Task Planning
Task planning in artificial intelligence focuses on enabling agents, both virtual and robotic, to autonomously generate sequences of actions to achieve specified goals. Current research emphasizes improving the robustness and efficiency of planning methods, particularly using large language models (LLMs) and visual language models (VLMs), often integrated with symbolic planning techniques or reinforcement learning, to handle complex, long-horizon tasks and multi-agent scenarios. This field is crucial for advancing embodied AI, improving decision-making in various domains (e.g., disaster response, robotics, game design), and developing more reliable and adaptable autonomous systems.
Papers
MACOptions: Multi-Agent Learning with Centralized Controller and Options Framework
Alakh Aggarwal, Rishita Bansal, Parth Padalkar, Sriraam Natarajan
Exploitation and exploration in text evolution. Quantifying planning and translation flows during writing
Donald Ruggiero Lo Sardo, Pietro Gravino, Christine Cuskley, Vittorio Loreto
Planning for Learning Object Properties
Leonardo Lamanna, Luciano Serafini, Mohamadreza Faridghasemnia, Alessandro Saffiotti, Alessandro Saetti, Alfonso Gerevini, Paolo Traverso
Diffusion-based Generation, Optimization, and Planning in 3D Scenes
Siyuan Huang, Zan Wang, Puhao Li, Baoxiong Jia, Tengyu Liu, Yixin Zhu, Wei Liang, Song-Chun Zhu
Design and Planning of Flexible Mobile Micro-Grids Using Deep Reinforcement Learning
Cesare Caputo, Michel-Alexandre Cardin, Pudong Ge, Fei Teng, Anna Korre, Ehecatl Antonio del Rio Chanona
LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models
Chan Hee Song, Jiaman Wu, Clayton Washington, Brian M. Sadler, Wei-Lun Chao, Yu Su