Search Results for author:
Found 3 papers, 0 papers with code
Kraken: enabling joint trajectory prediction by utilizing Mode Transformer and Greedy Mode Processing
The most prominent motion prediction approaches are based on modeling the distribution of possible future trajectories of each actor in autonomous system's vicinity.
Match and Locate: low-frequency monocular odometry based on deep feature matching
Accurate and robust pose estimation plays a crucial role in many robotic systems.
PRANK: motion Prediction based on RANKing
To be useful within a real-time autonomous driving pipeline, a motion prediction system must provide efficient ways to describe and quantify this uncertainty, such as computing posterior modes and their probabilities or estimating density at the point corresponding to a given trajectory.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
