Outdoor environments are mostly unstructured and subject to nature's diverse conditions. The deployment of autonomous systems in such challenging scenarios requires robust and non-interrupted perception. Multi-modal sensor suites are necessary to achieve spatial data with visual and geometric information. AI-enabled fusion of multi-domain sensing can generate the required perception, which in turn ensures the correct inputs for decision-making. In this talk, we present our work on multi-modal sensing and its robust spatial intelligence. The developed capability works in adverse environments where commonly used sensors fail. Furthermore, various multi-modal sensing-based autonomy capabilities are illustrated for path-planning and navigation of autonomous robots. Finally, an industry application of robust spatial intelligence is shown to be successful in quay crane automation.
Danwei Wang
received the B.E. degree from the South China University of Technology, China, in 1982, and the M.S.E. and Ph.D. degrees from the University of Michigan, Ann Arbor, in 1984 and 1989, respectively. He is a Professor with the School of Electrical and Electronic Engineering, Nanyang Technological University (NTU), Singapore. He was the Head of the Division of Control and Instrumentation, NTU, from 2005 to 2011; the Director of the Centre for System Intelligence and Efficiency, NTU, from 2013 to 2016; and the Director of the ST Engineering-NTU Corporate Laboratory, NTU, from 2015 to 2021. His research interests include robotics, control engineering, and fault diagnosis. Dr. Wang is a fellow of Academy of Engineering Singapore. He was a recipient of the Alexander von Humboldt Fellowship, Germany. He served as the general chair, the technical chair, and in various positions in several international conferences, and as an invited guest editor for various international journals. He is a Distinguished Lecturer of the IEEE Robotics and Automation Society.