Nathan Ratliff

Latest

• CuRobo: Parellelized Collision-Free Robot Motion Generation
• Global and Reactive Motion Generation with Geometric Fabric Command Sequences
• Neural Geometric Fabrics: Efficiently Learning High-Dimensional Policies from Demonstration
• Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees
• Generalized Nonlinear and Finsler Geometry for Robotics
• RMP2 : A Differentiable Policy Class with Control-Theoretic Guarantees
• RMPflow: A Geometric Framework for Generation of Multi-Task Motion Policies
• Towards Coordinated Robot Motions: End-to-End Learning of Motion Policies on Transform Trees
• Collaborative Interaction Models for Optimized Human-Robot Teamwork
• DexPilot: Depth-Based Teleoperation of Dexterous Robotic Hand-Arm System
• Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systems
• Guided Uncertainty-Aware Policy Optimization: Combining Model-Free and Model-Based Strategies for Sample-Efficient Learning
• Model-based Generalization under Parameter Uncertainty using Path Integral Control
• Scaling Local Control to Large-Scale Topological Navigation
• Combining Model-Free and Model-Based Strategies for Sample-Efficient Reinforcement Learning
• RMPflow: A Computational Graph for Automatic Motion Policy Generation
• Representing Robot Task Plans as Robust Logical-Dynamical Systems
• Learning Reactive Motion Policies in Multiple Task Spaces from Human Demonstrations
• Riemannian Motion Policy Fusion through Learnable Lyapunov Function Reshaping
• Predictor Corrector Policy Optimization
• Robust Learning of Tactile Force Estimation through Robot Interaction
• Riemannian Motion Policies