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.
Research Areas
Akshara's Publications
October 31, 2024
ROBOTICS
PARTNR: A Benchmark for Planning and Reasoning in Embodied Multi-agent Tasks
Gunjan Chhablani, Roozbeh Mottaghi, Akshara Rai, Alexander William Clegg, Daniel Tran, Eric Undersander, Ishita Prasad, Jacob Krantz, Jimmy Yang, Joanne Truong, John Turner, Matthew Chang, Michal Hlavac, Mikael Dallaire Cote, Priyam Parashar, Ram Ramrakhya, Ruta Desai, Siddharth Patki, Vladimir Karashchuk, Xavi Puig
October 31, 2024
March 12, 2024
ROBOTICS
Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
Andrew Szot, Ruslan Partsey, Vladimír Vondruš, Zsolt Kira, Roozbeh Mottaghi, Akshara Rai, Alexander William Clegg, Devendra Singh Chaplot, Dhruv Batra, Eric Undersander, Jimmy Yang, Jitendra Malik, Mikael Dallaire Cote, Mrinal Kalakrishnan, Oleksandr Maksymets, Ruta Desai, Theo Gervet, Tiffany Min, Unnat Jain, Vincent-Pierre Berges, Xavi Puig
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
Roberto Calandra, Akshara Rai, Ben Letham, 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
Our approach
Latest news
Foundational models
Meta © 2026