Perception and Mapping for Navigation

Learning-assisted map representation and navigation with mobile robots.

My research leverages machine learning techniques to develop sparse map represenations with efficient collision checking and to assist motion planners in robot navigation.

project thumbnail

Autonomous Navigation in Unknown Environments with Sparse Bayesian Kernel-based Occupancy Mapping

We develop an online learning-based occupancy mapping based on Relevance Vector Machines and real-time collision checking for general curves onboard an autonomous robot navigating in a large unknown environment.

T-RO'22, ICRA'20
project thumbnail

Optimal Scene Graph Planning with Large Language Model Guidance

We consider a scene graph representation of the environment and utilize a large language model (LLM) to convert a natural language task into a linear temporal logic (LTL) automaton and generate a heuristic guidance for optimal hierarchical LTL planning.

ICRA'24