FORTE: Forecasting Occupancy for Spatiotemporal Risk-Aware Planning in Dynamic Environments

2026-09-30

AI Summary

This study addresses the limited navigation accuracy, computational inefficiency, and underutilization of temporal information inherent in Occupancy Grid Map (OGM) prediction within dynamic environments. To overcome these challenges, we propose FORTE, a framework that innovatively leverages predicted OGMs for path selection from a spatiotemporal evolution perspective. Specifically, it enables detection-free, risk-aware planning through spatiotemporal occupancy overlap and directionality assessment. Furthermore, by integrating latent diffusion models with time-shift modules, FORTE generates temporally consistent OGMs in a non-autoregressive manner. Experimental results demonstrate substantial improvements over existing state-of-the-art methods, achieving up to a 215.3% increase in prediction IoU, a 5.24× inference speedup, and navigation success rates up to 3.5 times those of baseline approaches.

Abstract

Safe navigation in dynamic environments requires anticipating future environmental states to account for spatiotemporal risks, specifically when and where collisions may occur. To this end, occupancy grid map (OGM) prediction has been widely adopted as an effective approach. However, existing OGM-based navigation methods often struggle to achieve accurate and efficient forecasting and fail to fully exploit the temporal information in predicted OGMs during planning. To address these challenges, we propose FORTE, a navigation framework that directly exploits the spatiotemporal evolution of predicted occupancy from the perspectives of spatiotemporal occupancy overlap and occupancy directivity. Based on these properties, FORTE evaluates multiple topology-distinct paths and selects the suitable one without explicit object detection or tracking. To support online planning, we formulate a latent diffusion model-based OGM predictor that generates the entire forecast horizon in a non-autoregressive manner while maintaining temporal consistency through temporal shift modules. Extensive evaluations demonstrate that FORTE outperforms state-of-the-art baselines. For prediction, FORTE achieves up to 215.3% higher IoU and 5.24x faster inference; for navigation, it yields up to a 3.5x higher success rate.

Problem

• dynamic environment navigation
• occupancy grid map prediction
• spatiotemporal risk
• safe planning

Innovation

• Occupancy Grid Map Prediction
• Latent Diffusion Model
• Non-autoregressive Forecasting
• Spatiotemporal Risk-Aware Planning
• Temporal Shift Modules