Somdyuti Paul
Papers
1
Total Citations
5
H-Index
1
About
Somdyuti Paul is a researcher at the forefront of autonomous robotics, with a primary focus on robotic path planning and manipulation in unstructured environments. Her most influential work introduces a novel application of deterministic policy gradient algorithms to enable robotic manipulators to navigate continuous action spaces—a critical advancement over traditional methods that rely on precise target localization and inverse kinematics. This approach allows robots to adapt to real-world uncertainties without requiring exact object positions, significantly enhancing their autonomy and flexibility. With her 2017 paper garnering 5 citations, Paul’s contributions are foundational for researchers tackling the challenges of robotic control in dynamic settings. Her work bridges reinforcement learning and practical robotics, offering a pathway toward more intelligent, self-reliant systems. For students and researchers exploring the intersection of machine learning and robotics, Paul’s research provides a compelling example of how policy gradient methods can solve complex, real-world manipulation tasks, making her a notable voice in the ongoing evolution of autonomous robotic systems.
Research Focus
Key Achievements
Top Papers
- 1