Search Results - "Srirama, Mohan Kumar"

HRP: Human Affordances for Robotic Pre-Training by Srirama, Mohan Kumar, Dasari, Sudeep, Bahl, Shikhar, Gupta, Abhinav

“…In order to *generalize* to various tasks in the wild, robotic agents will need a suitable representation (i.e., vision network) that enables the robot to…”
Get full text

An Unbiased Look at Datasets for Visuo-Motor Pre-Training by Dasari, Sudeep, Srirama, Mohan Kumar, Jain, Unnat, Gupta, Abhinav

“…Visual representation learning hold great promise for robotics, but is severely hampered by the scarcity and homogeneity of robotics datasets. Recent works…”
Get full text

The Ingredients for Robotic Diffusion Transformers by Dasari, Sudeep, Mees, Oier, Zhao, Sebastian, Srirama, Mohan Kumar, Levine, Sergey

“…In recent years roboticists have achieved remarkable progress in solving increasingly general tasks on dexterous robotic hardware by leveraging high capacity…”
Get full text

Manipulate by Seeing: Creating Manipulation Controllers from Pre-Trained Representations by Wang, Jianren, Dasari, Sudeep, Srirama, Mohan Kumar, Tulsiani, Shubham, Gupta, Abhinav

“…The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far…”
Get full text

Train Offline, Test Online: A Real Robot Learning Benchmark by Zhou, Gaoyue, Dean, Victoria, Srirama, Mohan Kumar, Rajeswaran, Aravind, Pari, Jyothish, Hatch, Kyle, Jain, Aryan, Yu, Tianhe, Abbeel, Pieter, Pinto, Lerrel, Finn, Chelsea, Gupta, Abhinav

“…Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do…”
Get full text

Train Offline, Test Online: A Real Robot Learning Benchmark by Zhou, Gaoyue, Dean, Victoria, Srirama, Mohan Kumar, Rajeswaran, Aravind, Pari, Jyothish, Hatch, Kyle, Jain, Aryan, Yu, Tianhe, Abbeel, Pieter, Pinto, Lerrel, Finn, Chelsea, Gupta, Abhinav

“…Three challenges limit the progress of robot learning research: robots are expensive (few labs can participate), everyone uses different robots (findings do…”
Get full text