activity
20122022
most citedDeep Convolutional Inverse Graphics Network

747 citations · 2.1k across the 73 of their papers we have counts for

collaborators
Showing cs.ROShow all

13 papers · 1 filter

cs.RO2022

H-SAUR: Hypothesize, Simulate, Act, Update, and Repeat for Understanding Object Articulations from Interactions

Kei Ota, Hsiao-Yu Tung, Kevin A. Smith +5

The world is filled with articulated objects that are difficult to determine how to use from vision alone, e.g., a door might open inwards or outwards. Humans handle these objects…

cs.RO20224 cited

Contact Points Discovery for Soft-Body Manipulations with Differentiable Physics

Sizhe Li, Zhiao Huang, Tao Du +3

Differentiable physics has recently been shown as a powerful tool for solving soft-body manipulation tasks. However, the differentiable physics solver often gets stuck when the ini…

cs.RO2022

DURableVS: Data-efficient Unsupervised Recalibrating Visual Servoing via online learning in a structured generative model

Nishad Gothoskar, Miguel Lázaro-Gredilla, Yasemin Bekiroglu +4

Visual servoing enables robotic systems to perform accurate closed-loop control, which is required in many applications. However, existing methods either require precise calibratio…

cs.RO20211 cited

OPEn: An Open-ended Physics Environment for Learning Without a Task

Chuang Gan, Abhishek Bhandwaldar, Antonio Torralba +2

Humans have mental models that allow them to plan, experiment, and reason in the physical world. How should an intelligent agent go about learning such models? In this paper, we wi…

cs.RO2021

Discovering State and Action Abstractions for Generalized Task and Motion Planning

Aidan Curtis, Tom Silver, Joshua B. Tenenbaum +2

Generalized planning accelerates classical planning by finding an algorithm-like policy that solves multiple instances of a task. A generalized plan can be learned from a few train…

cs.RO2021

Dynamic Modeling of Hand-Object Interactions via Tactile Sensing

Qiang Zhang, Yunzhu Li, Yiyue Luo +6

Tactile sensing is critical for humans to perform everyday tasks. While significant progress has been made in analyzing object grasping from vision, it remains unclear how we can u…