Astghik Hakobyan
Papers
9
Total Citations
245
H-Index
6
About
Astghik Hakobyan is a leading researcher at the intersection of robotics, control theory, and machine learning, whose work fundamentally redefines how autonomous systems navigate uncertainty. Her primary research areas are risk-aware motion planning, distributionally robust control, and learning-based decision-making for mobile robots. Dr. Hakobyan’s major contribution is the development of novel mathematical frameworks that explicitly quantify and manage safety risks in dynamic, unpredictable environments. She pioneered the use of Conditional Value-at-Risk (CVaR) as a constraint in motion planning, enabling robots to systematically balance safety and conservativeness when avoiding randomly moving obstacles. Her most influential paper, "Risk-Aware Motion Planning and Control Using CVaR-Constrained Optimization" (2019), has garnered 108 citations, establishing a foundational methodology in the field. She further advanced the state of the art by introducing Wasserstein distributionally robust control, which ensures safe operation even when the true probability distribution of environmental uncertainty is unknown. Her work on the Distributionally Robust Risk Map (DR-risk map) provides a powerful tool for safety specification in learning-enabled environments. By elegantly fusing Model Predictive Control with meta-Reinforcement Learning, Dr. Hakobyan has created adaptive decision-making systems that allow robots to rapidly respond to environmental changes while maintaining provable safety guarantees. Her research is essential reading for anyone working on safe autonomy in robotics.
Research Focus
Key Achievements
Top Papers
- 1Risk-Aware Motion Planning and Control Using CVaR-Constrained Optimization108 citations · 2019
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9