In this talk we will look at a new algorithmic solution mitigating the effect of "range-anxiety" of electric vehicle owners, i.e. the fear of running out of the battery. We first employ automatic machine learning to learn how different drivers affect consumption of an electric car. We then use this knowledge to design a new efficient graph-planning algorithm to predict effective drivable range tailored for individual drivers.
YOU MAY ALSO LIKE:
- Brian Sletten's Data Science with Python Workshop (in London on 18th - 20th November 2019)
- Fast Track to Machine Learning with Louis Dorard (in London on 2nd - 4th December 2019)
- Practical ML 2020 (in London on 2nd - 3rd July 2020)
- Solandra Hands-On Tutorial & Emergent Behaviour In Insects (in London on 28th October 2019)
- A Guide to the Market Promise of Automagic AI-Enabled Detection and Response (in London on 29th October 2019)
- Using Kubeflow Pipelines for building machine learning pipelines (SkillsCast recorded in September 2019)
- Unleashing the Power of AI on projects; why we need to change culture (SkillsCast recorded in September 2019)
Algorithms for intelligent vehicles
Peter is a PhD student at Oxford University Mobile Robotics Group and has a strong background in algorithm design. His primary focus is on applications of Artificial Intelligence in robotics and his further research interests span areas as diverse as deep machine learning, inverse reinforcement learning, computer vision, planning and natural language processing. Peter has done internships in Facebook, Google, Microsoft Research and MetaMind. In his free time he enjoys participation in algorithmic programming competitions like TopCoder and Codeforces where he enjoys notable success.