no code implementations • 8 Mar 2024 • Ziyu Zhang, Johann Laconte, Daniil Lisus, Timothy D. Barfoot
This paper presents a novel method to assess the resilience of the Iterative Closest Point (ICP) algorithm via deep-learning-based attacks on lidar point clouds.
no code implementations • 15 Sep 2023 • Daniil Lisus, Johann Laconte, Keenan Burnett, Timothy D. Barfoot
Combining a proven analytical approach with a learned weight reduces localization errors in radar-lidar ICP results run on real-world autonomous driving data by up to 54. 94% in translation and 68. 39% in rotation, while maintaining interpretability and robustness.
no code implementations • 10 Sep 2021 • Daniil Lisus, Charles Champagne Cossette, Mohammed Shalaby, James Richard Forbes
It is essential that a robot has the ability to determine its position and orientation to execute tasks autonomously.