Top of page

Student/Staff Portal
Global Site Navigation

School of Science

Local Section Navigation
You are here: Main Content

Related Contents

  • See Also
  • ORCiD profile
    https://orcid.org/0000-0002-1550-1129
  • ORCiD profile
  • ResearchGate profile
    https://www.researchgate.net/profile/Muraleekrishna-Gopinathan
  • ResearchGate profile
  • LinkedIn profile
    https://www.linkedin.com/in/gmuraleekrishna/
  • LinkedIn profile
  • Google Scholar profile
    https://scholar.google.com/citations?user=hMIUoZsAAAAJ
  • Google Scholar profile

Muraleekrishna Gopinathan

Overview of thesis

Title: Towards Embodied Navigation through Vision and Language

Abstract: Embodied AI seeks to create autonomous systems that assist humans in completing challenging tasks. Embodiment denotes the agents' ability to understand and interact with the environment based on informed reasoning. Their use in service and industrial robotics makes them relevant and powerful.

These agents must perceive the real world through various sensors, reason about the possible actions, interact and communicate with the humans for clarification about the task, and act based on their understanding While embodied AI is a challenging task, we selected a sub-problem called vision and language navigation (VLN), where the agent follows natural language commands to navigate inside an indoor environment. Here, vision serves as an important sensory input for perception and reasoning about the environment. Visual semantics such as object category, location, object-object relationships, object-place relationships, and environment geometry can be used to ground or connect to natural language instructions. The objective of this project is to investigate methods to improve vision and language navigation by leveraging the various semantics from visual models and efficiently ground them using natural language instructions. This work aims to develops methods that extract meaningful information from language and vision to enable navigation in an unseen environment.

Qualifications

  • Master of Engineering (Mechatronics), Australian National University, ACT, (2018-2019)
  • Bachelor of Technology (Electronics and Communication Engineering), Mahatma Gandhi University, India, (2010-2014)

Research

Research Interests

  • Embodied AI
  • Visual Navigation
  • Computer Vision
  • Semantic Understanding

Past Research employment history

  • 2021-2022 Research Assistant, CAIML

Other work

  • 2019: Data Science Engineer, Hitachi STS Australia
  • 2018-2019: Avionics Engineer (Lead), ANU Rocketry
  • 2014-2018 Software Engineer, Aconex India Pvt. Ltd.

Past Teaching

  • ENGN8200: Introduction to Systems Engineering, Sem 1 (ANU)
  • ENGN6213: Digital Systems and Microprocessors, Sem 2 (ANU)

Scholarships and Awards

  • 2021 ECU Vice Chancellor’s PhD by Research Scholarship

Supervisors

Contact

Muraleekrishna Gopinathan
PhD Student
Centre for Artificial Intelligence and Machine Learning
School of Science
Skip to top of page