Vishal Mandadi

Papers

Total Citations

H-Index

About

Vishal Mandadi is a rising roboticist whose research sits at the intersection of motion planning, perception, and manipulation. His most cited work, "EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning" (2024, 22 citations), introduces a novel diffusion-based framework that leverages an ensemble of classical cost functions to guide trajectory generation. This approach bridges the gap between data-driven generative models and traditional, scene-agnostic planning algorithms, offering remarkable adaptability without requiring task-specific training. Mandadi’s contributions are particularly significant for robotic manipulation, where generalizable and cost-aware planning remains a core challenge. In his earlier work, "Approaches and Challenges in Robotic Perception for Table-top Rearrangement and Planning" (2022, 4 citations), he systematically analyzed the perception stack—from 3D scene registration to object detection and manipulation—highlighting its critical role in table-top rearrangement tasks. This foundational survey underscores his deep engagement with the full pipeline of embodied AI. Though early in his career, Mandadi’s integration of diffusion models with classical planning signals a promising trajectory toward more robust, real-world robotic systems.