activity
20182024
most citedWhat Matters in Learning from Offline Human Demonstrations for Robot Manipulation

71 citations · 93 across the 7 of their papers we have counts for

collaborators
Showing cs.ROShow all

11 papers · 1 filter

cs.RO20244 cited

AHA: A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

Jiafei Duan, Wilbert Pumacay, Nishanth Kumar +7

Robotic manipulation in open-world settings requires not only task execution but also the ability to detect and learn from failures. While recent advances in vision-language models…

cs.RO2024

IntervenGen: Interventional Data Generation for Robust and Data-Efficient Robot Imitation Learning

Ryan Hoque, Ajay Mandlekar, Caelan Garrett +2

Imitation learning is a promising paradigm for training robot control policies, but these policies can suffer from distribution shift, where the conditions at evaluation time diffe…

cs.RO202171 cited

What Matters in Learning from Offline Human Demonstrations for Robot Manipulation

Ajay Mandlekar, Danfei Xu, Josiah Wong +7

Imitating human demonstrations is a promising approach to endow robots with various manipulation capabilities. While recent advances have been made in imitation learning and batch…

cs.RO2021

Learning Latent Actions to Control Assistive Robots

Dylan P. Losey, Hong Jun Jeon, Mengxi Li +5

Assistive robot arms enable people with disabilities to conduct everyday tasks on their own. These arms are dexterous and high-dimensional; however, the interfaces people must use…

cs.RO2021

Generalization Through Hand-Eye Coordination: An Action Space for Learning Spatially-Invariant Visuomotor Control

Chen Wang, Rui Wang, Ajay Mandlekar +3

Imitation Learning (IL) is an effective framework to learn visuomotor skills from offline demonstration data. However, IL methods often fail to generalize to new scene configuratio…

cs.RO2020

Learning Multi-Arm Manipulation Through Collaborative Teleoperation

Albert Tung, Josiah Wong, Ajay Mandlekar +4

Imitation Learning (IL) is a powerful paradigm to teach robots to perform manipulation tasks by allowing them to learn from human demonstrations collected via teleoperation, but ha…