Bogdan Vlahov

Papers

Total Citations

H-Index

About

Bogdan Vlahov’s research lies at the intersection of optimal control, variational inference, and robotics, with a focus on enabling autonomous systems to make robust, real-time decisions under uncertainty. His most significant contribution is the development of a generalized framework for Variational Inference-Model Predictive Control (VI-MPC) using Tsallis divergence. In his 2021 paper, Vlahov introduced a novel approach that incorporates the deformed exponential function into the optimality likelihood function, creating a Tsallis Variational Inference-MPC framework. This work, which has garnered 17 citations, provides a more flexible and robust alternative to traditional KL-divergence-based methods, allowing for better handling of non-Gaussian uncertainties in control tasks. Earlier in his career, Vlahov tackled the practical challenge of balancing a humanoid wheeled inverted pendulum robot. His 2018 paper presented an innovative method for online center of mass estimation, condensing mass model inaccuracies into a single error term and using robust control with online learning to maintain balance. This work, while less cited, demonstrates his ability to bridge theoretical advances with real-world robotic applications. Vlahov’s research is particularly valuable for students and researchers working in model predictive control, stochastic optimal control, and legged robotics, offering both foundational theory and practical implementation strategies.