Fuel efficiency and range are two of the most important metrics in the automotive industry. As regulations constantly get stricter, it is critical to continually extend the range of cars without increasing their fuel usage. Car manufacturers can increase range by optimizations to the hardware, but large gains can also be achieved by improvements to a car’s software. DeepSim can be used to automatically generate this type of controller software. Since software upgrades do not require materials, the expense is fixed and does not increase the bill of materials.
In this blog post we present a whitepaper for a detailed case study on how the minds.ai DeepSim platform is used to train an RL-agent that controls the energy management system of a Hybrid Electric Vehicle (HEV). The trained agent can improve the fuel efficiency of an HEV over previously unseen drive cycles.
The topics covered in the white paper are:
- Reinforcement learning and hybrid electric vehicles overview.
- Adapting a simulator for use with DeepSim.
- Using DeepSim to train with the simulator.
- Training experiments.
- Summary of results.
The whitepaper can be found here.
For more information about DeepSim see the dedicated section on our website, or contact us via firstname.lastname@example.org for more information, demos and a discussion on how DeepSim can help to improve performance while decreasing your time to market and development cost.
In the above figure we compare the efficiency of the trained RL agent with that of the existing (optimized) baseline software.
The DeepSim optimized controller increases the fuel efficiency by almost 4%.