VIODE: A Simulated Dataset to Address the Challenges of Visual-Inertial Odometry in Dynamic Environments.
Koji MinodaFabian SchillingValentin WüestDario FloreanoTakehisa YairiPublished in: IEEE Robotics Autom. Lett. (2021)
Keyphrases
- dynamic environments
- inertial sensors
- path planning
- real environment
- autonomous agents
- mobile robot
- simultaneous localization and mapping
- real world
- changing environment
- autonomous navigation
- potential field
- collision avoidance
- agent systems
- position and orientation
- visual information
- visual features
- visual odometry
- single agent
- motion tracking
- plan execution
- human actions
- multi agent
- real time