H.B. Keller Colloquium

Unmanned aerial systems hold promise for critical applications including search and rescue, environmental monitoring, and autonomous delivery. Real world deployment in safety critical settings, however, remains challenging due to GPS denied operation, uncertainty in perception, and the need for safe trajectory planning in dynamic, partially known environments. This talk presents recent advances in planning, control, and perception that together enable robust, scalable, and efficient aerial autonomy. On the planning and control side, I first present IL-RTMPC, a demonstration and training efficient approach for learning robust control policies from model predictive control. By combining single trajectory demonstrations with disturbance aware data aggregation, IL-RTMPC produces policies that generalize to unseen conditions, with validation on quadrotors and the MIT SoftFly platform. I then introduce DYNUS, which enables uncertainty aware trajectory planning for safe, real time flight in dynamic and unknown environments. Building on this foundation, MIGHTY performs fully coupled spatiotemporal optimization to generate agile and precise motion by jointly reasoning about path and timing. Together with prior work on Robust MADER, these methods enable fast, safe, multi robot navigation under uncertainty. On the perception side, I introduce complementary mapping frameworks that support long term autonomy and planning. GRAND SLAM combines 3D Gaussian splatting with semantic and geometric priors to produce unified scene representations suitable for photorealistic planning. ROMAN compresses environments into sparse, object centric maps that are orders of magnitude smaller than traditional representations while still enabling accurate relocalization and loop closure under extreme viewpoint changes. I also discuss the interaction between perception and control, focusing on safety filtering for systems that rely on learned perception models. I will present results across simulation and hardware experiments and conclude with open challenges in building resilient autonomous aerial systems. These advances move us closer to reliable UAS autonomy with meaningful real world impact.