Project Overview

We are seeking one or more Postdoctoral Associates in computer science to join the “Towards an Immersive Workplace” project. This project is part of  Task “T1” of a five-year, ambitious research program on "Mens, Manus and Machina—How AI Empowers People, Institutions and Cities in Singapore (M3S)."

Successful applicants for this position will have the opportunity to work on cutting-edge research that builds new capabilities for AI-enhanced human-robot interaction, with a special focus on supporting multi-modal natural instruction comprehension in industrial environments, such as airport tarmacs and logistics warehouses.  The end goal is to build exciting new capabilities that allow robots and humans to work together, interactively and in close proximity, such that the robotic actions are controlled by commands and queries that humans would issue naturally in untethered, field settings.

This research will specifically look at the integration of 3D point-cloud data, generated by LIDAR sensors, into multi-modal instruction comprehension DNN models that additionally combine visual, verbal and gestural cues. Such comprehension will allow robots to clearly define a set of physical manipulation tasks, overcoming potential ambiguity and errors associated with comprehending instructions in cluttered and complex environments. Given the current state-of-the-art, the project will initially focus on tackling two novel challenges: (i) incorporating human and object kinematics into environmental context via use of temporal history of 3D sensing data, and (ii) developing DNN optimization techniques to support lightweight, accurate inference on resource-constrained embedded/robotic platforms. As subsequent steps, the research will explore how this process of comprehension can be further optimized by including awareness of the human instructor’s cognitive attention, which will be captured via advanced wearable devices being developed in complementary efforts within the overall T1 project.

The T1 team is led by distinguished scholars, including Profs. Sanjay Sarma, Daniela Rus and Jinhua Zhang from MIT; and Prof. Archan Misra from Singapore Management University. The proposed research described above will be spearheaded by Prof. Misra.

Job Description

• Conduct and coordinate research on the design, development and testing of optimized algorithms for multi-modal human instruction comprehension.
• Publish research results in top-tier conferences and journals, with focus on venues associated with human-robot interaction, mobile/embedded systems, AI and multimedia.
• Participate in the mentorship and training of graduate and undergraduate students at MIT and in Singapore.
• Assist in grant writing, project management, and other administrative duties related to research activities.

Job Requirements

• Ph.D. in Computer Science, including Artificial Intelligence and Machine Learning, Mobile/Wearable Computing, Human-Robot Interaction and Multimedia Systems.
• Experience in deep learning (audio, image), spatial and 3D computing and/or robotic systems applications highly desired.
• Strong publication record in top-tier conferences and journals.
• DESIRABLE: Demonstrated ability to conduct inter-disciplinary research with a systems focus.
• Excellent communication and collaboration skills.

This role is primarily based in Singapore and appointment is on a two-year contract, with the possibility of extension.

If you want to find out more about the role, please contact Professor Archan Misra  (archanm@smu.edu.sg). 

Interested applicants are invited to send in their full CV/resume, cover letter and list of three references (to include reference names and contact information). We regret that only shortlisted candidates will be notified.