Richa Verma
Papers
1
Total Citations
7
H-Index
1
About
Richa Verma is a researcher at the intersection of robotics, reinforcement learning, and combinatorial optimization. Her most-cited work, "A Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing" (2020, 7 citations), introduces a Deep RL framework that tackles the notoriously difficult online 3D bin-packing problem. Crucially, her algorithm is designed not just for theoretical efficiency, but for physical realizability—the packing decisions it generates can be executed by a real robotic loading arm. This focus on bridging the simulation-to-reality gap is a hallmark of her contributions. By generalizing the solution to accommodate any number of bins and arbitrary bin sizes, Verma has provided a flexible, scalable approach for logistics and warehouse automation. Her work demonstrates a rare combination of algorithmic depth and practical engineering, using a laboratory prototype to validate her method. For students and researchers in robotics and operations research, Verma’s research offers a compelling model of how to develop AI-driven solutions that are both mathematically rigorous and deployable in the physical world.
Research Focus
Key Achievements
Top Papers
- 1A Generalized Reinforcement Learning Algorithm for Online 3D Bin-Packing7 citations · 2020