Max Robotics — Global Service Robot Directory + US Certification

About

Arvind Easwaran’s research sits at the critical intersection of machine learning, real-time systems, and safety-critical cyber-physical systems (CPS). His work addresses a fundamental challenge: how to deploy ML reliably in environments where failure is not an option—such as autonomous vehicles, robotics, and chemical plants. Easwaran is a leading voice on ensuring that ML-based decision-making remains trustworthy even when faced with novel or unexpected inputs. His most influential paper, “Towards Safe Machine Learning for CPS” (28 citations), lays the groundwork for integrating safety guarantees into learning-enabled systems. He has made seminal contributions to out-of-distribution (OOD) detection, developing methods to identify when an ML model is operating on unfamiliar data—a key enabler for safe autonomy. His 2021 paper on embedded OOD detection for autonomous robots (13 citations) and his 2022 design methodology for deep OOD detectors (7 citations) demonstrate practical, real-time solutions deployable on resource-constrained platforms. Easwaran also addresses the security dimension of CPS, analyzing how real-time constraints interact with security overheads. His work is foundational for researchers and engineers building the next generation of safe, secure, and intelligent autonomous systems.