Preserving Independence in the Home
Researchers at Carlos III University of Madrid (UC3M) have developed a new way for a robot to coordinate its two arms smoothly and autonomously. They presented their work at IROS 2025, one of the world’s largest robotics conferences. Their system paves the way for service robots to perform more natural movements and learn household tasks more easily.
ADAM: The Challenge of Two-Arm Coordination
Alicia Mora, one of the researchers in the Mobile Robots Group at the UC3M Robotics Laboratory, explains the machine’s current capabilities: “It can set the table and then clear it, tidy up the kitchen, or bring a user a glass of water or medication at the specified time.” She adds a detail about mobility assistance: “It can also help them when they go out by bringing them a coat or other clothing.”
ADAM was designed with older adults in mind. Ramón Barber, director of the Mobile Robotics Group at UC3M, highlights the human impact of this technology: “We all know people for whom simple gestures—such as someone bringing them a glass of water with a pill or setting the table for them—make a huge difference.”
A Learning Method Inspired by Living Organisms
However, simply copying isn’t enough. If a bottle moves a few centimeters across a table, a robot that merely repeats a recorded movement will miss it. Real life is chaotic: objects move, people move. To solve this, researchers combined imitation learning with a mathematical method called “Gaussian Belief Propagation.”
Each arm learns its task separately. Then, the two arms share information via this mathematical system. This acts like a constant internal conversation, allowing them to adjust in real time. They avoid collisions with each other and with nearby objects, and they don’t need to stop and replan from scratch. The result is movement that adapts smoothly as conditions change. The researchers describe the learned motion as behaving like a rubber band.
If the target moves, the trajectory stretches and reshapes itself while retaining the main characteristics of the action. If the robot is pouring water, it keeps the bottle upright to prevent spills, even if the cup is in a slightly different location. In a paper presented at IROS 2025 by researchers Adrián Prados and Gonzalo Espinoza, the team demonstrated that this method works both in simulations and on real household robots. Adrián Prados explains the team’s vision: “The ultimate goal is for robots to stop being mere movement recorders and become true colleagues, capable of perceiving their environment, anticipating actions, and collaborating safely in human spaces.”
Under the Hood: Perception, Reasoning, and Action
Internally, ADAM’s operation follows a clear cycle: perception, reasoning, and action. First, it senses the world. It uses 2D and 3D laser sensors to measure distances, detect obstacles, and locate objects. It also relies on RGB cameras with depth information to build three-dimensional models of its environment.
A Necessary Investment in the Face of Demographic Challenges
Ramón Barber concludes by highlighting this societal need: “Every day, there are more elderly people in our society and fewer people who can care for them, so these types of technological solutions will become increasingly necessary.” He adds: “In this context, assistive robots are emerging as a key tool for improving people’s quality of life and independence.”
Source: earth.com
Created by humans, powered by AI.
This new two-armed robot could soon revolutionize home care
This content was created with the help of AI.