Somrita Banerjee
Papers
2
Total Citations
31
H-Index
2
About
Somrita Banerjee is a rising leader in the intersection of robotics, optimization, and trustworthy autonomy. Her research focuses on developing algorithms that make robotic systems both faster and more reliable, with particular emphasis on trajectory optimization and robust learning-based control. In her highly cited 2020 work, Banerjee pioneered a learning-based warm-starting approach for Sequential Convex Programming (SCP), dramatically accelerating the computation of locally optimal trajectories for aerospace and robotic systems—even when starting from infeasible initial guesses. This contribution has become foundational for real-time motion planning in safety-critical domains. More recently, her 2022 system-level analysis of out-of-distribution (OOD) data in robotics has shaped how the field approaches the reliability of learned components in modern autonomy stacks. By identifying the vulnerabilities of perception and control modules to distributional shift, Banerjee has charted a path toward more trustworthy, learning-enabled robots. With her work bridging theoretical rigor and practical deployment, she is establishing herself as a key voice in the next generation of autonomous systems research.
Research Focus
Key Achievements
Top Papers
- 1
- 2A System-Level View on Out-of-Distribution Data in Robotics7 citations · 2022