2 papers
cs.RO2026
CLAR: Learning 3D Representations for Robotic Manipulation by Fusing Masked Reconstruction with Multi-Level Contrastive Alignment
Wenbo Cui, Chengyang Zhao, Yuhui Chen +4
The spatial information inherent in 3D point clouds is crucial for robotic manipulation. However, existing 3D pre-training methods face a fundamental trade-off: Masked Autoencoding…
cs.RO2024
RoboGPT: an intelligent agent of making embodied long-term decisions for daily instruction tasks
Yaran Chen, Wenbo Cui, Yuanwen Chen +4
Robotic agents must master common sense and long-term sequential decisions to solve daily tasks through natural language instruction. The developments in Large Language Models (LLM…