Laboratory for Autonomous Systems and Mobile Robotics


The Laboratory for Autonomous Systems and Mobile Robotics (LAMOR), directed by Prof. Ivan Petrović of the University of Zagreb Faculty of Electrical Engineering and Computing, has a long tradition in research of advanced control strategies and estimation techniques for a variety of applications with a strong emphasis on autonomous navigation of ground and aerial robots in unknown and dynamic environments. Our methodology relies on a strong coupling between theoretical research, algorithm development, experimental evaluations, and a healthy dose of serendipity. LAMOR's research activity is organized around three major axes: Motion Planning and Control, Simultaneous Localization and Mapping, and Detection and Tracking of Moving Objects. Our laboratory is equipped with state-of-the-art ground and aerial robotic platforms, advanced perception sensors and a motion capture covered arena.


LAMOR - Laboratory for Autonomous Systems and Mobile Robotics, Centre of research excellence for data science and cooperative systems, and IEEE Croatia Robotics and  Automation Chapter invite you to the lecture:

"Getting in Touch: Mobile Manipulator Kinematic and Sensor Extrinsic Parameter Calibration Through Contact-Based Interaction"

which will be held by Prof. Jonathan Kelly, University of Toronto, Canada. The lecture will take place on Thursday, July 25, 2019 at 13.15h, in the Gray Hall of the Faculty of Electrical Engineering and Computing.

You can find more about the lecturer and the seminar in the detailed news content.

Abstract:

Mobile manipulation platforms typically rely on one or more exteroceptive sensors (cameras, depth cameras, lidar units, etc.) to provide information about the immediate operating environment. In some situations, these sensors may be mounted directly to or near the end-effector. However, in many other cases, the sensors are rigidly attached to the mobile base, while the robot arm moves independently. In this talk, I will describe a novel approach for mobile manipulator self-calibration that relies on contact information; the method uses point cloud registration to estimate the transform (relative pose) between a base-mounted exteroceptive sensor and the manipulator's tool endpoint frame. Beyond sensor calibration, I will discuss the possibility of simultaneously calibrating the manipulator kinematic model through a non-rigid registration process. Finally, I will provide an overview of our experimental results and characterize the conditions necessary for reliable calibration.

Bio:

Dr. Jonathan Kelly leads the Space & Terrestrial Autonomous Robotic Systems (STARS) Laboratory at the University of Toronto Institute for Aerospace Studies, where his group carries out research at the nexus of sensing, planning, and control, with an emphasis on the study of fundamental problems related to perception, representation, and understanding of the world. Dr. Kelly holds a Dean's Catalyst Professorship (an early-career award for research excellence and potential) and a Canada Research Chair in Collaborative Robotics. Prior to joining the University of Toronto, he was a postdoctoral researcher in the Robust Robotics Group at the Massachusetts Institute of Technology working with Prof. Nick Roy. Dr. Kelly received his PhD degree in 2011 from the University of Southern California under the supervision of Prof. Gaurav Sukhatme; at USC, he was a member of the first cohort of Annenberg Fellows. Before starting graduate school, he was a Software Engineer in the Space Technologies division of the Canadian Space Agency.

News list

Current Projects

 

   

 


External sites