Assistant Professor Loianno runs the Agile Robotics and Perception Lab (ARPL) of the New York University Tandon School of Engineering. Earlier this year, he was part of a team featuring students from his lab, the University of Pennsylvania and the Czech Technical University in Prague, they won first place at the MBZIRC competition using a Kinova Gen3 robotic arm on top of their UGV (unmanned ground vehicle).
Kinova: Can you give us a brief description of the project?
Giuseppe Loianno: The Mohamed Bin Zayed International Robotics Challenge (MBZIRC) is an international robotics competition, to be held every two years with total prize and team sponsorship of USD 5 Million.
Robotic competitions in the past few decades have been a catalyst that has accelerated the rate of technological advancements in the field of robotics and autonomous systems.
MBZIRC aims to provide an ambitious, science-based, and technologically demanding set of challenges in Robotics, open to a large number of international teams. It is intended to demonstrate the current state of the art in robotics in terms of scientific and technological accomplishments, and to inspire the future of robotics. It’s also enable students to quickly learn and use robotic arms.
K.: What was the specific challenge at MBZIRC?
G.L.: The challenge involved the problem of picking and placing bricks to generate a wall. This task combines perception, autonomy, control, planning, and it has a tremendous potential to solve future civil and urban problems with ground and aerial robotic systems.
K.: Why did you choose a Kinova robotic arm?
G.L.: I was looking for a fast-lightweight arm with at least 3 Kg payload. It is hard to find something like that in the current market. Moreover, I wanted a versatile solution without an external controller box. Everything needed to be self-contained in the arm. These represent conflicting design requirements and for this reason it was very difficult to find the solution we were looking for.
In the end, I must say that Kinova was the only one able to satisfy all my requirements and needs.
The lightweight aspect was one of our major concerns because I felt this was extremely important to guarantee the safety of the grasped object and the end user. Finally, another nice feature is that the arm contains already multiple ready to use sensors such as camera and depth sensors in proximity of the end effector.
K.: In your chosen approach, what task does the Kinova Gen3 do?
G.L.: We actually combined a ground platform with a Kinova Gen3 arm mounted on top. The approach is mainly composed by four steps.
- We use the front camera to identify bricks. The algorithm is able to identify the position of the brick with respect to the arm.
- The robot then plans a trajectory to pick the brick and recall the internal Cartesian position control of the Kinova arm.
- The end-effector, a magnetic gripper, is activated to lock the brick.
- The ground robot moves, and the brick is sequentially positioned on the wall.
K.: Can you describe your impressions of Gen3?
G.L.: Very solid and easy to use. The simulation environment and the ROS interface contributes to facilitate its use and interface with students and other hardware peripherals.
K.: Who would you recommend this product for?
G.L.: I would recommend it to all the academic institutions. No doubt this is the probably the best educational and research manipulation product on the market at this stage.
K.: Until the next competition, what have you planned for the Gen3 robotic arm?
G.L.: Since the arm is really easy to use and safe, one of the student has been able to use it at home during the COVID situation. A student also built a GitHub specifically about the integration of the arm on a mobile platform.
We will also use it back in the laboratory, and eventually in one of my class.