Demo Vidoes

A successful Ph.D. defense with an impressive robot pouring live demo

Yongqiang Huang demonstrated his robotic pouring research result in his Ph.D. defense. The pouring motion was generated using a recurrent neural network.

Drinking Game Just Become Easier with a Beer-Pouring Robot

The demo shows our robotic motion generator can pour any arbitrary amount of liquid accurately from various unseen containers without changing the code. This recurrent neural network based motion generator shows good generalization behavior.

Ideomotor Learning for Robotic Manipulation

Yu Sun's talk at Stanford University during the Bay Area Robotics Symposium 2016

Branching Segment Detection Hamlyn

Example results in our TBME paper "Efficient Vessel Feature Detection for Endoscopic Image Analysis" by Bingxiong Lin, Yu Sun, Jaime E. Sanchez, and Xiaoning Qian

Vessel Tracing Process

The vessel tracing process in our paper "Efficient Vessel Feature Detection for Endoscopic Image Analysis" by Bingxiong Lin, Yu Sun, Jaime E. Sanchez, and Xiaoning Qian

Execution after learning the tasks

Lin, Y., Sun, Y. (2013) Task-Oriented Grasp Planning Based on Disturbance Distribution, ISRR, pp 1-16

Task-Oriented Grasp Planning Based on Disturbance Distribution

One difficulty of task-oriented grasp planning is task modeling. In this paper, a manipulation task was modeled by building a non-parametric statistical distribution model from disturbance data captured during demonstrations. This paper proposes a task-oriented grasp quality criterion based on distribution of task disturbance and uses the criterion to search for a grasp that covers the most significant part of the disturbance distribution. To reduce the computational complexity of the search in a high-dimensional robotic hand configuration space, as well as to avoid a correspondence problem, the candidate grasps are computed from a reduced configuration space that is confined by a set of given thumb placements and thumb directions. The proposed approach has been validated with a Barrett hand and a Shadow hand on several objects in simulation. The resulting grasps in the evaluation generated by our approach increase the coverage of frequently-occurring disturbance rather than the coverage of a large area with a scattered distribution.

SAGE update

Spatial Augmented Reality on Person