Ashwin Balakrishna
54 works · 1,281 citations · h-index 17
Top works
- Open X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration 0
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter
- Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor
- Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data
- Safety Augmented Value Estimation From Demonstrations (SAVED): Safe Deep Model-Based RL for Sparse Cost Robotic Tasks
- Learning Dense Visual Correspondences in Simulation to Smooth and Fold Real Fabrics
- VisuoSpatial Foresight for Multi-Step, Multi-Task Fabric Manipulation
- VisuoSpatial Foresight for physical sequential fabric manipulation
- LazyDAgger: Reducing Context Switching in Interactive Imitation Learning
- OpenVLA: An Open-Source Vision-Language-Action Model
- Untangling Dense Non-Planar Knots by Learning Manipulation Features and Recovery Policies
- Deep Imitation Learning of Sequential Fabric Smoothing Policies
- ThriftyDAgger: Budget-Aware Novelty and Risk Gating for Interactive Imitation Learning
- Learning to Smooth and Fold Real Fabric Using Dense Object Descriptors Trained on Synthetic Color Images
- A Taxonomy for Evaluating Generalist Robot Manipulation Policies
- On-Policy Robot Imitation Learning from a Converging Supervisor
- Untangling Dense Knots by Learning Task-Relevant Keypoints
- Disentangling Dense Multi-Cable Knots
- ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions