Akshara Rai

RESEARCH SCIENTIST | MENLO PARK, UNITED STATES

Akshara is a Research Scientist at Facebook AI Research, working at the intersection of machine learning and control. Her research aims at teaching robots to perform novel tasks in very few trials, by utilizing models, simulators, or data from previously learned tasks. She is focussed on bringing mobile robot platforms, in particular legged systems, to the real-world, by utilizing supervised, unsupervised and reinforcement learning along with control theory.

Akshara's Publications

March 12, 2024

ROBOTICS

Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots

Xavi Puig, Eric Undersander, Andrew Szot, Mikael Dallaire Cote, Jimmy Yang, Ruslan Partsey, Ruta Desai, Alexander William Clegg, Tiffany Min, Vladimír Vondruš, Theo Gervet, Vincent-Pierre Berges, Oleksandr Maksymets, Zsolt Kira, Mrinal Kalakrishnan, Jitendra Malik, Devendra Singh Chaplot, Unnat Jain, Dhruv Batra, Akshara Rai, Roozbeh Mottaghi

March 12, 2024

September 19, 2023

COMPUTER VISION

EgoTV: Egocentric Task Verification from Natural Language Task Descriptions

Ruta Desai, Akshara Rai, Brian Chen, Nitin Kamra, Rishi Hazra

September 19, 2023

March 29, 2023

ROBOTICS

Adaptive Skill Coordination for Robotic Mobile Manipulation

Akshara Rai, Alexander William Clegg, Dhruv Batra, Eric Undersander, Naoki Yokoyama, Sehoon Ha

March 29, 2023

July 11, 2022

Vision-aided Dynamic Quadrupedal Locomotion on Discrete Terrain using Motion Libraries

Akshara Rai, Ayush Agrawal, Koushil Sreenath, Shuxiao Chen

July 11, 2022

July 07, 2022

Learning-based Initialization Strategy for Safety of Multi-Vehicle Systems

Akshara Rai, Jennifer C. Shih, Laurent El Ghaoui

July 07, 2022

March 25, 2021

ROBOTICS

REINFORCEMENT LEARNING

Re-Examining Linear Embeddings for High-Dimensional Bayesian Optimization

Ben Letham, Roberto Calandra, Akshara Rai, Eytan Bakshy

March 25, 2021

November 24, 2020

RESEARCH

A Framework for Online Updates to Safe Sets for Uncertain Dynamics

Akshara Rai, Franziska Meier, Jennifer Shih

November 24, 2020