The transformation in autonomous vehicles has seen huge advancements in innovation, with tech organizations heavily investing in research and development in self-driving technology. The earlier ten years saw an important ascent in the progression of autonomous vehicles, fundamentally supported by improvements in deep learning and artificial intelligence. However, when we saw the boundless reception of autonomous vehicles on our streets, we encountered many anomalies in the framework and some accident cases as well. Decision-making is a critical and complex aspect of self-driving cars, being essential to guaranteeing the effectiveness, safety, and adaptability of autonomous cars. Effective decision-making is at the core of the success and acceptance of self-driving cars. The development of robust algorithms, ethical considerations, adaptability to various conditions, and compliance with legal standards are all crucial elements that contribute to the overall functionality and safety of autonomous vehicles. The crust of any self-driving vehicle is its neural network as it is ultimately responsible for decision-making. As the traditional Neural Network Architectures fail to achieve efficient decision-making in self-driving cars we propose a new Neural Network to achieve effective decision making thus lowering the number of accidents gradually leading to safe driving.
CarLINK: AI Driven Traffic Adviser for Automobiles
07.06.2024
1039193 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Real-Time Surface Traffic Adviser
NTRS | 2001
|An Advanced Body System Application Using Active Junction Boxes with Carlink Data Communication
SAE Technical Papers | 1991
|Electrically driven automobiles
Engineering Index Backfile | 1899
|Engineering Index Backfile | 1934
|