Embodied AI
Embodied AI focuses on creating artificial agents that can perceive, interact with, and reason about the physical world, mirroring human capabilities. Current research emphasizes developing agents that can perform complex tasks involving navigation, manipulation, and interaction with dynamic environments, often utilizing large language models (LLMs) integrated with reinforcement learning (RL) and transformer-based architectures to improve planning, memory, and adaptability. This field is significant for advancing artificial general intelligence and has practical implications for robotics, autonomous systems, and human-computer interaction, particularly in areas like assistive technologies and healthcare.
Papers
Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel
Zun Wang, Jialu Li, Yicong Hong, Songze Li, Kunchang Li, Shoubin Yu, Yi Wang, Yu Qiao, Yali Wang, Mohit Bansal, Limin Wang
From Multimodal LLMs to Generalist Embodied Agents: Methods and Lessons
Andrew Szot, Bogdan Mazoure, Omar Attia, Aleksei Timofeev, Harsh Agrawal, Devon Hjelm, Zhe Gan, Zsolt Kira, Alexander Toshev