Plenary Speakers

Modern drones such as First Person View aircraft, stealthy “dark” drones, and drone swarms are a threat to military, critical infrastructure, and civilian airspace. Traditional radar systems struggle with the low altitude, slow speed, and small size of drones. The use of radar in the drone kill chain of Detect, Track, Identify, and Mitigate is discussed with the specific example of a compact multi-receive channel architecture enabling Space Time Adaptive Processing powered by an onboard GPU and using real‑time Artificial Intelligence and Machine Learning techniques. Real-world surface-to-air radar and air-to-air interceptor applications are illustrated. Modern radar is key to the rapid detection, tracking, and neutralization of drones, safeguarding assets and people in the modern battlefield.

Radar technology, together with camera technology is the backbone of todays advanced driver assistance systems and is considered indispensable for higher levels of vehicular autonomy. We give an overview of millimeter-wave automotive radar technology, including modulation schemes, monolithic microwave integrated circuits, antennas, and bistatic array configurations. Practical trade-offs and challenges are discussed and compared to Lidar and camera technology. In particular we discuss how the all-weather robustness of millimeter waves comes at the cost of notoriously sparse point clouds and present potential remedies.

Modern radar systems are becoming increasingly sophisticated and responsive to their environments. While this flexibility enhances performance, it also introduces a fundamental vulnerability: behavioral adaptation becomes observable. An adversary can exploit radar emissions, responses, and operational patterns to infer hidden states, tracking strategies, and intent. This talk presents a unifying perspective on radar interaction as an adversarial inference problem, grounded in statistical signal processing and inverse reinforcement learning. Instead of estimating a target, we  shift the focus to inferring an adversarial radar,  using inverse filtering and natural language  processing techniques to  reconstruct  the radar's  estimate of the target, its hidden beliefs, and its operational intent. We then address a fundamental question: how can one detect the presence of a cognitive radar and identify its underlying objectives? This motivates revealed preference theory from microeconomics and inverse reinforcement learning as principled tools for inferring radar intent from observed behavior. Finally, we reverse the perspective: how can a radar mask its sensing strategy from an adversary while preserving operational effectiveness? We discuss mechanisms including utility masking and information-theoretic approaches that degrade identifiability while preserving  performance.