Continual Learning of Visual Concepts for Robots through Limited Supervision

by   Ali Ayub, et al.

For many real-world robotics applications, robots need to continually adapt and learn new concepts. Further, robots need to learn through limited data because of scarcity of labeled data in the real-world environments. To this end, my research focuses on developing robots that continually learn in dynamic unseen environments/scenarios, learn from limited human supervision, remember previously learned knowledge and use that knowledge to learn new concepts. I develop machine learning models that not only produce State-of-the-results on benchmark datasets but also allow robots to learn new objects and scenes in unconstrained environments which lead to a variety of novel robotics applications.


page 1

page 2

page 3


Continual Learning of Knowledge Graph Embeddings

In recent years, there has been a resurgence in methods that use distrib...

From Continual Learning to Causal Discovery in Robotics

Reconstructing accurate causal models of dynamic systems from time-serie...

Lessons Learned from Real-World Experiments with DyRET: the Dynamic Robot for Embodied Testing

Robots are used in more and more complex environments, and are expected ...

Predictive World Models from Real-World Partial Observations

Cognitive scientists believe adaptable intelligent agents like humans pe...

Cooperative Learning with Visual Attributes

Learning paradigms involving varying levels of supervision have received...

Pour me a drink: Robotic Precision Pouring Carbonated Beverages into Transparent Containers

With the growing emphasis on the development and integration of service ...

Please sign up or login with your details

Forgot password? Click here to reset