Learning to Represent Surroundings, Anticipate Motion and Take Informed Actions in Unstructured Environments
This work tackles the problem of robot adaptability in dynamic, unstructured environments for robotics applications, representing an incremental advancement in learning-based approaches.
The thesis addresses the challenge of robots failing in unstructured environments by developing learning-based methods to understand surroundings, anticipate motion, and take informed actions, aiming to improve adaptability beyond pre-defined rules.
Contemporary robots have become exceptionally skilled at achieving specific tasks in structured environments. However, they often fail when faced with the limitless permutations of real-world unstructured environments. This motivates robotics methods which learn from experience, rather than follow a pre-defined set of rules. In this thesis, we present a range of learning-based methods aimed at enabling robots, operating in dynamic and unstructured environments, to better understand their surroundings, anticipate the actions of others, and take informed actions accordingly.