Abstract. This paper describes Team Delft's robot, which won the Amazon Picking Challenge 2016, including both the Picking and the Stowing competitions. The goal of the challenge is to automate pick and place operations in unstructured environments, specifically the shelves in an Amazon warehouse. Team Delft's robot is based on an industrial robot arm, 3D cameras and a customized gripper. The robot's software uses ROS to integrate off-the-shelf components and modules developed specifically for the competition, implementing Deep Learning and other AI techniques for object recognition and pose estimation, grasp planning and motion planning. This paper describes the main components in the system, and discusses its performance and results at the Amazon Picking Challenge 2016 finals.

No abstract

No abstract

No abstract

An all-glass bifurcation microfluidic chip for blood plasma separation was fabricated by a cost-effective glass molding process using an amorphous carbon (AC) mold, which in turn was fabricated by the carbonization of a replicated furan precursor. To compensate for the shrinkage during AC mold fabrication, an enlarged photoresist pattern master was designed, and an AC mold with a dimensional error of 2.9% was achieved; the dimensional error of the master pattern was 1.6%. In the glass molding process, a glass microchannel plate with negligible shape errors (~1.5%) compared to AC mold was replicated. Finally, an all-glass bifurcation microfluidic chip was realized by micro drilling and thermal fusion bonding processes. A separation efficiency of 74% was obtained using the fabricated all-glass bifurcation microfluidic chip.