Kallol Saha

Papers

Total Citations

H-Index

About

Kallol Saha is a rising force in robotics, whose work sits at the intersection of machine learning and motion planning. His research focuses on developing data-driven methods to solve complex, real-world manipulation tasks, with a particular emphasis on leveraging generative models for robotic control. His most-cited work, "EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning" (2024, 22 citations), introduces a novel framework that integrates classical cost functions with modern diffusion models. This approach allows a robot to generate smooth, collision-free trajectories without requiring scene-specific training, effectively bridging the gap between the adaptability of traditional planners and the power of learned representations. By guiding the diffusion process with an ensemble of costs, Saha’s method achieves remarkable generalization across diverse environments. This contribution is significant for enabling robots to operate robustly in unstructured settings, a key challenge in embodied AI. Already garnering attention for its elegant synthesis of old and new ideas, Saha’s work signals a promising trajectory toward more intelligent and flexible robotic systems.