Papers
9
Total Citations
252
H-Index
7
About
Rishi Graham is a robotics and autonomous systems researcher whose work sits at the intersection of field robotics, marine science, and statistical estimation. His research focuses primarily on adaptive robotic sampling, spatiotemporal random field estimation, and cooperative sensor network coordination — with a particular emphasis on applying these methods to marine ecosystem monitoring. Graham's most influential contribution, "Data-driven robotic sampling for marine ecosystem monitoring" (2015, 110 citations), demonstrated how autonomous robots can intelligently collect physical samples in dynamic ocean environments, advancing persistent, in-situ scientific observation. His foundational work on trajectory optimization for robotic sensor networks, particularly "Adaptive Information Collection by Robotic Sensor Networks for Spatial Estimation" (2011, 63 citations), established key frameworks for minimizing predictive uncertainty across multi-agent systems navigating complex, high-dimensional spaces. A recurring theme across his body of work is enabling robots to operate effectively under uncertainty — whether through partially known covariance structures, distributed coordination algorithms, or learning-based event response for detecting ephemeral phenomena like oceanic fronts and algal blooms. His momentum-based front detection method exemplifies his commitment to practical, deployable solutions for coastal ecology research. Collectively, Graham's work has meaningfully shaped how autonomous systems are designed to observe and understand dynamic natural environments.
Research Focus
Key Achievements
Top Papers
- 1Data-driven robotic sampling for marine ecosystem monitoring110 citations · 2015
- 2
- 3
- 4
- 5Exploring Space-Time Tradeoffs in Autonomous Sampling for Marine Robotics11 citations · 2013
- 6
- 7Learning-based event response for marine robotics9 citations · 2013
- 8Distributed sampling of random fields with unknown covariance7 citations · 2009
- 9