Researchers at Universidad Carlos III de Madrid (UC3M), Spain, have developed a new way for their assistive robot, called ADAM, to move its two arms without needing to be manually programmed for every movement. This work was presented at IROS 2025, the world’s leading robotics conference, held in China. The authors believe it could be living in our homes within 15 years.
ADAM, which stands for Autonomous Domestic Ambidextrous Manipulator, was designed specifically to help elderly people with everyday tasks in their homes or in care facilities. “It can, for example, set the table and clear it afterwards, tidy the kitchen, or bring a user a glass of water or medication at the indicated time. It can also help them when they are going out by bringing a coat or an article of clothing,” said Alicia Mora, one of the researchers from UC3M’s Mobile Robots Group.
The key challenge the team tackled was getting the robot’s two arms to work together. Their solution combines two approaches: first, each arm learns a task independently by watching a human demonstrate it; then the two arms are allowed to “talk” to each other through a mathematical system. This allows the arms to coordinate in real time, avoiding collisions with each other and with nearby objects, and without having to stop and recalculate every time something changes.
The result is movement that looks natural and that can adapt when things change. Traditional robot programming requires thousands of lines of code to define every single movement. But if an object moves slightly from where the robot expects it, a rigidly programmed robot will simply fail. The UC3M team’s approach makes the robot’s movements more like a rubber band: if the target shifts, the robot adjusts its path smoothly to reach it, without losing the “essence” of the movement, such as keeping a bottle upright so nothing spills.
“The ultimate goal is for robots to stop being simple movement recorders and become authentic coworkers, capable of perceiving their environment, anticipating actions, and collaborating safely in human spaces,” said researcher Adrián Prados.
The motivation behind the project is rooted in a very human need. “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, represent a very significant help. That is the main objective of our robot,” said Professor Ramón Barber, director of the Mobile Robots Group.
ADAM currently costs between €80,000 and €100,000 to build, making it an experimental platform rather than a consumer product. But the researchers believe the underlying technology is mature enough that robots like it could become affordable household companions within the next decade or so.
The urgency behind that ambition is clear. “Every day there are more elderly people in our society and fewer people who can care for them, so these types of technological solutions are going to become increasingly necessary,” concluded Professor Barber.
Video: https://youtu.be/Ew86EO3wWio
A. Prados, G. Espinoza, L. Moreno and R. Barber, “Coordination of Learned Decoupled Dual-Arm Tasks through Gaussian Belief Propagation,” 2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Hangzhou, China, 2025, pp. 15917-15924, doi: 10.1109/IROS60139.2025.11246414.