A team of researchers at Georgia Tech has developed a new smartphone-based system that could simplify the way humans interact with robots. Called COBALT, the platform allows users with little or no computer experience to remotely control robotic arms from almost anywhere in the world using just a phone and an internet connection.
The project, developed at Georgia Tech’s People, AI & Robotics (PAIR) Lab, turns smartphones into motion controllers for robotic arms. Users simply move their phones in different directions, and the robot displays those movements in real time. Basic tasks like grabbing, moving, and releasing objects can be done with simple on-screen controls, making the experience feel more like playing a mobile game than using industrial machinery.
Ayush Agarwal, who has a Ph.D. student at Georgia Tech’s School of Interactive Computing who leads the COBALT research team, said the program was intentionally designed to make robotics more accessible to beginners than experts. During the experiment, participants from countries including India, Indonesia, and Pakistan remotely controlled robotic arms located inside the Georgia Tech lab despite having no prior robotics experience.
Researchers believe that crowdsourcing can shape the future of robots
The broader mission behind COBALT goes beyond comfort. The researchers believe the platform could solve one of robotics’ biggest challenges: collecting enough real-world training data to develop AI-powered robots.
Modern robots require large amounts of policy training data to learn to perform physical tasks reliably. According to Assistant Professor Animesh Garg, who directs the PAIR Lab, simulation alone is not enough to train robots for large-scale use. Instead, the researchers envision a network full of resources where millions of smartphone users inadvertently contribute performance data through remote interactions with robots.
Garg compared the idea to tapping into nearly five billion users worldwide. By lowering the barrier to entry, the team hopes to create a global system capable of accelerating robot learning and automation.
Technology can have a huge impact on education. Georgia Tech researchers recently demonstrated COBALT to students at Midtown High School in Atlanta, allowing them to remotely operate robotic arms using smartphones. The simplicity of the interface can make robotics education accessible to classrooms without expensive equipment or specialized hardware.
The future “gig economy” of robots may not be far off
Researchers believe COBALT could eventually support new types of long-distance work. Garg explained the possibility of a robotics gig economy where people remotely operate assistive robots in homes, warehouses, or factories from anywhere in the world.
In practical terms, that would mean an industrial robot automatically handles many tasks but calls for human help when it encounters a difficult situation. Instead of requiring on-site staff, remote operators can take brief control over their phones before handing operations over to the AI system.
Agarwal said user research shows that smartphones are preferred over VR headsets, keyboards, or traditional controllers because they feel more intuitive while providing high-quality control data. The system also reduces latency by using WebRTC technology, similar to platforms such as Zoom and Google Meet, ensuring that robot movements and live video streams remain responsive even over long distances.
A research paper on COBALT was presented this week at the IEEE International Conference on Robotics and Automation in Vienna, where the team is showing not only the technology itself, but the large operational wilderness network built around it.
