activity
20162022
most citedRearrangement: A Challenge for Embodied AI

101 citations · 252 across the 19 of their papers we have counts for

collaborators
Showing 2019Show all

10 papers · 1 filter

cs.CV2019

Sim2Real Predictivity: Does Evaluation in Simulation Predict Real-World Performance?

Abhishek Kadian, Joanne Truong, Aaron Gokaslan +6

Does progress in simulation translate to progress on robots? If one method outperforms another in simulation, how likely is that trend to hold in reality on a robot? We examine thi…

cs.RO20198 cited

Tool Substitution with Shape and Material Reasoning Using Dual Neural Networks

Nithin Shrivatsav, Lakshmi Nair, Sonia Chernova

This paper explores the problem of tool substitution, namely, identifying substitute tools for performing a task from a given set of candidate tools. We introduce a novel approach…

cs.RO20191 cited

Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance

M. Asif Rana, Daphne Chen, S. Reza Ahmadzadeh +3

In this work, we contribute a large-scale study benchmarking the performance of multiple motion-based learning from demonstration approaches. Given the number and diversity of exis…

cs.RO2019

CAGE: Context-Aware Grasping Engine

Weiyu Liu, Angel Daruna, Sonia Chernova

Semantic grasping is the problem of selecting stable grasps that are functionally suitable for specific object manipulation tasks. In order for robots to effectively perform object…

cs.LG20191 cited

Active Learning within Constrained Environments through Imitation of an Expert Questioner

Kalesha Bullard, Yannick Schroecker, Sonia Chernova

Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic huma…

cs.LG2019

Leveraging Semantics for Incremental Learning in Multi-Relational Embeddings

Angel Daruna, Weiyu Liu, Zsolt Kira +1

Service robots benefit from encoding information in semantically meaningful ways to enable more robust task execution. Prior work has shown multi-relational embeddings can encode s…