4 papers
EATR-Stereo: Embodiment-Aware Token Routing of Paired Stereo Evidence for Humanoid Vision-Language-Action Control
Songwei Wu, Rui Zhao, Fan Yang +7
Long-horizon humanoid vision--language--action (VLA) control with head-mounted stereo cameras requires visual interfaces that can exploit complementary views while maintaining comp…
CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation
Wu Songwei, Jiang Zhiduo, Sun Wandong +4
Learning long-horizon robotic manipulation requires jointly achieving expressive behavior modeling, real-time inference, and stable execution, which remains challenging for existin…
DCIRNet: Depth Completion with Iterative Refinement for Dexterous Grasping of Transparent and Reflective Objects
Guanghu Xie, Zhiduo Jiang, Yonglong Zhang +4
Transparent and reflective objects in everyday environments pose significant challenges for depth sensors due to their unique visual properties, such as specular reflections and li…
HTMNet: A Hybrid Network with Transformer-Mamba Bottleneck Multimodal Fusion for Transparent and Reflective Objects Depth Completion
Guanghu Xie, Yonglong Zhang, Zhiduo Jiang +4
Transparent and reflective objects pose significant challenges for depth sensors, resulting in incomplete depth information that adversely affects downstream robotic perception and…