4 papers
P3: Probabilistic Policy Propagation for Stable VAE-Based Robot Learning
Liyun Yan, Jianming Ma, Yang Zhang +5
Variational Autoencoders are widely used to encode high-dimensional and noisy observations in robotics. However, their stochastic latent creates a mismatch with Proximal Policy Opt…
GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models
Yizhi Chen, Zhanxiang Cao, Xinyi Peng +14
Current Vision--Language--Action (VLA) models often optimize for semantic grounding, whereas executable manipulation requires geometry-aware spatial alignment and dynamic affordanc…
Construction of a Multiple-DOF Under-actuated Gripper with Force-Sensing via Deep Learning
Jihao Li, Keqi Zhu, Guodong Lu +2
We present a novel under-actuated gripper with two 3-joint fingers, which realizes force feedback control by the deep learning technique- Long Short-Term Memory (LSTM) model, witho…
The Stiffness of 3-PRS PM Across Parasitic and Orientational Workspace
Hassen Nigatu, Li Jihao, Keqi Zhu +4
This study investigates the stiffness characteristics of the Sprint Z3 head, also known as 3-PRS Parallel Kinematics Machines, which are among the most extensively researched and v…