Papers
6
Total Citations
186
H-Index
4
About
Shray Bansal’s research lies at the intersection of human-robot interaction, probabilistic modeling, and game theory, with a focus on enabling robots to anticipate and adapt to human behavior in shared workspaces. His most influential work, “Probabilistic human action prediction and wait-sensitive planning for responsive human-robot collaboration” (87 citations), introduced a graphical model that predicts when a human will perform subtasks requiring robot assistance, allowing robots to plan proactively rather than reactively. Expanding on this, his 2014 paper (78 citations) developed a representation for structured activities that enables robots to infer current and future human actions despite task and sensor uncertainty—a critical step toward fluid collaboration. More recently, Bansal has pioneered a Bayesian framework for Nash equilibrium inference in human-robot parallel play, where humans and robots pursue independent goals in shared spaces. By modeling these scenarios as general-sum games, his work (cumulatively ~19 citations) provides a principled method for robots to reason about strategic interactions. Bansal’s contributions have been recognized in top robotics venues, and his wait-sensitive planning approach remains a foundational reference for researchers building responsive, anticipatory robotic systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6