Jacobs Robotics Team
- Kaustubh Pathak (Jacobs University)
- Narunas Vaskevicius (Jacobs University)
- Tobias Fromm (Jacobs University)
- Christian A. Müller (Jacobs University)
Jacobs University Bremen is a new private research university patterned after the Anglo-Saxon university system. The university was founded in 1999. It has an international student body (ca. 1400 students from over 100 nations, admitted in a highly selective process).
Robotics research at Jacobs started with the very beginning of research and teaching activities at Jacobs University in September 2001. The research activities of the robotics group include 3D perception and world-modelling in unstructured environments, among others in logistics applications.
The Jacobs Robotics Group has significant expertise that is relevant for the EuRoC Challenge 2 “Shop Floor Logistics and Manipulation”. The team participated among others very successfully in the ICRA'11 Solutions in Perception Challenge, where its software was used to grasp objects in cluttered scenes with a PR2 robot.
Another example is its participation in the DLR SpacebotCup for which a mobile platform with a light-weightarm was used by the team to find and grasp objects on a mock-up planetary surface. Furthermore, the Jacobs Robotics Group is participating in the EU-FP7 project “Cognitive Robot for Automation of Logistic Processes (Roblog)”, where seven partners are developing novel solutions for the unloading of shipping containers.
The team consists of three PhD students who are supervised by two faculty members. The team members cover different expertise with respect to object recognition, manipulation, and autonomous navigation.
Dr. Andreas Birk is a full professor and Kaustubh Pathak, PhD, is an assistant professor; both are in Electrical Engineering and Computer Science at Jacobs University.
Narunas Vaskevicius, Tobias Fromm, and Christian A. Müller are PhD students in the Jacobs Robotics Group.
Selected Relevant Publications:
- C. A. Mueller, K. Pathak, A. Birk. Object Shape Categorization in RGBD Images using Hierarchical Graph Constellation Models based on Unsupervisedly Learned Shape Parts described by a Set of Shape Specificity Levels. IEEE/RSJ IROS 2014
- N. Vaskevicius, K. Pathak, A. Birk. Fitting Superquadrics in Noisy, Partial Views from a Low-cost RGBD Sensor for Recognition and Localization of Sacks in Autonomous Unloading of Shipping Containers. IEEE CASE 2014
- N. Vaskevicius, C. A.Mueller, M. Bonilla, V. Tincani, T. Stoyanov, G. Fantoni, K. Pathak, A. J. Lilienthal, A. Bicchi, A. Birk. Object Recognition and Localization for Robust Grasping with a Dexterous Gripper in the Context of Container Unloading. IEEE CASE 2014
- R. Krug, T. Stoyanov, M. Bonilla, V. Tincani, N. Vaskevicius, G. Fantoni, A. Birk, A. J. Lilienthal, A. Bicchi. Velvet Fingers: Grasp Planning and Execution for an Underactuated Gripper with Active Surfaces. ICRA 2014
- C. A. Mueller, K. Pathak, A. Birk. Object Recognition in RGBD Images of Cluttered Environments using Graph-Based Categorization with Unsupervised Learning of Shape Parts, IROS 2013
- N. Vaskevicius, K. Pathak, A. Ichim, A. Birk, The Jacobs Robotics Approach to Object Recognition and Localization in the Context of the ICRA'11 Solutions in Perception Challenge, ICRA 2012