Integrating Specialized and Generic Agent Motion Prediction with Dynamic Occupancy Grid Maps

TL;DR

This paper introduces a unified framework that combines agent-specific and agent-agnostic scene prediction using Dynamic Occupancy Grid Maps, improving accuracy in complex driving environments by modeling multiple future scenarios.

Contribution

The authors propose a novel integrated approach leveraging Dynamic Occupancy Grid Maps and a specialized loss function for joint prediction of occupancy, flow, and agent behaviors in driving scenes.

Findings

Outperforms baseline methods on nuScenes and Woven Planet datasets.

Accurately predicts behaviors of vehicles and other dynamic scene elements.

Effectively models multiple future scenarios with improved robustness.

Abstract

Accurate prediction of driving scene is a challenging task due to uncertainty in sensor data, the complex behaviors of agents, and the possibility of multiple feasible futures. Existing prediction methods using occupancy grid maps primarily focus on agent-agnostic scene predictions, while agent-specific predictions provide specialized behavior insights with the help of semantic information. However, both paradigms face distinct limitations: agent-agnostic models struggle to capture the behavioral complexities of dynamic actors, whereas agent-specific approaches fail to generalize to poorly perceived or unrecognized agents; combining both enables robust and safer motion forecasting. To address this, we propose a unified framework by leveraging Dynamic Occupancy Grid Maps within a streamlined temporal decoding pipeline to simultaneously predict future occupancy state grids, vehicle grids, and scene flow grids. Relying on a lightweight spatiotemporal backbone, our approach is centered on a tailored, interdependent loss function that captures inter-grid dependencies and enables diverse future predictions. By using occupancy state information to enforce flow-guided transitions, the loss function acts as a regularizer that directs occupancy evolution while accounting for obstacles and occlusions. Consequently, the model not only predicts the specific behaviors of vehicle agents, but also identifies other dynamic entities and anticipates their evolution within the complex scene. Evaluations on real-world nuScenes and Woven Planet datasets demonstrate superior prediction performances for dynamic vehicles and generic dynamic scene elements compared to baseline methods.