Machine Learning Architectures for the Estimation of Predicted Occupancy Grids in Road Traffic

2025-12-14

AI Summary

To address the challenge of probabilistic spatiotemporal forecasting in complex traffic scenarios, this paper proposes a novel architecture integrating enhanced occupancy grids (AOG) as input and probabilistic occupancy grids (POG) as output. Methodologically, we introduce the first hybrid model coupling dual-stacked denoising autoencoders (SDA) with random forests, achieving high prediction accuracy while significantly reducing computational overhead. We also establish, for the first time, a systematic mapping between POGs and active safety decisions—including emergency braking and lane changes. Experiments demonstrate that our approach improves prediction accuracy by 7.2% and accelerates inference speed by 3.8× over the SDA+DeconvNet baseline. Crucially, POGs explicitly encode behavioral uncertainty of traffic agents, providing interpretable, probabilistic foundations for downstream safety-critical decision-making.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Relational Probabilistic Models
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

This paper introduces a novel machine learning architecture for an efficient estimation of the probabilistic space-time representation of complex traffic scenarios. A detailed representation of the future traffic scenario is of significant importance for autonomous driving and for all active safety systems. In order to predict the future space-time representation of the traffic scenario, first the type of traffic scenario is identified and then the machine learning algorithm maps the current state of the scenario to possible future states. The input to the machine learning algorithms is the current state representation of a traffic scenario, termed as the Augmented Occupancy Grid (AOG). The output is the probabilistic space-time representation which includes uncertainties regarding the behaviour of the traffic participants and is termed as the Predicted Occupancy Grid (POG). The novel architecture consists of two Stacked Denoising Autoencoders (SDAs) and a set of Random Forests. It is then compared with the other two existing architectures that comprise of SDAs and DeconvNet. The architectures are validated with the help of simulations and the comparisons are made both in terms of accuracy and computational time. Also, a brief overview on the applications of POGs in the field of active safety is presented.

Problem

• Estimates future traffic scenarios using probabilistic space-time representation
• Identifies traffic scenario types and maps current to future states
• Compares novel machine learning architectures for accuracy and efficiency

Innovation

• Uses Augmented Occupancy Grids as input for prediction
• Combines Stacked Denoising Autoencoders with Random Forests
• Outputs probabilistic Predicted Occupancy Grids with uncertainties