CogniPlan: Uncertainty-Guided Path Planning with Conditional Generative Layout Prediction

TL;DR

CogniPlan introduces a novel path planning framework that uses conditional generative layout prediction to improve exploration and navigation in unknown environments, effectively reasoning under uncertainty with strong empirical results.

Contribution

The paper presents CogniPlan, a new approach combining generative layout prediction with graph-based planning, enhancing uncertainty handling and performance in robotic navigation.

Findings

Outperforms state-of-the-art planners in exploration and navigation tasks.

Demonstrates high-quality path planning in simulation and real-world tests.

Effectively integrates generative models with graph-based planning for uncertainty reasoning.

Abstract

Path planning in unknown environments is a crucial yet inherently challenging capability for mobile robots, which primarily encompasses two coupled tasks: autonomous exploration and point-goal navigation. In both cases, the robot must perceive the environment, update its belief, and accurately estimate potential information gain on-the-fly to guide planning. In this work, we propose CogniPlan, a novel path planning framework that leverages multiple plausible layouts predicted by a COnditional GeNerative Inpainting model, mirroring how humans rely on cognitive maps during navigation. These predictions, based on the partially observed map and a set of layout conditioning vectors, enable our planner to reason effectively under uncertainty. We demonstrate strong synergy between generative image-based layout prediction and graph-attention-based path planning, allowing CogniPlan to combine the scalability of graph representations with the fidelity and predictiveness of occupancy maps, yielding notable performance gains in both exploration and navigation. We extensively evaluate CogniPlan on two datasets (hundreds of maps and realistic floor plans), consistently outperforming state-of-the-art planners. We further deploy it in a high-fidelity simulator and on hardware, showcasing its high-quality path planning and real-world applicability.