Advancing Enhancing Autonomous Vehicle Safety: Integrating Functional Safety and Advanced Path Planning Algorithms for Precise Control

Abstract

Automated vehicles, commonly known as self-driving cars, have garnered significant attention due to their potential benefits in terms of safety, efficiency, and convenience. However, their widespread adoption requires a thorough evaluation of potential risks and the level of automation. This paper addresses two critical aspects of autonomous driving: functional safety and route planning. In the realm of functional safety, we delve into the concepts of Functional Safety Concept (FSC) and Safety of the Intended Functionality (SOTIF) within the context of designing autonomous driving systems. The goal is to mitigate risks associated with scenarios where drivers may misuse the technology. This is achieved by incorporating fail-safe design principles and a comprehensive consideration of possible system failures to ensure a secure environment for autonomous driving. Path planning is a fundamental technology for autonomous navigation, and developing a robust and universally applicable path planning algorithm remains a significant challenge. To address this challenge, we introduce an Enhanced Spatiotemporal Multi-Level LSTM (ESM-LSTM) network combined with Bayesian Optimization (BO). This path planning system, based on deep learning, utilizes Convolution Multi-Level Long-Short Term Memory (Conv-MLSTM) to extract hidden features from sequential image data. Spatiotemporal information is further processed using a 3D Stacked Convolution Neural Network (3D-SCNN) in conjunction with BO. The resulting model provides real-time insights, ensuring reliable and accurate visual outcomes for autonomous vehicles. The planned trajectory is subjected to filtering to assess potential hazards, and a system-safe state architecture is proposed to enhance the control of autonomous vehicles.