Perception plays a crucial role in various robot applications. However existing well-
annotated datasets are biased towards autonomous driving scenarios while unlabelled …

In the past decade, deep neural networks have achieved significant progress in point cloud
learning. However, collecting large-scale precisely-annotated point clouds is extremely …

Continual learning, also known as incremental learning or life-long learning, stands at the
forefront of deep learning and AI systems. It breaks through the obstacle of one-way training …

Multi-modal unsupervised domain adaptation (MM-UDA) for 3D semantic segmentation is a
practical solution to embed semantic understanding in autonomous systems without …

One-shot LiDAR localization refers to the ability to estimate the robot pose from one single
point cloud, which yields significant advantages in initialization and relocalization …

Test-time adaptation (TTA) aims to address the distribution shift between the training and
test data with only unlabeled data at test time. Existing TTA methods often focus on …

Multi-modal test-time adaptation (MM-TTA) is proposed to adapt models to an unlabeled
target domain by leveraging the complementary multi-modal inputs in an online manner …