projects!

Before coming to Cornell, I did my undergraduate at Shanghai Jiao Tong University, in China.

Email: yunjiang@cs.cornell.edu.

My curriculum vitae is here.

Modeling High-Dimensional Humans using Gaussian Process

In many robotic applications, we need to model human configurations in both detailed high-dimensional descriptions and compact low-dimensional representations. We therefore propose a new model, GP-LCRF, which learns a probabilistic mapping between the high- and low-dim. representations using a Gaussian process, and models the rich context between humans, objects and the activity using CRF in the task of human activity anticipation.

Publications: RSS'14

Infinite Latent Conditional Random Fields (ILCRFs)

This work is motivated by the need of modeling latent human poses and human-object interactions: The number of potential humans is unknown, and the human-object interactions vary not only in type but also in which human pose relates to each object.

Our ILCRF models a scene as a mixture of CRFs generated from Dirichlet processes. Each CRF represents one possible explanation of the scene. In addition to visible object nodes and edges, it generatively models the distribution of different CRF structures over the latent human nodes and corresponding edges.

Publications: RSS'13, under journal submission (2014)

Hallucinating Humans

We show that modeling human-object relationships (i.e., object affordances) gives us a more compact way of modeling the contextual relationships (as compared to modeling the object-object relationships). One key aspect of our work is that the humans may not be even seen by our algorithm! Applications to vision/robotics: 3D perception and arranging a disorganized room.

Publications: ICML'12, ISER'12, CVPR'13 (oral), RSS'13

Learning to Place Novel Objects

The ability to place objects in the environment is an important skill for a personal robot. An object should not only be placed stably, but should also be placed in its preferred location/orientation. For instance, a plate is preferred to be inserted vertically into the slot of a dish-rack as compared to be placed horizontally. In this work, we propose a supervised learning algorithm for finding good placements given the point-clouds of the object and the placing area.

Publications: IJRR'12, ICRA'12, ISER'12

Learning to Grasp Novel Objects

We consider the problem of grasping novel objects, specifically ones that are being seen for the first time through vision. We present a learning algorithm that predicts, directly as a function of the RGB/RGBD image, a point at which to grasp the object. We apply this algorithm to unload items from a dishwasher, and also to novel grippers such as jamming gripper.

Publications: ICRA'12, ICRA'11