collaborators
Showing cs.ROShow all

5 papers · 1 filter

cs.RO2026

Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering

Hao Wang, Jiuzhou Lei, Dayou Li +5

Behavior-cloned policies often learn multiple behavior modes from demonstration datasets, including modes that are unsafe or otherwise undesired at deployment. For example, a polic…

cs.RO2026

Learning Actionable Manipulation Recovery via Counterfactual Failure Synthesis

Dayou Li, Jiuzhou Lei, Hao Wang +6

While recent foundation models have significantly advanced robotic manipulation, these systems still struggle to autonomously recover from execution errors. Current failure-learnin…

cs.RO2024

Learning Instruction-Guided Manipulation Affordance via Large Models for Embodied Robotic Tasks

Dayou Li, Chenkun Zhao, Shuo Yang +3

We study the task of language instruction-guided robotic manipulation, in which an embodied robot is supposed to manipulate the target objects based on the language instructions. I…

cs.RO2024

Where to Fetch: Extracting Visual Scene Representation from Large Pre-Trained Models for Robotic Goal Navigation

Yu Li, Dayou Li, Chenkun Zhao +3

To complete a complex task where a robot navigates to a goal object and fetches it, the robot needs to have a good understanding of the instructions and the surrounding environment…

cs.RO2024

MPGNet: Learning Move-Push-Grasping Synergy for Target-Oriented Grasping in Occluded Scenes

Dayou Li, Chenkun Zhao, Shuo Yang +3

This paper focuses on target-oriented grasping in occluded scenes, where the target object is specified by a binary mask and the goal is to grasp the target object with as few robo…