Vignesh Vembar Manikantan

Undergraduate Researcher, Robotics Research Center, IIIT Hyderabad
B.Tech, Electronics & Communication Engineering

I am an undergraduate researcher at the Robotics Research Center, IIIT Hyderabad, advised by Prof. K. Madhava Krishna. I am currently pursuing my B.Tech in Electronics and Communication Engineering (expected July 2027).

My research centers on robotic manipulation, in particular bimanual (dual-arm) grasping. I work on learning-based approaches for generating stable, collision-free grasps from partial point clouds, and on deploying these methods on real heterogeneous robotic arms.

Beyond research, I help administer the lab’s Linux compute cluster and enjoy teaching — I have been a teaching assistant for a robotics course and an instructor at the IIITH Robotics Summer School.

news

Apr 2026 Started as Systems Administrator for the Robotics Research Center compute cluster.
Jan 2026 Our paper DAGDiff was accepted to ICRA 2026!
Jan 2026 Teaching Assistant for Introduction to Robotics: Perception and Planning at IIIT Hyderabad.
Nov 2025 Placed in the top 15 out of 80+ teams as Structural Team Lead of Team Brahmand (CANSAT).
Jan 2025 Joined the Robotics Research Center, IIIT Hyderabad as an undergraduate researcher.

selected publications

DAGDiff: Guiding Dual-Arm Grasp Diffusion to Stable and Collision-Free Grasps

Md Faizal Karim*, Vignesh Vembar*, Keshab Patra, Gaurav Singh, K Madhava Krishna

IEEE International Conference on Robotics and Automation (ICRA), 2026

abs arxiv project pdf

Reliable dual-arm grasping is essential for manipulating large and complex objects but remains a challenging problem due to stability, collision, and generalization requirements. Prior methods typically decompose the task into two independent grasp proposals, relying on region priors or heuristics that limit generalization and provide no principled guarantee of stability. We propose DAGDiff, an end-to-end framework that directly denoises to grasp pairs in the SE(3) x SE(3) space. Our key insight is that stability and collision can be enforced more effectively by guiding the diffusion process with classifier signals, rather than relying on explicit region detection or object priors. To this end, DAGDiff integrates geometry-, stability-, and collision-aware guidance terms that steer the generative process toward grasps that are physically valid and force-closure compliant. We comprehensively evaluate DAGDiff through analytical force-closure checks, collision analysis, and large-scale physics-based simulations, showing consistent improvements over previous work on these metrics. Finally, we demonstrate that our framework generates dual-arm grasps directly on real-world point clouds of previously unseen objects, which are executed on a heterogeneous dual-arm setup where two manipulators reliably grasp and lift them.