Researchers at Universidad Carlos III de Madrid (UC3M) have developed a new methodology enabling robots to learn complex movements autonomously, bringing assistive robotics closer to widespread home use. The breakthrough centers on combining observational learning with a system of “intercommunication” between a robot’s limbs, allowing for more adaptable and easily teachable service robots.
Traditionally, programming robots to perform even simple tasks has required painstakingly coding every single movement. The UC3M team’s approach, presented at the IROS 2025 robotics conference, bypasses this laborious process by allowing robots to learn through imitation – mirroring human actions. However, the innovation doesn’t stop at simple copying. The key lies in the robot’s ability to adapt to slight variations in its environment, a capability crucial for real-world application.
Autonomous Domestic Ambidextrous Manipulator Robot
The research focuses on the ADAM robot (Autonomous Domestic Ambidextrous Manipulator), specifically designed for assistive tasks in home settings. ADAM is tackling one of the most significant hurdles in current robotics: coordinating two arms working in tandem. “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,” explains Alicia Mora, a researcher from the UC3M Robotics Lab’s Mobile Robots Group. “It can also help them when they are going out by bringing a coat or an article of clothing.”
ADAM is Currently an Experimental Platform
While currently an experimental platform with an estimated cost of between 80,000 and 100,000 euros, researchers believe the technology is mature enough to suggest that similar robots could be integrated into homes within 10 to 15 years at a significantly more affordable price point. This development arrives at a critical juncture, as the global population ages and the demand for assistive technologies increases.
“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,” says Ramón Barber, director of the Mobile Robots Group at UC3M’s Department of Systems Engineering, and Automation. He emphasizes that assistive robots are emerging as a key tool to improve the quality of life and autonomy of individuals needing support. “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.”
Teaching a Robot to Perform Daily Tasks
The core challenge in robotic manipulation is not simply replicating a movement, but understanding and adapting to changing conditions. Traditional robot programming requires writing thousands of lines of code to define every action. Imitation learning offers a more intuitive alternative: the robot learns by observing and replicating human demonstrations. A human can either directly move the robot’s arm to demonstrate a task or record themselves performing the action – for example, serving water or organizing a shelf.
However, a simple copy-and-paste approach is insufficient. If a robot learns to grasp a bottle in a specific location, and that bottle is slightly moved, a system relying solely on imitation will fail. The goal, according to researchers, is to enable robots to not just mechanically repeat movements, but to understand and adapt to new situations.
The UC3M team’s techniques address this problem by allowing learned movements to behave like a “rubber band.” If the target object changes position, the robot’s trajectory smoothly adjusts to reach it, maintaining the essential characteristics of the action. This allows the robot to adapt to new scenarios without losing crucial elements of the movement, such as keeping a bottle upright to prevent spills.
This “intercommunication” between the robot’s limbs is key to achieving this coordinated movement. The system allows the arms to work together, adjusting to each other’s movements and the changing environment. This represents a significant step forward in the field of multi-arm robotics, which has long been hampered by the complexity of coordinating multiple degrees of freedom.
The development of ADAM and the underlying methodology represent a significant advancement in the quest for truly useful and adaptable domestic robots. While challenges remain in terms of cost and widespread deployment, the UC3M team’s work offers a promising glimpse into a future where robots can provide meaningful assistance to people in their homes, particularly as populations age and the need for assistive technologies grows.
