Max Robotics — Global Service Robot Directory + US Certification

About

R. Iris Bahar is a leading researcher at the intersection of computer architecture, robotics, and machine learning, with a focus on building secure, energy-efficient, and robust autonomous systems. Her work addresses critical vulnerabilities in robotic perception, particularly how convolutional neural networks (CNNs) can be deceived in adversarial environments. Bahar’s most cited paper, “GRIP: Generative Robust Inference and Perception for Semantic Robot Manipulation in Adversarial Environments” (2019, 26 citations), introduces a generative-discriminative framework that significantly improves object detection reliability under attack. She further advances this theme in “Robust object estimation using generative-discriminative inference for secure robotics applications” (2018), proposing methods to make robots resilient to uncertainty and malicious inputs. A notable contribution is her work on hardware acceleration, exemplified by “Hardware Acceleration of Monte-Carlo Sampling for Energy Efficient Robust Robot Manipulation” (2020), which tackles the computational bottlenecks of sampling-based algorithms for real-time, low-power robotics. Bahar’s research is pivotal for deploying trustworthy AI in safety-critical applications, and her interdisciplinary approach—spanning algorithm design to hardware optimization—has earned her recognition as a key innovator in secure, autonomous robotics.