Related Experiment Video
Updated: Jul 12, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
Published on: March 2, 2015
From real-time adaptation to social learning in robot ecosystems
Alex Szorkovszky1,2, Frank Veenstra1,2, Kyrre Glette1,2
1RITMO Centre for Interdisciplinary Studies in Rhythm, Time and Motion, University of Oslo, Oslo, Norway.
This study introduces social learning for robots, enabling them to adapt quickly to environmental changes. Robots synchronize movements to learn new gaits, fostering diversity and potentially creating adaptable generalist robots.
Area of Science:
- Robotics
- Artificial Intelligence
- Evolutionary Computation
Background:
- Evolutionary robotics excels at creating adapted morphologies and controllers.
- Short-term environmental adaptation in robots is most efficiently achieved through learning.
- Existing robot learning methods often involve starting from scratch or using data from direct ancestors.
Purpose of the Study:
- To propose and demonstrate a novel social learning method for robot gait patterns.
- To leverage sensorimotor synchronization for inter-robot learning.
- To explore the potential for emergent generalist behaviors in robot populations.
Main Methods:
- Utilizing movement patterns of other robots as input for decentralized controllers like Central Pattern Generators (CPGs).
- Employing sensorimotor synchronization to drive CPGs into new, diverse limit cycles.
- Implementing a quasi-Hebbian feedback scheme to stabilize learned autonomous controllers.
Main Results:
- Demonstrated that movement patterns from other robots can induce novel gait patterns in decentralized controllers.
- Showcased the ability to lock in stable autonomous controllers through a quasi-Hebbian feedback mechanism.
- Provided a framework for social learning in robotic systems.
Conclusions:
- Social learning via sensorimotor synchronization offers an efficient adaptation mechanism for robots.
- This approach encourages movement diversity and can lead to the emergence of generalist task-solvers.
- The proposed method has implications for robot populations evolving in heterogeneous environments.
Related Concept Videos
Observational Learning
Nonconscious Mimicry
Cognitive Learning
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Avoidance Learning and Learned Helplessness
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...
Associative Learning
Classical conditioning, also known...
Natural Selection and Adaptation
Beyond physical adaptations,...

