Picture for Carl Qi

Carl Qi

Robot Air Hockey: A Manipulation Testbed for Robot Learning with Reinforcement Learning

Add code
May 06, 2024
Viaarxiv icon

Learning Generalizable Tool-use Skills through Trajectory Generation

Oct 06, 2023
Figure 1 for Learning Generalizable Tool-use Skills through Trajectory Generation
Figure 2 for Learning Generalizable Tool-use Skills through Trajectory Generation
Figure 3 for Learning Generalizable Tool-use Skills through Trajectory Generation
Figure 4 for Learning Generalizable Tool-use Skills through Trajectory Generation
Viaarxiv icon

Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation

Oct 27, 2022
Figure 1 for Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
Figure 2 for Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
Figure 3 for Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
Figure 4 for Planning with Spatial-Temporal Abstraction from Point Clouds for Deformable Object Manipulation
Viaarxiv icon

Learning Closed-loop Dough Manipulation Using a Differentiable Reset Module

Jul 11, 2022
Figure 1 for Learning Closed-loop Dough Manipulation Using a Differentiable Reset Module
Figure 2 for Learning Closed-loop Dough Manipulation Using a Differentiable Reset Module
Figure 3 for Learning Closed-loop Dough Manipulation Using a Differentiable Reset Module
Figure 4 for Learning Closed-loop Dough Manipulation Using a Differentiable Reset Module
Viaarxiv icon

Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning

Apr 18, 2022
Figure 1 for Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning
Figure 2 for Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning
Figure 3 for Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning
Figure 4 for Imitating, Fast and Slow: Robust learning from demonstrations via decision-time planning
Viaarxiv icon