Continual Learning of Visual Concepts for Robots through Limited Supervision
This addresses the challenge for robots to adapt in dynamic real-world scenarios with scarce supervision, though it appears incremental as it builds on existing continual learning methods.
The research tackles the problem of enabling robots to continually learn new visual concepts with limited labeled data, achieving state-of-the-art results on benchmark datasets and allowing robots to learn objects and scenes in unconstrained environments.
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.