When using the phrase "Artificial Intelligence", the first thing that comes to most of the researchers is safety. Employment of techniques like Supervised learning, Reinforcement learning can prove pivotal (in terms of computational time, etc.) in developing controls for vehicle behaviour. But since, neural networks do not directly work based on the physical equations behind modelling controls, the question that arises is the "trust" you put into such methods. Are there any approaches put forward to make sure that the solution is robust and safe? I can see some literature in vertical dynamics field but I am interested in lateral dynamics as well.
Hi Guru,
Yes. It can be used for such kind of problem.
Please see the attachments.
Hello there, we have just unveiled our new environment in this area. This might be of interest to you:
https://www.researchgate.net/post/Are_you_looking_for_a_research_topic_in_AI_Reinforcement_Learning
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Control Theory
- Control Systems