Robotic Task
Robotic task research focuses on enabling robots to autonomously perform complex actions, often guided by high-level instructions (e.g., natural language commands). Current efforts concentrate on integrating large language models (LLMs) and vision-language models (VLMs) with task and motion planners, leveraging their semantic reasoning capabilities to generate and refine action sequences, often within a hierarchical planning framework. This research is crucial for advancing robot autonomy in unstructured environments and diverse applications, from manufacturing and warehousing to domestic assistance and search and rescue, by improving task success rates and reducing reliance on pre-programmed behaviors.
Papers
GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
Chi-Lam Cheang, Guangzeng Chen, Ya Jing, Tao Kong, Hang Li, Yifeng Li, Yuxiao Liu, Hongtao Wu, Jiafeng Xu, Yichu Yang, Hanbo Zhang, Minzhao Zhu
Abstract Hardware Grounding towards the Automated Design of Automation Systems
Yu-Zhe Shi, Qiao Xu, Fanxu Meng, Lecheng Ruan, Qining Wang
SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environments
Zachary Ravichandran, Varun Murali, Mariliza Tzes, George J. Pappas, Vijay Kumar
Guiding Long-Horizon Task and Motion Planning with Vision Language Models
Zhutian Yang, Caelan Garrett, Dieter Fox, Tomás Lozano-Pérez, Leslie Pack Kaelbling