most citedLearning 3D Dynamic Scene Representations for Robot Manipulation

21 citations · 21 across the 1 of their papers we have counts for

collaborators
Showing cs.ROShow all

6 papers · 1 filter

cs.RO2023

Pick2Place: Task-aware 6DoF Grasp Estimation via Object-Centric Perspective Affordance

Zhanpeng He, Nikhil Chavan-Dafle, Jinwook Huh +2

The choice of a grasp plays a critical role in the success of downstream manipulation tasks. Consider a task of placing an object in a cluttered scene; the majority of possible gra…

cs.RO2023

Decision Making for Human-in-the-loop Robotic Agents via Uncertainty-Aware Reinforcement Learning

Siddharth Singi, Zhanpeng He, Alvin Pan +5

In a Human-in-the-Loop paradigm, a robotic agent is able to act mostly autonomously in solving a task, but can request help from an external expert when needed. However, knowing wh…

cs.RO202021 cited

Learning 3D Dynamic Scene Representations for Robot Manipulation

Zhenjia Xu, Zhanpeng He, Jiajun Wu +1

3D scene representation for robot manipulation should capture three key object properties: permanency -- objects that become occluded over time continue to exist; amodal completene…

cs.RO2020

Hardware as Policy: Mechanical and Computational Co-Optimization using Deep Reinforcement Learning

Tianjian Chen, Zhanpeng He, Matei Ciocarlie

Deep Reinforcement Learning (RL) has shown great success in learning complex control policies for a variety of applications in robotics. However, in most such cases, the hardware o…

cs.RO2020

SQUIRL: Robust and Efficient Learning from Video Demonstration of Long-Horizon Robotic Manipulation Tasks

Bohan Wu, Feng Xu, Zhanpeng He +2

Recent advances in deep reinforcement learning (RL) have demonstrated its potential to learn complex robotic manipulation tasks. However, RL still requires the robot to collect a l…

cs.RO2018

Simulator Predictive Control: Using Learned Task Representations and MPC for Zero-Shot Generalization and Sequencing

Zhanpeng He, Ryan Julian, Eric Heiden +5

Simulation-to-real transfer is an important strategy for making reinforcement learning practical with real robots. Successful sim-to-real transfer systems have difficulty producing…