Max Robotics — Global Service Robot Directory + US Certification

About

Chadi Salmi is a robotics researcher whose work sits at the intersection of motion planning, model predictive control, and human-robot interaction. His primary contributions lie in developing sampling-based control methods that leverage GPU-parallelizable physics simulations, notably through his work on Model Predictive Path Integral (MPPI) controllers using IsaacGym. This approach, detailed in his most-cited paper (2025, 17 citations), enables real-time, robust control for complex robotic systems. Salmi has also advanced autonomous navigation by introducing self-supervised continual learning frameworks for pedestrian prediction (2022, 14 citations), allowing mobile robots to adapt to changing human behaviors online. His research further extends to reactive task and motion planning (TAMP), where he combines Active Inference with multi-modal MPPI to handle runtime uncertainties (2024, 10 citations). To support the broader robotics community, Salmi developed localPlannerBench, a benchmarking suite for local motion planning (2022, 2 citations). With a total of 49 citations across his most influential works, Salmi is recognized for pushing the boundaries of real-time, adaptive robotic control and navigation, making his research highly relevant for students and engineers working on autonomous systems.