Anutam Srinivasan

Achieving robust control for complex nonlinear systems at 67 Hz without sacrificing formal guarantees could revolutionize real-time decision-making in dynamic environments.

Auditing AI systems in real-world settings requires a shift from static benchmarks to dynamic, uncertainty-aware monitoring of fairness and safety constraints.

Probabilistic safety constraints in motion planning can be achieved through a novel integration of learned latent models and robust MPC, outperforming traditional methods.

Guarantee safety when your robot ventures into the unknown by using conformal prediction to generate high-confidence error bounds for learned dynamics models, then tightening constraints in a Model Predictive Controller.