A5008213233- Electric and Hybrid Vehicle Technologies
- Electric Vehicles and Infrastructure
- Vehicle emissions and performance
- Advanced Battery Technologies Research
- Reinforcement Learning in Robotics
- Transportation Planning and Optimization
- Traffic control and management
- Respiratory Support and Mechanisms
- Evolutionary Algorithms and Applications
- Mental Health Research Topics
- Modular Robots and Swarm Intelligence
- Railway Systems and Energy Efficiency
- Machine Learning in Healthcare
- Transportation Systems and Logistics
- Transportation and Mobility Innovations
- Explainable Artificial Intelligence (XAI)
- Traffic Prediction and Management Techniques
Deutsche Bahn (Germany)
2024
Institute of Computer Vision and Applied Computer Sciences
2024
TU Dresden
2017-2021
In order to maximize the energy efficiency of hybrid vehicles, both electric powertrain hardware and management have be optimized. Focusing on a certain deterministic driving cycle during design can lead higher consumption in customer use, as real cycles differ cycles. This contribution uses modern Deep Reinforcement Learning (DRL) management, which is able optimize controls for stochastic vehicle use. Additionally, Bayesian Optimization sequentially operating with DRL selects suitable...
Reinforcement Learning (RL) is a subfield of machine learning for artificially intelligent systems to solve variety complex problems [1].Recent years have seen surge applicative successes using RL challenging games and smaller domain [2][3][4].These in been achieved part due the strong collaborative effort by community work on common, open-sourced environment simulators such as OpenAI's Gym [5] that allow expedited development valid comparisons between different, state-of-art...