Institute Homepage
Institute Homepage Sign In

Back

Embodied Vision Members Publications

Visual-Inertial State Estimation with Online Adaptation of Mobile Robot Dynamics Models

Dynvio
ST-VIO tightly integrates visual, inertial, and dynamic motion constraints and calibrates the motion model online. © IEEE. Reprinted, with permission, from [File Icon].
In our works [File IconFile Icon], we investigate visual-inertial odometry approaches that enable wheeled robots to estimate their 3D motion in real-time and adapt the kinematic or dynamic model of the robot online to variations of robot and terrain properties. Kin-VIO [File Icon] adapts parameters of the mapping from velocity controls to an effective control command for a kinematic velocity-based motion model. In ST-VIO [File Icon] a single-track dynamic model formulated as an ODE is used to predict robot motion. Several of its parameters which map steering angle and thrust commands to robot motion are calibrated online.

n/a

Members

Thumb ticker sm profilepic stueckler
Embodied Vision
Jörg Stückler
Max Planck Research Group Leader
Thumb ticker sm img 5012
Embodied Vision
Haolong Li
Thumb ticker sm pp
Embodied Vision
Victor Dhédin
  • Master Student
Thumb ticker sm dsc00314
Embodied Vision
Lukas Mack
Research Associate

Publications

Embodied Vision Conference Paper Online Calibration of a Single-Track Ground Vehicle Dynamics Model by Tight Fusion with Visual-Inertial Odometry Li, H., Stueckler, J. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2024 (Published) preprint supplemental video code datasets DOI URL BibTeX
Embodied Vision Autonomous Motion Movement Generation and Control Conference Paper Visual-Inertial and Leg Odometry Fusion for Dynamic Locomotion Dhédin, V., Li, H., Khorshidi, S., Mack, L., Ravi, A. K. C., Meduri, A., Shah, P., Grimminger, F., Righetti, L., Khadiv, M., et al. In Proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2023 (Published) preprint video DOI URL BibTeX
Embodied Vision Article Visual-Inertial Odometry with Online Calibration of Velocity-Control Based Kinematic Motion Models Li, H., Stueckler, J. IEEE Robotics and Automation Letters, 7(3):6415-6422, July 2022, Accepted for oral presentation at IEEE ICRA 2023 (Published) preprint DOI URL BibTeX
Embodied Vision Article Visual-Inertial Mapping with Non-Linear Factor Recovery Usenko, V., Demmel, N., Schubert, D., Stückler, J., Cremers, D. IEEE Robotics and Automation Letters (RA-L), 5(2):422-429, 2020, presented at IEEE International Conference on Robotics and Automation (ICRA) 2020, preprint arXiv:1904.06504 (Published) Code Preprint URL BibTeX