Avatar

Ahalya Prabhakar

Assistant Professor

University of Sydney, Department of Aerospace, Mechanical and Mechatronic Engineering (AMME)

Biography

I am an incoming Assistant Professor at the University of Sydney in the Department of Aerospace, Mechanical and Mechatronic Engineering. My research explores human-robot interaction and collaboration through robot learning and optimal control. I focus on developing useful algorithmic interfaces for humans to intuitively interact with and control complex, dynamic robotic systems. Previously, I was a postdoctoral researcher in the Learning Algorithms and Systems (LASA) lab at EPFL, where I worked on multimodal sensory learning for safe manipulation and adaptive safety controllers for human-robot collaboration. I obtained my Ph.D. at Northwestern University, where my research focused on algorithms for intuitive human-robot collaboration and efficient robot learning. I led Northwestern’s team for the DARPA OFFSET Urban Swarm Challenge, developing autonomous swarm algorithms for shared human-swarm collaboration under dynamic, time-sensitive constraints. Prior to joining the University of Sydney, I served as an Associate Research Scientist and Lecturer at Yale University in the Department of Mechanical Engineering.

Interests

  • Human-Robot Collaboration and Learning
  • Sensor Modeling and Learning
  • Information-Theoretic Algorithms
  • High-Dimensional Robot Learning

Education

  • PhD in Mechanical Engineering, 2020

    Northwestern University

  • MSc in Mechanical Engineering, 2016

    Northwestern University

  • BSc in Mechanical Engineering, 2013

    California Institute of Technology

Recent Posts

Projects

Learning Interpretable Action-Perception Models

As robotic systems are deployed with varying sensor modalities, especially in novel scenarios, it is important for the robot to build …

Optimal Interface Design for Human-Robot Collaboration

Designing interpretable, multimodal interfaces for intuitive human-robot interaction and collaboration

Principled Methods for Human-Robot Collaborative Learning and Control

Enabling seamless human-robot collaboration while ensuring task success requires the reduction of the task information to its essential …

Recent Publications

A Predictive Model for Tactile Force Estimation using Audio-Tactile Data

Robust in-hand manipulation of objects with movable content requires estimation and prediction of the contents’ motion with …

Active Exploration for Real-Time Haptic Training

Tactile perception is important for robotic systems that interact with the world through touch. Touch is an active sense in which …

Collaborative robots can augment human cognition in regret-sensitive tasks

Despite theoretical benefits of collaborative robots, disappointing outcomes are well documented by clinical studies, spanning …

Measuring Human-Robot Team Benefits Under Time Pressure in a Virtual Reality Testbed

During a natural disaster such as hurricane, earthquake, or fre, robots have the potential to explore vast areas and provide valuable …

Contact