- Iterative Repair of Social Robot Programs from Implicit User Feedback via Bayesian Inference
- In-Situ Learning from a Domain Expert for Real World Socially Assistive Robot Deployment
- A Motion Taxonomy for Manipulation Embedding
- Reachable Sets for Safe, Real-Time Manipulator Trajectory Design
- Controlling Contact-Rich Manipulation Under Partial Observability
- GTI: Learning to Generalize across Long-Horizon Tasks from Human Demonstrations
- Active Preference-Based Gaussian Process Regression for Reward Learning
- Learning from Interventions: Human-robot interaction as both explicit and implicit feedback
- Concept2Robot: Learning Manipulation Concepts from Instructions and Human Demonstrations
- Explaining Multi-stage Tasks by Learning Temporal Logic Formulas from Suboptimal Demonstrations
- AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos