Max Robotics — Global Service Robot Directory + US Certification

About

Shreekant Gayaka’s research bridges classical control theory and modern computer vision, with a focus on enabling robots to perceive and interact with their environments more intelligently. His early work tackled the challenge of velocity estimation in highly nonlinear electro-hydraulic systems, designing an adaptive robust observer that relied solely on pressure measurements—a contribution that has garnered 25 citations and demonstrated his ability to handle severe parametric uncertainties. More recently, Gayaka has pivoted to cutting-edge problems in robotic perception, co-authoring “SupeRGB-D: Zero-Shot Instance Segmentation in Cluttered Indoor Environments” (2023, 11 citations). This work addresses a critical bottleneck for indoor robots: detecting and segmenting small, unseen objects in cluttered spaces without requiring expensive manual annotations, leveraging RGB-D data for robust performance. His latest research pushes into 3D object generation from single images using Gaussian Splatting and hybrid diffusion priors (2025), aiming to reconstruct complete geometry and texture for precise robotic manipulation and grasping. Gayaka’s trajectory—from robust control to zero-shot segmentation and 3D generation—reflects a deep commitment to making autonomous systems more adaptable and capable in unstructured, real-world settings.