The robodrive challenge: Drive anytime anywhere in any condition
In the realm of autonomous driving, robust perception under out-of-distribution conditions is
paramount for the safe deployment of vehicles. Challenges such as adverse weather …
paramount for the safe deployment of vehicles. Challenges such as adverse weather …
An Empirical Study of Training State-of-the-Art LiDAR Segmentation Models
In the rapidly evolving field of autonomous driving, precise segmentation of LiDAR data is
crucial for understanding complex 3D environments. Traditional approaches often rely on …
crucial for understanding complex 3D environments. Traditional approaches often rely on …
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving
Recent advancements in bird's eye view (BEV) representations have shown remarkable
promise for in-vehicle 3D perception. However, while these methods have achieved …
promise for in-vehicle 3D perception. However, while these methods have achieved …
4D Contrastive Superflows are Dense 3D Representation Learners
In the realm of autonomous driving, accurate 3D perception is the foundation. However,
developing such models relies on extensive human annotations--a process that is both …
developing such models relies on extensive human annotations--a process that is both …
Is Your HD Map Constructor Reliable under Sensor Corruptions?
Driving systems often rely on high-definition (HD) maps for precise environmental
information, which is crucial for planning and navigation. While current HD map constructors …
information, which is crucial for planning and navigation. While current HD map constructors …
[PDF][PDF] The RoboDrive Challenge: Drive Anytime Anywhere in Any Condition
LKSXH Hu, YNWT Ooi, BRCLX Ng, YMWZL Pan… - researchgate.net
In the realm of autonomous driving, robust perception under out-of-distribution conditions is
paramount for the safe deployment of vehicles. Challenges such as adverse weather …
paramount for the safe deployment of vehicles. Challenges such as adverse weather …
[PDF][PDF] RobuAlign: Robust Alignment in Multi-Modal 3D Object Detection
D Fu, Y Lin, H Yang, H Li, Y Luo, X Cheng, Y Xu - researchgate.net
The failure of vehicle-mounted cameras and LiDAR sensors is inevitable in practice,
resulting in incomplete data. To enhance the ability to robustly handle incomplete data, we …
resulting in incomplete data. To enhance the ability to robustly handle incomplete data, we …
[PDF][PDF] ASF: Robust 3D Object Detection by Solving Sensor Failures
This paper describes the methodology and results of Track 5-Robust Multi-Modal BEV
Detection in the 2024 Robo-Drive Challenge. This track focuses on 3D scene perception …
Detection in the 2024 Robo-Drive Challenge. This track focuses on 3D scene perception …
[PDF][PDF] TSMA-BEV: Towards Robust Multi-Camera 3D Object Detection through Temporal Sequence Mix Augmentation
The advent of bird's-eye view (BEV) representation has witnessed significant advancements
in camera-only 3D object detection. However, existing approaches usually struggle when …
in camera-only 3D object detection. However, existing approaches usually struggle when …
[PDF][PDF] Cross-Modal Transformers for Robust Multi-Modal BEV Detection
In this paper, we elaborate on the practical application and demonstration of Cross-Modal
Transformer (CMT) for Track 5–Robust Multi-Modal BEV Detection, in the 2024 RoboDrive …
Transformer (CMT) for Track 5–Robust Multi-Modal BEV Detection, in the 2024 RoboDrive …