2 citations · 2 across the 5 of their papers we have counts for
7 papers
RoboFQE: Rollout-Free Evaluation of Visual Robot Policies from Offline Trajectories
Yunfu Deng, Sangwoo Shin, Brahma S. Pavse +1
Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world models. These rollout-based app…
Grasp2Twist: Learning Bimanual Dexterous Jar Opening by Reinforcement Learning
Mo Xu, Yunfu Deng, Jianuo Wang +2
This paper presents Grasp2Twist, a bimanual dexterous manipulation system that learns to grasp and twist open jar lids using reinforcement learning. Learning this task raises three…
BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer
Yunfu Deng, Josiah P. Hanna
Sim2real transfer for robot policy learning suffers due to mismatch between simulation and reality. Existing methods typically address each gap in isolation through separate adapta…
Abstract Sim2Real through Approximate Information States
Yunfu Deng, Yuhao Li, Josiah P. Hanna
In recent years, reinforcement learning (RL) has shown remarkable success in robotics when a fast and accurate simulator is available for a given task. When using RL and simulation…
Fine-Grained Instruction-Guided Graph Reasoning for Vision-and-Language Navigation
Yaohua Liu, Binkai Ou, Rong Fu +2
Vision and Language Navigation (VLN) requires an embodied agent to traverse complex environments by following natural language instructions, demanding accurate alignment between vi…
Self-Supervised Learning of Object Segmentation from Unlabeled RGB-D Videos
Shiyang Lu, Yunfu Deng, Abdeslam Boularias +1
This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which…
USHER: Unbiased Sampling for Hindsight Experience Replay
Liam Schramm, Yunfu Deng, Edgar Granados +1
Dealing with sparse rewards is a long-standing challenge in reinforcement learning (RL). Hindsight Experience Replay (HER) addresses this problem by reusing failed trajectories for…