Robust Planning

Robust planning focuses on creating reliable and efficient plans for autonomous systems, particularly in uncertain or dynamic environments, aiming to minimize failures and optimize performance despite unforeseen events. Current research emphasizes methods incorporating risk assessment (e.g., Conditional Value-at-Risk), adaptive world models (e.g., using graph convolutional neural networks), and neuro-symbolic approaches combining the strengths of large language models and symbolic planners to handle complex tasks and uncertainties. These advancements are crucial for improving the safety and reliability of autonomous robots in various applications, from autonomous driving and underwater exploration to human-robot collaboration and logistics.