Shubhanshu Shekhar
Papers
1
Total Citations
2
H-Index
1
About
Shubhanshu Shekhar develops principled frameworks for safe autonomous decision-making under uncertainty, bridging control theory, learning, and robotics. His work centers on ensuring that robots can explore unknown environments and learn about their dynamics without violating safety constraints—a critical challenge for deploying autonomous systems in the real world. In his most cited work, "Uncertainty-aware Safe Exploratory Planning using Gaussian Process and Neural Control Contraction Metric" (2021), Shekhar introduces a method that enables a robot to safely collect observations of an unknown disturbance function while avoiding forbidden areas. By combining Gaussian process regression with a neural control contraction metric, his approach provides formal safety guarantees even as the robot actively explores. This work has garnered 2 citations and represents a foundational step toward integrating learning-based planning with rigorous safety certificates. Shekhar’s research has significant implications for field robotics, autonomous driving, and any application where systems must operate reliably in partially unknown environments. His contributions are shaping a new generation of control algorithms that are both adaptive and provably safe.
Research Focus
Key Achievements
Top Papers
- 1