Apoorva Sharma
Papers
1
Total Citations
7
H-Index
1
About
Apoorva Sharma is a robotics researcher whose work centers on the critical intersection of machine learning reliability and autonomous systems. Specializing in out-of-distribution (OOD) data detection and trustworthy robot autonomy, Sharma has made meaningful contributions to understanding how learning-enabled systems fail when encountered with unfamiliar conditions during deployment. Sharma's most recognized work, "A System-Level View on Out-of-Distribution Data in Robotics" (2022), has garnered 7 citations and represents a significant step toward framing OOD challenges not as isolated algorithmic problems, but as system-wide concerns affecting the entire robot autonomy stack. This perspective shift — from component-level to system-level thinking — is particularly valuable as the robotics community increasingly deploys learned models in safety-critical real-world environments. Sharma's research addresses one of the most pressing open problems in deploying autonomous systems responsibly: ensuring robots can recognize when they are operating outside the bounds of their training experience. This work is especially relevant for students and researchers interested in robot safety, uncertainty quantification, and the practical challenges of bridging the sim-to-real gap in modern autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1A System-Level View on Out-of-Distribution Data in Robotics7 citations · 2022