Generative Zero-Shot Learning approach (GZSL) has demonstrated significant potential in 3D point cloud semantic segmentation tasks. GZSL leverages generative models like GANs or VAEs to synthesize realistic features (real features) of unseen classes. This allows the model to label unseen classes during testing, despite being trained only on seen classes. In this context, we introduce the Generalized Zero-Shot Learning based-upon Mixture-of-Experts (GZSL-MoE) model. This model incorporates Mixture-of-Experts layers (MoE) to generate fake features that closely resemble real features extracted using a pre-trained KPConv (Kernel Point Convolution) model on seen classes. The main contribution of this paper is the integration of Mixture-of-Experts into the Generator and Discriminator components of the Generative Zero-Shot Learning model for 3D point cloud semantic segmentation, applied to the COVERED dataset (CollabOratiVE Robot Environment Dataset) for Human-Robot Collaboration (HRC) environments. By combining the Generative Zero-Shot Learning model with Mixture-of- Experts, GZSL-MoE for 3D point cloud semantic segmentation provides a promising solution for understanding complex 3D environments, especially when comprehensive training data for all object classes is unavailable. The performance evaluation of the GZSL-MoE model highlights its ability to enhance performance on both seen and unseen classes. Keywords Generalized Zero-Shot Learning (GZSL), 3D Point Cloud, 3D Semantic Segmentation, Human-Robot Collaboration, COVERED (CollabOratiVE Robot Environment Dataset), KPConv, Mixture-of Experts

This paper presents a direct 3D visual servo scheme for the automatic alignment of point clouds (respectively, objects) using visual information in the spectral domain. Specifically, we propose an alignment method for 3D models/point clouds that works by estimating the global transformation between a reference point cloud and a target point cloud using harmonic domain data analysis. A 3D discrete Fourier transform (DFT) in $\mathbb{R}^3$ is used for translation estimation and real spherical harmonics in $SO(3)$ are used for rotation estimation. This approach allows us to derive a decoupled visual servo controller with 6 degrees of freedom. We then show how this approach can be used as a controller for a robotic arm to perform a positioning task. Unlike existing 3D visual servo methods, our method works well with partial point clouds and in cases of large initial transformations between the initial and desired position. Additionally, using spectral data (instead of spatial data) for the transformation estimation makes our method robust to sensor-induced noise and partial occlusions. Our method has been successfully validated experimentally on point clouds obtained with a depth camera mounted on a robotic arm.