About Me
My name is Mike Danielczuk, and I’m a fourth-year PhD student and NSF Graduate Research Fellow in EECS at UC Berkeley. I am advised by Professor Ken Goldberg of the UC Berkeley AUTOlab. My work thus far has focused on robotic perception and manipulation, ranging from instance segmentation to area contact modeling and robotic pushing to increase grasp success. Specifically, I am very interested in how we can use simulation to generate large datasets for deep learning methods, thus avoiding expensive hand-labeling. I received my BSE in Electrical Engineering from Princeton University.
I also enjoy running and hiking in the many beautiful California parks around the Berkeley area, and I am an avid New England sports fan.
Recent News
- November 25, 2020 : A paper on mechanical search in lateral access environments that I collaborated with several AUTOLab and Google Robotics members on was released on arXiv.
- November 24, 2020 : My paper on using learned collision functions for object rearrangement with Arsalan Mousavian, Clemens Eppner and Dieter Fox from my summer internship in the NVIDIA Seattle Robotics Lab was released on arXiv.
- November 18, 2020: A paper I co-authored with Ashwin Balakrishna and several other AUTOLab members on exploratory grasping was presented virtually at CoRL 2020.
- October 25, 2020 : My paper on mechanical search using learned occupancy distributions as part of a collaboration with Robotics at Google was presented virtually at IROS 2020.
- August 20, 2020 : Four of our papers on grasp exploration using learned priors, reducing repeated failures in bin picking, one-shot instance segmentation, and task-directed grasping as a service were presented virtually at CASE 2020.