DIFF-IPPO: Diffusion-Based Informative Path Planning with Open-Vocabulary Belief Maps
This work addresses the problem of informative path planning for robots with non-Gaussian, multimodal belief maps from semantic perception, offering a novel diffusion-based approach for global trajectory generation.
DIFF-IPPO integrates an open-vocabulary belief map generator with a diffusion-based planner for global trajectory generation, achieving normalized detection scores between 81.49% and 86.55% across dataset scenarios and enabling a team of five drones to achieve first detections in 3.5 minutes in a simulated search-and-rescue scenario.
Exploration and object search require robots to perceive their environment, identify regions of interest, and plan trajectories that improve target-detection likelihood or maximize information gain. Many IPP methods, especially in continuous environmental monitoring, rely on Gaussian-process belief models, while object-search settings often produce complex, multimodal belief maps from semantic or open-vocabulary perception. Global trajectory generation directly conditioned on such non-Gaussian belief maps remains comparatively underexplored. Although diffusion-based planners offer strong capabilities for modeling such distributions, their use in informative path planning remains limited. In this work, we propose DIFF-IPPO, a pipeline that integrates an open-vocabulary belief map generator with a diffusion-based planner for global trajectory generation over belief maps. The method generates trajectories that concentrate sensor coverage over high-belief regions, achieving normalized detection scores between 81.49% and 86.55% across different dataset scenarios. We validate the system in a simulated search-and-rescue scenario where the planner searches candidate building regions to locate a burning building. In this setting, a team of five drones using batched belief-map-conditioned trajectory generation achieves first detections in 3.5 minutes.