Max Robotics — Global Service Robot Directory + US Certification

About

Vineet Kosaraju is a researcher whose work sits at the intersection of deep learning, trajectory forecasting, and autonomous systems. He is best known for his contributions to multi-agent path prediction, a critical challenge in enabling self-driving vehicles and social robots to navigate safely around humans. His most influential work, **Social-BiGAT** (2019), introduced a novel framework combining Bicycle-GAN with Graph Attention Networks to model complex social interactions between pedestrians, accumulating 278 citations and establishing him as a notable voice in the trajectory forecasting community. Alongside this, his development of **SoPhie** — an attentive GAN-based framework that jointly respects social and physical constraints — further demonstrated his ability to design interpretable, constraint-aware generative models for real-world autonomous applications. More recently, Kosaraju has expanded into robotic learning, contributing to research on **asymmetric self-play** for automatic goal discovery, enabling robots to generalize across manipulation tasks with unseen objects. Across his body of work, Kosaraju consistently bridges generative modeling, graph-based reasoning, and embodied AI, making his research particularly relevant for students and practitioners working on the next generation of intelligent, interactive autonomous systems.