TY - GEN
T1 - LVI-SAM
T2 - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
AU - Shan, Tixiao
AU - Englot, Brendan
AU - Ratti, Carlo
AU - Rus, Daniela
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - We propose a framework for tightly-coupled lidar-visual-inertial odometry via smoothing and mapping, LVI-SAM, that achieves real-time state estimation and map-building with high accuracy and robustness. LVI-SAM is built atop a factor graph and is composed of two sub-systems: a visual-inertial system (VIS) and a lidar-inertial system (LIS). The two subsystems are designed in a tightly-coupled manner, in which the VIS leverages LIS estimation to facilitate initialization. The accuracy of the VIS is improved by extracting depth information for visual features using lidar measurements. In turn, the LIS utilizes VIS estimation for initial guesses to support scan-matching. Loop closures are first identified by the VIS and further refined by the LIS. LVI-SAM can also function when one of the two sub-systems fails, which increases its robustness in both texture-less and feature-less environments. LVI-SAM is extensively evaluated on datasets gathered from several platforms over a variety of scales and environments. Our implementation is available at https://git.io/lvi-sam.
AB - We propose a framework for tightly-coupled lidar-visual-inertial odometry via smoothing and mapping, LVI-SAM, that achieves real-time state estimation and map-building with high accuracy and robustness. LVI-SAM is built atop a factor graph and is composed of two sub-systems: a visual-inertial system (VIS) and a lidar-inertial system (LIS). The two subsystems are designed in a tightly-coupled manner, in which the VIS leverages LIS estimation to facilitate initialization. The accuracy of the VIS is improved by extracting depth information for visual features using lidar measurements. In turn, the LIS utilizes VIS estimation for initial guesses to support scan-matching. Loop closures are first identified by the VIS and further refined by the LIS. LVI-SAM can also function when one of the two sub-systems fails, which increases its robustness in both texture-less and feature-less environments. LVI-SAM is extensively evaluated on datasets gathered from several platforms over a variety of scales and environments. Our implementation is available at https://git.io/lvi-sam.
UR - http://www.scopus.com/inward/record.url?scp=85107943676&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85107943676&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9561996
DO - 10.1109/ICRA48506.2021.9561996
M3 - Conference contribution
AN - SCOPUS:85107943676
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 5692
EP - 5698
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Y2 - 30 May 2021 through 5 June 2021
ER -