Safe Interactive Autonomy for Multi-Agent Systems

It is envisioned that in the near future autonomous systems such as multi-agent systems, will co-exist with humans, e.g., vehicles share roads human drivers. These safety-critical scenarios require formally provable safety guarantees so robots never collide humans or each other. challenging to provide real world due stochastic environments and inaccurate models of heterogeneous agents including humans. My PhD research investigates decision-making algorithm design for provably-correct mixed systems.