Deployment-friendly Lane-changing Intention Prediction Powered by Brain-inspired Spiking Neural Networks

2025-02-09

AI Summary

To address the challenges of poor real-time performance, high computational and memory overhead, and difficulty in edge deployment for surrounding vehicle lane-change intention prediction in open-world autonomous driving, this paper introduces spiking neural networks (SNNs)—for the first time—to this task, proposing a lightweight spatiotemporal modeling framework. The method integrates brain-inspired neural dynamics, event-driven state encoding, and sparse spike-based computation. Evaluated on HighD and NGSIM datasets, it achieves a 75% reduction in training time, a 99.9% decrease in memory footprint, and significantly accelerated inference, while maintaining prediction accuracy comparable to state-of-the-art artificial neural networks (ANNs). This work overcomes the deployment bottleneck of conventional deep models on resource-constrained in-vehicle platforms, establishing a novel paradigm for low-power, high-real-time intention perception.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Learning on the Edge & Model Compression
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

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: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Accurate and real-time prediction of surrounding vehicles' lane-changing intentions is a critical challenge in deploying safe and efficient autonomous driving systems in open-world scenarios. Existing high-performing methods remain hard to deploy due to their high computational cost, long training times, and excessive memory requirements. Here, we propose an efficient lane-changing intention prediction approach based on brain-inspired Spiking Neural Networks (SNN). By leveraging the event-driven nature of SNN, the proposed approach enables us to encode the vehicle's states in a more efficient manner. Comparison experiments conducted on HighD and NGSIM datasets demonstrate that our method significantly improves training efficiency and reduces deployment costs while maintaining comparable prediction accuracy. Particularly, compared to the baseline, our approach reduces training time by 75% and memory usage by 99.9%. These results validate the efficiency and reliability of our method in lane-changing predictions, highlighting its potential for safe and efficient autonomous driving systems while offering significant advantages in deployment, including reduced training time, lower memory usage, and faster inference.

Problem

• predict lane-changing intentions accurately
• reduce computational and memory costs
• enhance autonomous driving system efficiency

Innovation

• Spiking Neural Networks for prediction
• Event-driven encoding of states
• Reduced training and memory costs