Rohan Paul

Unsupervised Learning of Neuro-symbolic Rules for Generalizable Context-aware Planning in Object Arrangement Tasks

2024

As robots tackle complex object arrangement tasks, it becomes imperative for them to be able to generalize to complex worlds and scale with number of objects. This work postulates that extracting action primitives, such as …

Efficient Grounding of Abstract Spatial Concepts for Natural Language Interaction with Robot Manipulators

2016

Our goal is to develop models that allow a robot to understand natural language instructions in the context of its world representation. Contemporary models learn possible correspondences between parsed instructions and candidate groundings that include …