5 papers
DRL-TH: Jointly Utilizing Temporal Graph Attention and Hierarchical Fusion for UGV Navigation in Crowded Environments
Ruitong Li, Lin Zhang, Yuenan Zhao +3
Deep reinforcement learning (DRL) methods have demonstrated potential for autonomous navigation and obstacle avoidance of unmanned ground vehicles (UGVs) in crowded environments. M…
Informative Text-Image Alignment for Visual Affordance Learning with Foundation Models
Qian Zhang, Lin Zhang, Xing Fang +4
Visual affordance learning is crucial for robots to understand and interact effectively with the physical world. Recent advances in this field attempt to leverage pre-trained knowl…
StyleLoco: Generative Adversarial Distillation for Natural Humanoid Robot Locomotion
Le Ma, Ziyu Meng, Tengyu Liu +4
Humanoid robots are anticipated to acquire a wide range of locomotion capabilities while ensuring natural movement across varying speeds and terrains. Existing methods encounter a…
Point-aware Interaction and CNN-induced Refinement Network for RGB-D Salient Object Detection
Runmin Cong, Hongyu Liu, Chen Zhang +4
By integrating complementary information from RGB image and depth map, the ability of salient object detection (SOD) for complex and challenging scenes can be improved. In recent y…
Provably Uncertainty-Guided Universal Domain Adaptation
Yifan Wang, Lin Zhang, Ran Song +3
Universal domain adaptation (UniDA) aims to transfer the knowledge from a labeled source domain to an unlabeled target domain without any assumptions of the label sets, which requi…