Skip to Main content Skip to Navigation
Conference papers

Learning Object Manipulation Skills via Approximate State Estimation from Real Videos

Abstract : Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to obtain. In this paper, we explore a method that facilitates learning object manipulation skills directly from videos. Leveraging recent advances in 2D visual recognition and differentiable rendering, we develop an optimization based method to estimate a coarse 3D state representation for the hand and the manipulated object(s) without requiring any supervision. We use these trajectories as dense rewards for an agent that learns to mimic them through reinforcement learning. We evaluate our method on simple single-and two-object actions from the Something-Something dataset. Our approach allows an agent to learn actions from single videos, while watching multiple demonstrations makes the policy more robust. We show that policies learned in a simulated environment can be easily transferred to a real robot.
Document type :
Conference papers
Complete list of metadata
Contributor : Makarand Tapaswi Connect in order to contact the contributor
Submitted on : Saturday, November 21, 2020 - 5:48:25 AM
Last modification on : Wednesday, November 17, 2021 - 12:33:27 PM
Long-term archiving on: : Monday, February 22, 2021 - 6:23:22 PM


Files produced by the author(s)


  • HAL Id : hal-03017607, version 1
  • ARXIV : 2011.06813



Vladimír Petrík, Makarand Tapaswi, Ivan Laptev, Josef Sivic. Learning Object Manipulation Skills via Approximate State Estimation from Real Videos. CoRL 2020 - Conference on Robot Learning, Nov 2020, Virtual, United States. ⟨hal-03017607⟩



Record views


Files downloads