Co-Modality Active sensing and Perception (C-MAP) in Autonomous Vehicles, Augmented Reality, Remote Environmental Monitoring, and Robotic Grasping
Tuesday, April 25, 2023
Combining multiple sensor modalities to achieve more robust understanding of environment and robot status is an emerging research area in robot navigation and autonomous driving. To fuse sensors such as camera, lidar, inertial measurement unit, wheel encoder, etc., one must solve problems in synchronization, calibration, signal correspondence, and data fusion. A successful fusion algorithm will improve precision, feasibility, and robustness in perception. In this talk, I will discuss the lessons that we have learned in sensor fusion to address many problems in autonomous driving and robot navigation using autonomous motorcycle and NASA Robonaut as examples. We will also discuss how augmented reality development on mobile devices benefited from the sensor fusion approach in robotics. I will also talk about our recent works in robotic remote environment monitoring, especially focused on subsurface surface void and pipeline mapping. Moreover, addressing perception challenges after sensory data are collected from individual modalities may limit perception potential; I will talk about C-MAP sensor fusion at device level where we combine different sensory modalities into a single device to achieve new promising capabilities in various of applications in robotic material handling. If time permits, we will introduce our latest work on robotic weed removal in precision agriculture.
Post Talk Link: Click Here
Passcode: ZX4u.Kgy
Speaker/s
Dezhen Song is a Professor and Associate Department Head for Academics with Department of Computer Science and Engineering, Texas A&M University, College Station, Texas, USA. Song received his Ph.D. in 2004 from University of California, Berkeley; MS and BS from Zhejiang University in 1998 and 1995, respectively. Song's primary research area is robot perception, networked robots, visual navigation, automation, and stochastic modeling. From 2008 to 2012, Song was an associate editor of IEEE Transactions on Robotics (T-RO). From 2010 to 2014, Song was an Associate Editor of IEEE Transactions on Automation Science and Engineering (T-ASE). Song was a Senior Editor for IEEE Robotics and Automation Letters (RA-L) from 2017 to 2021 and currently is a Senior Editor for IEEE Transactions on Automation Science and Engineering (T-ASE). He is also a multimedia Editor and chapter author for Springer Handbook of Robotics. His research has resulted in one monograph and more than 130 refereed conference and journal publications. Dr. Song received NSF Faculty Early Career Development (CAREER) Award in 2007, Kayamori Best Paper Award of the 2005 IEEE International Conference on Robotics and Automation (ICRA), the 2022 Best Paper Award of the LCT 2022 Affiliated Conference, the 1st place in GM/SAE autonomous driving dynamic competition in 2021, and Amazon Research Award in 2020.
Related
Polygenic Score Modeling to Investigate Genotype-Phenotype Associations
Read More
Trustworthy Machine Learning: Transparency, Collaboration, and Evaluation
Read More