Forte improves safe path planning by forecasting future occupancy rapidly
FORTE: Forecasting Occupancy for Spatiotemporal Risk-Aware Planning in Dynamic Environments
Robotics
Summary
Navigating safely in places where things move, like busy streets, needs predicting where obstacles will be next. The authors created FORTE, a system that predicts future space occupancy efficiently and uses this to choose safer paths without tracking individual objects. It forecasts the whole future scene quickly while keeping the timeline consistent, helping robots or vehicles avoid collisions. Their tests show FORTE is much faster and more accurate compared to previous methods, increasing successful navigation rates.
What this means in practice
- •For autonomous vehicle developers: Improve vehicle navigation safety by predicting future obstacle locations more accurately and quickly without explicit object detection.$Commercial implications: Supports development of advanced driver-assistance systems and self-driving cars needing real-time risk-aware path planning.
- •For robotics engineering teams: Enable robots to select safer paths in dynamic settings by forecasting occupancy grid maps over time efficiently.
Authors
Hahjin Lee, Young J. Kim
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.