The Pransky interview: Dr Raffaello D’Andrea, Founder, CEO, and Chairman of the board at Verity; Entrepreneur; Professor; Scientist and Artist

Purpose The following article is a “Q&A interview” conducted by Joanne Pransky of Industrial Robot Journal as a method to impart the combined technological, business and personal experience of a prominent, robotic industry PhD and inventor regarding his pioneering efforts and the commercialization of bringing a technological invention to market. This paper aims to discuss these issues. Design/methodology/approach The interviewee is Dr Raffaello D’Andrea, a highly successful entrepreneur and proven business leader and one of the world’s foremost leaders in robotics and machine learning. D’Andrea is Founder, CEO and Chairman of the Board at Verity, the world’s leading autonomous indoor drone company, as well as a Professor of Dynamic Systems and Control at the Swiss Federal Institute of Technology (ETH) in Zurich. D’Andrea is also one of the co-founders and advisors of Robo-Global, an index and research company focused on investments in robotics, automation and artificial intelligence. In this interview, D’Andrea shares some of his business and personal experiences of working in industry and academia and his criteria for turning his ideas into successful working systems. Findings Raffaello D’Andrea’s entire career is built on his ability to bridge theory and practice. D’Andrea combined his love for science with his need to create and received a BS degree in engineering science at the University of Toronto, where he was awarded the Wilson Medal as the top graduating student in 1991. He obtained both his MS and PhD degrees in electrical engineering at Caltech, and then he joined the Cornell faculty as an assistant professor. While on leave from Cornell, from 2003 to 2007, he co-founded the disruptive warehouse automation company Kiva Systems, where he led the systems architecture, robot design, robot navigation and coordination, and control algorithms efforts. In 2014, D’Andrea took robotics technology into the air and founded Verity, the world’s first company to deliver a fully integrated autonomous, indoor drone-based system solution. Originality/value Raffaello D’Andrea combines academia, business and the arts to reinvent autonomous systems. D’Andrea was a founding member of the Systems Engineering Program at Cornell, where he established robot soccer as the flagship, multidisciplinary team project. In addition to pioneering the use of semi-definite programming for the design of distributed control systems, he went on to lead the Cornell Robot Soccer Team to win four world international RoboCup championships. Kiva Systems, co-founded by D’Andrea and acquired by Amazon in 2012, helped the re-branded Amazon Robotics to disrupt the entire warehousing and logistics systems industry. Additionally, D’Andrea is an internationally-exhibited new media artist, best known for the Robotic Chair (Ars Electronica, ARCO, London Art Fair, National Gallery of Canada) and Flight Assembled Architecture (FRAC Centre). With his team at Verity, he created the drone design and choreography for Cirque Du Soleil’s Paramour on Broadway, Metallica’s WorldWired Tour and Céline Dion’s Courage Tour. Other D’Andrea creations include the Flying Machine Arena, where flying robots perform aerial acrobatics, juggle balls, balance poles and cooperate to build structures; the Distributed Flight Array, a flying platform consisting of multiple autonomous single propeller vehicles that are able to drive, dock with their peers and fly in a coordinated fashion; the Balancing Cube, a dynamic sculpture that can balance on any of its edges or corners and its little brother Cubli, a small cube that can jump up, balance and walk; Blind Juggling Machines that can juggle balls without seeing them, and without catching them. D’Andrea is also collaborating with scientists, engineers, and wingsuit pilots to create an actively controlled suit that will allow humans to take off and land at will, to gain altitude, even to perch, while preserving the intimacy of wingsuit flight. D’Andrea has received the IEEE Robotics and Automation Award, the Engelberger Robotics Award, the IEEE/IFR Invention and Entrepreneurship Award in Robotics and Automation and the Presidential Early Career Award for Scientists and Engineers. In 2020, he was inducted in the National Inventors Hall of Fame and elected to the National Academy of Engineering.

Implementation of high-voltage kicker system for “ROSTU” middle-size league robot soccer

Middle-size robot soccer is one of the divisions that competed in national events such as the National Indonesia Robotics Competition and international competitions such as the middle size league (MSL). One of the main components in soccer robots is the kicker system. The kicker system is expected to be high torque, robust, and safe. In this work, a high voltage kicker system is designed and evaluated to substitute ROSTU's previous kicker system. This high voltage solenoid-based kicker system works at 380V and uses the electromagnetic force principle to move a ball. The performance criteria of the kicker system are it can move a ball with a mass of around 1 kg for a minimum range of 3 m and control the charging and discharging process in high voltage conditions. The experiment results show that the kicker system can move a ball with a mass of 1.06 kg, a difference kick distance from 100cm to 350cm, and a monitoring system that can show information about the capacitor voltage and system status.

Development of Ball Detection System with YOLOv3 in a Humanoid Soccer Robot

One of the practical researches of humanoid robots is research on the use of humanoid robots to play soccer. Research in this field is also encouraged by the existence of various humanoid robot soccer competitions. In humanoid robots for soccer, one of the important aspects is the robot’s ability to detect the ball, goal, field boundaries and other players, both friend players and opposing players. This study focuses on the ball detection system which is a basic ability that humanoid robots need to have. The ball detection system developed in this study uses the YOLOv3 method. The test results show that the system built and trained with 3000 image samples can detect balls at a distance of 50 to 900 cm. The time it takes to detect the ball is about 0.033 seconds.

Two-stage training algorithm for AI robot soccer

In multi-agent reinforcement learning, the cooperative learning behavior of agents is very important. In the field of heterogeneous multi-agent reinforcement learning, cooperative behavior among different types of agents in a group is pursued. Learning a joint-action set during centralized training is an attractive way to obtain such cooperative behavior; however, this method brings limited learning performance with heterogeneous agents. To improve the learning performance of heterogeneous agents during centralized training, two-stage heterogeneous centralized training which allows the training of multiple roles of heterogeneous agents is proposed. During training, two training processes are conducted in a series. One of the two stages is to attempt training each agent according to its role, aiming at the maximization of individual role rewards. The other is for training the agents as a whole to make them learn cooperative behaviors while attempting to maximize shared collective rewards, e.g., team rewards. Because these two training processes are conducted in a series in every time step, agents can learn how to maximize role rewards and team rewards simultaneously. The proposed method is applied to 5 versus 5 AI robot soccer for validation. The experiments are performed in a robot soccer environment using Webots robot simulation software. Simulation results show that the proposed method can train the robots of the robot soccer team effectively, achieving higher role rewards and higher team rewards as compared to other three approaches that can be used to solve problems of training cooperative multi-agent. Quantitatively, a team trained by the proposed method improves the score concede rate by 5% to 30% when compared to teams trained with the other approaches in matches against evaluation teams.