Abstract: Pushing the limit of robot autonomy in real-world challenging environments is the key to making it useful. One of the main challenges is to develop systems that are robust to extreme operating conditions, which introduces sensing degradation. In this talk, I’ll present a series of works targeting extreme and uncertain environments, including scenes with dynamic objects, adversarial weather, fog, smoke, and unstructured terrains. We developed challenging datasets and robust algorithms that allow our robots to navigate reliably in off-road terrains, dynamic scenes, and complete darkness.

Bio: Wenshan Wang is a Systems Scientist at the Robotics Institute, Carnegie Mellon University. She received her PhD degree from Shanghai Jiao Tong University. Her research interests are applying machine learning to robotic problems and improving the robustness and intelligence of autonomous systems. Her work on off-road driving, autonomous aerial filming, and visual SLAM has pushed the limit of autonomous robots in real-world challenging environments. She organized and hosted a series of workshops about pushing robots’ capabilities in challenging environments, including the CVPR 2020 SLAM workshop, ICCV 2023 robot learning workshop, ICRA 2024 and RSS 2025 off-road driving workshop, and IROS 2024 – 2025 AI meets robots workshop. Her work, MAC-VO, has won the Best Paper Award and Best Perception Paper Award at ICRA 2025.