Papers
11
Total Citations
361
H-Index
8
About
Sumeet Singh is a robotics researcher whose work spans robust motion planning, control theory, and the integration of large language models (LLMs) into robotic systems. His most influential contribution, "Robust Online Motion Planning via Contraction Theory and Convex Optimization" (2017, 183 citations), established a foundational framework for generating real-time, disturbance-resilient motion plans for nonlinear robotic systems — a line of work he extended in subsequent publications combining contraction metrics with safe planning guarantees. Singh has also made meaningful contributions to multi-robot coordination, demonstrating decentralized cooperative transport with quadrotors without peer communication (2018). More recently, his research has pivoted toward LLM-powered robotics: his KnowNo framework (2023) addresses the critical challenge of uncertainty alignment in LLM-based planners, enabling robots to recognize when to ask for human help rather than hallucinate confidently. His "PromptBook" work further bridges semantic reasoning and manipulation skills. Singh's contributions to the landmark Gemini Robotics project (2025) reflect his growing influence at the frontier of embodied AI, making him a compelling voice at the intersection of classical control theory and modern generative AI for physical systems.
Research Focus
Key Achievements
Top Papers
- 1Robust online motion planning via contraction theory and convex optimization183 citations · 2017
- 2
- 3Robust feedback motion planning via contraction theory38 citations · 2023
- 4
- 5
- 6Single-Level Differentiable Contact Simulation8 citations · 2023
- 7
- 8Safe Motion Planning with Tubes and Contraction Metrics8 citations · 2021
- 9Learning Stabilizable Dynamical Systems via Control Contraction Metrics7 citations · 2020
- 10Gemini Robotics: Bringing AI into the Physical World4 citations · 2025