April Chan
Papers
1
Total Citations
5
H-Index
1
About
April Chan is a leading researcher in robot learning, with a focus on bridging the gap between simulation and real-world deployment. Her work centers on robust manipulation, imitation learning, and reinforcement learning, where she develops methods that enable robots to adapt autonomously to dynamic environments. Her most-cited paper, "Reconciling Reality through Simulation: A Real-to-Sim-to-Real Approach for Robust Manipulation" (2024, 5 citations), introduces a novel framework that combines the efficiency of imitation learning with the exploration capabilities of reinforcement learning. By iteratively transferring policies from real-world demonstrations to simulation and back, Chan’s approach reduces human supervision while enhancing robustness to object pose changes, physical disturbances, and visual distractors—a critical step toward practical, generalizable robotic systems. Though early in her career, her work has already garnered attention for its potential to streamline robot training. Chan’s contributions are particularly notable for addressing a key bottleneck in robotics: the trade-off between data efficiency and policy robustness. Her research promises to accelerate the deployment of autonomous robots in unstructured settings, from warehouses to homes.
Research Focus
Key Achievements
Top Papers
- 1