Open Positions

Deep Learning based Robust Grasping of objects using Shadow Hand

Description: The PRG Lab has an opening for a graduate student, to work on adaptive grasping with the Shadow Dexterous Hand and UR-10 manipulator. We are looking for dedicated and motivated students with good programming skills, good work ethics, and a keen interest in learning new skills. The work you do here has both research and industry applications.
Goal: The project is on adaptive grasping with the Shadow Hand, using the BioTac tactile sensors. The Hand is mounted on the UR-10 arm/manipulator that allows further mobility during pick and place operations. The main idea is to allow grasping of novel, previously unseen objects without the use of cameras. We call it "Grasping In The Dark", since we mimic the human behavior of grasping without needing to look at the object. The pipeline combines control systems, motion planning and signal processing techniques to perform a successful grasp.

Contact: Kanishka Ganguly (kganguly[at]terpmail[dot]umd[dot]edu))
Skills Required: We expect a thorough understanding of ROS, and prior knowledge of the MoveIt! planning framework is a bonus. The existing codebase is in C++11 and Python, so working knowledge of both is necessary. Linear algebra and undergrad math knowledge is also a must.
Please provide a short resume and transcripts with grades of relevant coursework (Planning, Control, Perception) to Kanishka Ganguly at and we will contact you for a short interview.

Operating Home Appliances using the Baxter Robot

Description: Grasping is a fundamental problem which need to be solved by humanoid robots or robotic arms. Grasping traditionally involves end effector planning coupled with perception and complex controls. In this project, you will be working on operating refrigerator and microwave oven in particular. Check [1] and [2] videos for reference. The codebase is available and you will be responsible for improving the robustness of the system.
Goal: Operating the refrigerator and microwave oven using Baxter.

Contact: Cornelia Fermuller (fer[at]cfar[dot]umd[dot]edu))
Skills Required: Proficiency in ROS, C++, Linux and Python.
Thesis Type: Semester Project/Independent Study
Job Opportunities: Upon successful completion of the project, students will have a good chance of getting a job at Amazon and any other robotic arm companies or robotics automation companies.