AISCO - Artificial Intelligence for Solar Car Optimisation - will revolutionize the Design process of Solar Race Cars. AISCO will define new ways of approaching sophisticated Design Challenges and disrupt existing methods ....
Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text Aisco Intro Text
Our aeroshell can only be placed between inner and outer bounding boxes. These are defined by:
- Regulations - defined by the World Solar Challenge Commitee, as vision requirements, wheelbase
- Requirements - defined by the aCentauri Solar Racing Team, as minimal solar input
- Primitive Components - as battery, occupant cell,
Our vision is to explore a variety of new aeroshell designs.
The optimiser maximises performance by minimising a cost function, consisting of multiple losses. Losses range from how well no build zones are respected over aerodynamic performance to solar power performance.The vision is to explore a variety of new aeroshell designs.
The optimiser maximises performance by minimising a cost function
Simulating an entire aerodynamic flow field for just one car design takes half a day with conventional methods.
Our approach is to train a Model to predict aerodynamic drag faster.
The performance metric will be fed back into the aeroshell optimiser as a loss function.
Solar power input depends on factors such as incidence angle, weather, bending angle of the solar deck, degree of bending, solar cell placement, string arrangement and more.
Almost all of these factors are dependent on the actual aeroshell.
The estimated solar power will be fed back into the aeroshell optimiser as a loss function.
We want users of our aeroshell optimisation model to be in control.
This is why we're developping a GUI (Graphical User Interface) to change specific constraints and regulations.
aCentauri is already 4 years old and its founders graduated from university.
Knowledgetransfer is of immense importance to survive as a student-led association.
This is why we're working on an LLM (Large Langauage Model), which we train on internal documents and messages.
Accessing knowledge will be way easier like this.
The AISCO Team consists of 9 ETH Focus Students and additional 5 Freelancers. Driven by passion, dedication and mutual trust, they are the heart of AISCO.
