[ICCV'23] Ji Zhang: From Lidar SLAM to Full-scale Autonomy and Beyond

In this talk, Prof. Zhang will introduce our full autonomy stack which enables robots to autonomously navigate to goal points and to explore and map unknown environments. His work started several years ago from the fundamental SLAM building block - Lidar Odometry And Mapping (LOAM). Building upon the SLAM module, the full autonomy stack now provides multiple low-level features, e.g. collision avoidance, terrain traversability analysis, and waypoint following. The autonomy stack further contains two high-level planners for waypoint navigation and exploration, respectively. The autonomy stack can be set to run both in simulation and on real robot platforms. In the talk, he will give examples of using the system to support research work such as advanced AI and SLAM. Aimed at lowering the bar for everybody to acquire autonomy and make further use of it, their system is open-sourced at cmu-exploration.com.

Bio:
Ji Zhang's research interests are in robotic navigation, spanning localization, mapping, planning, and exploration. His early work on Lidar Odometry and Mapping (LOAM) and the succeeding work leveraging range, vision, and inertial sensing ignited real-time 3D Lidar SLAM. His work ranked #1 on the odometry leaderboard of KITTI Vision Benchmark between 2014 and 2021. He founded Kaarta, Inc, a CMU spin-off commercializing 3D mapping & modeling technologies, and stayed with the company for 4 years as chief scientist. In late 2019, He rejoined CMU as a faculty member and started leading the development of a series of autonomous navigation algorithms. The complete navigation system brought CMU-OSU Team a "Most Sectors Explored Award" on DARPA Subterranean Challenge. He currently holds another role at the National Robotics Engineering Center at CMU and leads a few serious projects.

Slides:
Download from https://sairlab.org/iccv23/