Behavior-Aware Online Prediction of Obstacle Occupancy using Zonotopes

2025-10-23

AI Summary

Predicting future occupancy regions of dynamic obstacles (e.g., vehicles) in unstructured urban environments without prior knowledge remains challenging due to the absence of reliable dynamics models or historical trajectory data. Method: This paper proposes a purely motion-observation-driven online prediction method. It introduces a behavior-aware zonotope set representation, integrating extended Kalman filtering with linear programming to estimate a compact zonotope bounding the latent control inputs in real time. Forward reachability analysis is then applied to compute conservative, model-free, training-free occupancy predictions. Contribution/Results: The approach requires no prior dynamical model or training data and provides mathematically rigorous, real-time safety guarantees. Evaluated in urban simulation scenarios, it generates high-accuracy, compact, and provably safe future occupancy sets—significantly enhancing navigation robustness and safety of autonomous driving systems in complex, dynamic environments.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Intelligent Robots: State Estimation

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Security and Privacy: Large-scale security measurements

Abstract

Predicting the motion of surrounding vehicles is key to safe autonomous driving, especially in unstructured environments without prior information. This paper proposes a novel online method to accurately predict the occupancy sets of surrounding vehicles based solely on motion observations. The approach is divided into two stages: first, an Extended Kalman Filter and a Linear Programming (LP) problem are used to estimate a compact zonotopic set of control actions; then, a reachability analysis propagates this set to predict future occupancy. The effectiveness of the method has been validated through simulations in an urban environment, showing accurate and compact predictions without relying on prior assumptions or prior training data.

Problem

• Predicting vehicle motion in unstructured autonomous driving environments
• Estimating control actions using zonotopes without prior assumptions
• Propagating reachability analysis for future occupancy set prediction

Innovation

• Uses Extended Kalman Filter for control estimation
• Applies zonotopic sets for occupancy prediction
• Combines reachability analysis with linear programming