Philipp Wu
YOU?
Author Swipe
View article: RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot Manipulation
RoboCopilot: Human-in-the-loop Interactive Imitation Learning for Robot Manipulation Open
Learning from human demonstration is an effective approach for learning complex manipulation skills. However, existing approaches heavily focus on learning from passive human demonstration data for its simplicity in data collection. Intera…
View article: Semi-Supervised One-Shot Imitation Learning
Semi-Supervised One-Shot Imitation Learning Open
One-shot Imitation Learning~(OSIL) aims to imbue AI agents with the ability to learn a new task from a single demonstration. To supervise the learning, OSIL typically requires a prohibitively large number of paired expert demonstrations --…
View article: From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control
From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control Open
Hierarchical control for robotics has long been plagued by the need to have a well defined interface layer to communicate between high-level task planners and low-level policies. With the advent of LLMs, language has been emerging as a pro…
View article: Interactive Task Planning with Language Models
Interactive Task Planning with Language Models Open
An interactive robot framework accomplishes long-horizon task planning and can easily generalize to new goals and distinct tasks, even during execution. However, most traditional methods require predefined module design, making it hard to …
View article: GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators
GELLO: A General, Low-Cost, and Intuitive Teleoperation Framework for Robot Manipulators Open
Humans can teleoperate robots to accomplish complex manipulation tasks. Imitation learning has emerged as a powerful framework that leverages human teleoperated demonstrations to teach robots new skills. However, the performance of the lea…
View article: Masked Trajectory Models for Prediction, Representation, and Control
Masked Trajectory Models for Prediction, Representation, and Control Open
We introduce Masked Trajectory Models (MTM) as a generic abstraction for sequential decision making. MTM takes a trajectory, such as a state-action sequence, and aims to reconstruct the trajectory conditioned on random subsets of the same …
View article: DayDreamer: World Models for Physical Robot Learning
DayDreamer: World Models for Physical Robot Learning Open
To solve tasks in complex environments, robots need to learn from experience. Deep reinforcement learning is a common approach to robot learning but requires a large amount of trial and error to learn, limiting its deployment in the physic…
View article: Quasi-Direct Drive for Low-Cost Compliant Robotic Manipulation
Quasi-Direct Drive for Low-Cost Compliant Robotic Manipulation Open
Robots must cost less and be force-controlled to enable widespread, safe deployment in unconstrained human environments. We propose Quasi-Direct Drive actuation as a capable paradigm for robotic force-controlled manipulation in human envir…