Biography
Danna Ma is a roboticist specializing in swarm robotics, physically intelligent systems, and distributed control, currently serving as a visiting lecturer in Electrical and Computer Engineering at Cornell University. Ma develops swarms that “think” with their bodies rather than solely with their “brains,” exploring how embodied mechanics and minimal sensing can enable collective motion, cohesion, and adaptability in robotic matter.
Ma earned her Ph.D. in electrical and computer engineering from Cornell in 2025 under the supervision of Kirstin Petersen. Ma received her Master’s degree in electrical and computer engineering from Cornell University in 2018, and her Bachelor’s degree in electrical engineering from the National University of Singapore in 2016.
Research Interests
- Physically intelligent robotic swarms
- Emergent behaviors
- Soft sensors and soft robots
Ma’s current focus is on the design and control of physically intelligent robotic swarms, with the goal of understanding and harnessing the complex collective behaviors that arise through local interactions among agents. These swarms can exhibit highly coordinated actions despite individual agents having limited sensing and decision-making capabilities. Ma is particularly interested in how emergent behaviors—such as synchronization, aggregation, and task allocation—can be achieved through simple rules of interaction.
In her earlier work, Ma developed an affordable soft sensor for broad accessibility. Ma investigates how these sensors can be integrated into robotic systems that require flexibility and bio-safe applications. More recently, by leveraging principles of physical intelligence, Ma has developed a robotic swarm that can function both as taskable robotic platforms and as smart materials. The swarm exhibits emergent behavior, adjusting its collective actions based on local interactions and feedback from the environment. The ultimate goal of this research is to develop resilient, scalable, and efficient robotic systems capable of operating effectively in complex, real-world environments.