With more than 14 million electric vehicles (EVs) expected to be sold globally in 2023, it is clear the automotive industry has embraced the paradigm shift toward the future of sustainable mobility. Faced with the greatest disruption in the industry’s history, manufacturers are not only being challenged by a rapidly evolving technological landscape but also consumers’ demands for a seamless user experience.
To meet these highly complex and interrelated challenges the automotive industry, like many other sectors, has turned to artificial intelligence (AI) to help navigate the best course that will lead to the rapid and efficient rollout of the EV fleet. By leveraging the power of AI, EVs can be optimized to deliver superior performance, increased range, and reduced emissions, whilst providing a user experience deserving of the 21st century.
What is more, through the technology’s ability to process vast amounts of data and self-learn from real-world scenarios, AI is transforming EVs into intelligent machines capable of meeting the diverse needs and user experience (UX) expectations of modern consumers. From predictive maintenance that alerts the driver to potential malfunctions before they occur, to route planning and the seamless integration with smart homes and renewable energy systems, AI's unprecedented capabilities are molding EVs into true icons of sustainable, intelligent transportation.
Seamless AI elevates the UX and accelerates EV adoption
In EV battery cell research and development (R&D), AI’s ability to evaluate and learn from massive arrays of data has already led to major advances in material and chemistry selection. At the same time, its ability to learn and predict outcomes has drastically reduced the time required to forecast the lifetime performance of various complex and inter-dependent designs and chemistries, thereby reducing development costs as well as the time to market.
Manufacturers and service providers are harnessing these same features to deliver a heightened UX to the growing number of consumers turning to all-electric transportation.
And with EVs seen as the future of transport, drivers expect a seamless experience – one in which the car takes care of all the “chores” associated with vehicle ownership, without the owner’s intervention.
Thus, underpinned by machine learning (ML) EVs can seamlessly interrogate their systems and give themselves a clean bill of health, assessing wear in key components - including the battery, tires, brakes, gearbox, and suspension - in real-time. What is more, it can generate a “vehicle passport” on a tamper-proof, blockchained NFT containing all service and ownership records, and forecast when it needs servicing based on actual sensor readings, not simply kilometers driven.
AI also enhances the overall user experience in EVs by providing personalized features and intuitive interfaces from within the vehicle's infotainment system. Large Language Models (LLM) that are open source and can interact with huge data knowledge bases and using agents to perform tasks, can integrate with any physical or virtual device. LLM also learns user preferences and adapts vehicle settings accordingly.
Even though, as a stand-alone function, LLM would require a considerable amount of compute and GPU power, by utilizing existing hardware set up already to handle the various sensors – such as cameras and LiDAR – the impact is negligible.
Possibly of greater importance to the EV operator is AI’s role in optimizing the charging experience.
Optimizing the charging experience: AI predicts charging station congestion
With range and charge anxiety still high on the list of consumer concerns, AI is playing a key role in improving, not only range but also the overall charging experience.
In this regard, EV charging networks face a significant challenge in predicting and satisfying the demand for charging. To alleviate the pressure on charge stations, AI is used to evaluate historical data and create simulations to accurately predict demand. The data is analyzed based on usage patterns, time of day, seasonality, and other relevant factors. With this information, charging networks can optimize their capacity, plan for expansion, and avoid costly downtime.
Using AI, charging networks can be optimized, thereby delivering an improved UX | Image Source: StoreDot
At the same time, the charging network infrastructure can establish dynamic pricing models that respond to changes in user demand. By analyzing the data from charging stations and EVs, AI algorithms can determine which stations are experiencing high traffic and adjust pricing correspondingly. The enhanced data also helps to optimize the charging infrastructure, and for the consumer, enables real-time route planning, and reduced wait times.
Real-time feedback is essential for a positive user experience. By accessing metrics on each charging station’s usage and availability, customers can plan their trips accordingly. This information helps users minimize time spent at a charge station, making it an overall better experience than waiting around for a charging point to become available.
The integration of AI technology in charging station deployment and management is transforming the EV landscape. Intelligent infrastructure reduces deployment costs, enhances user experience, and drives EV adoption rates.
However, this is not the only way in which AI can advance EVs. By embedding AI and machine learning into the EV's operational software it is possible to continuously monitor the performance and health of the battery, and by recording the data and learning from it, the battery's operational parameters can be updated in real-time using OTA updates. By optimizing the battery performance within a narrower envelope than that set during R&D and industrialization the EV’s performance and range can be optimized, while also extending the battery's lifespan.
What is more, using AI, StoreDot, the developer of extreme fast charging (XFC) battery technology for EVs, has been granted a patent for a new and innovative technology that will allow battery cells to “heal” while they are in use, through a seamless background repair mechanism.
Enabled by AI, StoreDot’s self-healing battery technology ensures peak performance at all times
Underpinned by AI, StoreDot’s self-repairing system identifies a cell or module that is underperforming or overheating, and temporarily disables it in order to restore the battery back to 100 percent performance without the EV experiencing any downtime or loss of performance.
Using self-healing, this proactive approach can play a major role in prolonging battery life and driving range, as well as improving safety by preventing overheating or thermal runaway.
By always ensuring homogeneous cell performance across the pack, this AI-based system also offers manufacturers the opportunity to equip EVs with smaller XFC packs, safe in the knowledge that performance, durability, and safety are optimized at all times. Smaller fast-charging battery packs allow manufacturers to reduce costs without negatively impacting the consumer’s UX, thereby speeding up EV adoption.
As we move towards a greener, more sustainable future, it is essential that we leverage all available technologies to make the switch to EVs as accessible, affordable, and convenient as possible.
Artificial intelligence can help break down the barriers to EV adoption by improving accessibility, affordability, and convenience for consumers. By optimizing routing, providing real-time charging information, integrating payments, optimizing charging schedules, predicting battery life, and improving convenience through personalized charging and virtual assistants, AI has the potential to accelerate the uptake of EVs.
With the rapid advances being made in AI, the technology when applied to the EV ecosystem is set to assume a pivotal role in reducing costs and improving performance. StoreDot’s R&D success in developing a cutting-edge extreme fast charging battery technology with self-healing capability is proof of the effectiveness of AI in saving time and money and enhancing the consumer’s EV user experience.