Multi-task manipulation policies differ in architecture, scale, and pretrained priors all at once, so published comparisons cannot attribute performance to any single component. We argue that most of it comes from the visual representation, and that parameter scale and generative priors are largely incidental. To test...
Na Chen, Run-Qiu Yang, Jia-Wei Tang et al.· 0 citations
Visual grasp proposal generation has advanced rapidly, yet converting a selected proposal into a stable physical grasp remains a central execution-stage challenge. This paper introduces GraspTune, a tactile-driven execution-stage refinement framework that starts from a nominal proposal and applies bounded residual TCP...
Jun-Tao Li, Xing-Ke Xia, Si-Chao Liu et al.· arXiv.org· 0 citations
CAMP constructs candidate trajectories through layered hand search with local arm relaxation, then compactly represents them using endpoint-preserving via-point movement primitives (VMPs) for coarse-to-fine joint optimization and outperforming alternative planners with competitive efficiency.
Zi-Yuan Wang, Yunlong Shan, Fei Mo et al.· arXiv.org· 0 citations
This review surveys the full VBTS pipeline and treats sensing hardware, learning methods, simulation, and datasets as an integrated sensing-and-learning system to advance tactile intelligence for contact-rich robotic tasks.
Peng Zhou, Jun Hu, Si-Han Chen et al.· 2 citations
Robotic-GST is presented, a geometry-aware spatio-temporal behaviour representation and evaluation framework that constructs a Gaussian-SAM robotic environment for real-to-sim policy verification and improves the reliability of real-world manipulation deployment.