A simpler path to supercharge robotic systems

Professor Subhrajit Bhattacharya has earned a prestigious NSF CAREER award for project using the mathematical field of topology, which could help streamline complex robotic systems used in healthcare, transportation, and manufacturing.

The prestigious CAREER award is given annually to junior faculty members across the U.S. who exemplify the role of teacher-scholars through outstanding research, excellent education, and the integration of education and research.


Siami ’14G ’17 PhD awarded NSF grant for research on complex networks

Mechanical engineering alum Milad Siami ’14G ’17 PhD, an assistant professor at Northeastern University, has been awarded a $300,000 grant from the National Science Foundation in support of his research on streamlining complex networks.

The project seeks “to make large-scale complex networks simpler by sparse interactions in the right place at the right time.”

Siami received his MS and PhD from Lehigh and was advised by mechanical engineering and mechanics professor Nader Motee, who directs Lehigh’s Distributed Control and Dynamical Systems Laboratory and Autonomous and Intelligent Robotics (AIR) Lab.

Congratulations Milad!

Papers in IROS 2021

Non-Prehensile Manipulation of Cuboid Objects Using a CatenaryRobot (IROS + RAL)

Gustavo A. Cardona, Diego S. D’Antonio, Cristian-Ioan Vasile, and David Saldaña

Abstract: Manipulating objects with quadrotors has been widely studied in the literature, but the majority of those approaches assume quadrotors and loads are previously attached. This setup requires human intervention that is not always achievable or desirable in practice. Furthermore, most of the robot configurations consider rods, manipulators, magnets, and cables modeled as rigid links attached to predefined places on objects. In contrast, we are interested in manipulating objects that are not specifically designed to interact with quadrotors, e.g., no predefined connections, and that do not require humans to set up. In this paper, we control a catenary robot composed of a cable and two quadrotors attached to its ends. Our robot is tasked with moving cuboid objects (boxes) on a planar surface. We design a controller that allows the catenary robot to place the cable in a specific area on the box to perform dragging or rolling. We validate our control design in simulation and with real robots, where we show them rolling and dragging boxes to track desired trajectories.


AIRLab Members Contribute to the US Robotics Roadmap and Science Robotics

Professor Jeff Trinkle has been sharing his expertise and experiences with the robotics community for decades.

His recent effort is co-authoring the 2020 Edition of the “Roadmap for US Robotics – From Internet to Robotics”, which will be published as a Journal paper in a few weeks.

We are looking forward to its publication!



Available now, Prof. Jeff Trinkle and his Ph.D. student, Jinda Cui, published a review paper on Science robotics: https://robotics.sciencemag.org/content/6/54/eabd9461
(Author’s Publication Page for full-text)

This paper summarizes types of variations robots may encounter in human environments, and categorizes, compares, and contrasts the ways in which learning has been applied to manipulation problems through the lens of adaptability. Promising avenues for future research are proposed at the end.

A quick summary of this paper can be found in this report: https://techxplore.com/news/2021-05-path-human-like-robot-skills.html


Lehigh’s AIRLab is set to create and share knowledge in Robotics starting from its creation, and it will continue doing that.

ICRA 2021 Best Paper Nomination

Our #ICRA2021 paper titled “Vision-Based Self-Assembly for Modular Multirotor Structures” has been selected as a finalist paper in the Multi-robot Systems Session.

Authors: Yehonathan Litman*, Neeraj Gandhi, Linh Thi Xuan Phan, David Saldaña

Abstract:  Modular aerial robots can adapt their shape to suit a wide range of tasks, but developing efficient self-reconfiguration algorithms is still a challenge. Self-reconfiguration algorithms in the literature rely on high-accuracy global positioning systems which are not realistic for real-world applications. In this paper, we study self-reconfiguration algorithms using a combination of low-accuracy global positioning systems (e.g., GPS) and on-board relative positioning (e.g. visual sensing) for precise docking actions. We present three algorithms:
1) parallelized self-assembly sequencing that minimizes the number of serial “docking steps”;
2) parallelized self-assembly sequencing that minimizes total distance traveled by modules; and
3) parallelized self-reconfiguration that breaks an initial structure down as little as possible before assembling a new structure.
The algorithms take into account the constraints of the local sensors and use heuristics to provide a computationally efficient solution for the combinatorial problem. Our evaluation in 2-D and 3-D simulations shows that the algorithms scale with the number of modules and structure shape.