Car manufacturers, suppliers, dealers and service providers understand that quantum computing will eventually have a major impact on almost every aspect of the industry. Daimler, Honda, Hyundai, Ford, BMW, Volkswagen and Toyota have some sort of quantum evaluation program in place.
Classical computers cannot solve many of the significant real-world problems due to computational complexity or because calculations would take an inordinate amount of time, perhaps hundreds, thousands or even millions of years. Quantum computing offers the potential to solve these problems in a reasonable amount of time. While current hardware is not advanced enough to support the number of qubits required, we are already working to implement error correction solutions to build fault-tolerant quantum machines.
The same hardware constraints and error correction limit the full potential of quantum machine learning. In some cases, it has proven useful with current quantum computers; may also exceed the results of some classic models.
IonQ has a history of researching quantum machine learning, so I was looking forward to talking to Peter Chapman, CEO of IonQ, about their partnership with Hyundai Motors.
First, Chapman explained that the purpose of the partnership is to determine the potential of quantum computing to provide improved mobility solutions for autonomous vehicles. For these projects, IonQ will use Aria, its latest trapped ion quantum computer.
IonQ combined its quantum computing expertise with Hyundai’s lithium battery expertise two months ago. It is developing sophisticated quantum chemistry simulations to study battery charge and discharge cycles, capacity, durability and safety.
As an evolution of their relationship, the IonQ and Hyundai team will develop quantum machine learning (QML) models to detect and recognize traffic signs and identify 3D objects such as pedestrians and cyclists.
Recognizing traffic signs and identifying 3D objects are critical elements of Advanced Driver Assistance Systems (ADAS) used by autonomous vehicles. ADAS relies on cameras, lidar, radar and other sensors for inputs to onboard AV computers that interpret and respond to the driving environment. A 2016 study by the National Highway Transportation Safety Administration found that 94% to 96% of accidents are caused by human error. With enhanced quantum inputs for ADAS, it is likely that human error can be minimized to reduce accidents.
Earlier in his career, Chapman served as president of a Ray Kurzweil company, where he gained experience in machine learning. As a result, he has a deep understanding of classic machine learning models and the complicated steps required to identify images. More importantly, he understands why QML will be so much faster and more efficient than its classic counterpart.
“QML doesn’t need multiple processing steps for traffic sign recognition like classical approaches to object detection,” he said. “Quantum recognizes a sign and interprets its meaning in a single step.”
IonQ has already completed the difficult computational part of the road sign recognition project. It has trained quantum machine learning (QML) models using a standardized database of 50,000 images to recognize 43 different classifications of traffic signs. Next, IonQ will test its QML model under real driving conditions using Hyundai’s test environment.
Chapman also explained why he believes quantum machine learning and object recognition will be much more powerful than classics.
“What happens if your car sees something it’s never been trained for before? Let’s take an unusual case, like a person with a triple stroller, walking two dogs on a leash, talking on their iPhone and carrying a bag of groceries. training data had never seen this scenario, how would the car respond? I think quantum machine learning will fill in those gaps and provide a known answer to things it hasn’t seen before.”
Marcos IonQ Quantum ML
The following summarizes several QML projects that IonQ has participated in in recent years.
- In a partnership between IonQ and QC Ware, classical data was loaded into quantum states to enable efficient and robust QML applications.
- On IonQ computers, machine learning reached the same level of precision and worked faster than on classic computers.
- The project used QC Ware’s Forge Data Loader™ technology to transform classical data into quantum states.
- The quantum algorithm, running on IonQ hardware, worked at the same level as the classical algorithm, identifying the right digits 8 out of 10 times on average, the same number of times as the classical algorithm running on classical hardware.
- Researchers at IonQ and the Fidelity Center for Applied Technology (FCAT) used IonQ’s cloud-based quantum computer to develop a proof-of-concept QML model to analyze numerical relationships in the daily returns of Apple and Microsoft stocks from 2010 to 2018. Daily returns are the price of a stock at the daily close compared to its price at the close of the previous day. The metric measures the daily performance of stocks.
- Two QML algorithms used historical daily return data to produce a highly accurate synthetic dataset to assess forecast accuracy. The model demonstrated that quantum computers can be used to generate correlations that cannot be efficiently reproduced by classical means such as probability distribution.
- IonQ and Zapata Computing have developed the first practical and experimental implementation of a hybrid quantum-classical QML algorithm that can generate high-resolution images of handwritten digits.
- To train the hybrid algorithm, they used NIST’s extensive handwritten digit database.
- The results outperformed comparable classical Generative Adversarial Networks (GAN) trained on the same database. GAN is a machine learning model with two neural networks that compete with each other to produce the most accurate prediction.
- In October 2021, IonQ became the first pure quantum company listed on the New York Stock Exchange.
- While quantum computing is still in its infancy, it is too early to select a technology that will lead to error-free quantum systems that use millions of qubits to solve world-changing problems. Technology that works at this level may not even be in use today. The scale to millions of logical qubits is still many years away for all gate-based quantum computers.
- Quantum qubits are fragile and susceptible to errors caused by interacting with their environment. Error correction is a subject of serious research by almost all quantum companies. It will not be possible to scale quantum computers to a large number of qubits until a viable error correction technique is developed. I expect significant progress in 2022.
- Technical details of the daily IonQ-FCAT stock return study are available here.
- Technical details of the IonQ-Zapata Hybrid QML Research are available here.
- Access to IonQ quantum systems is available through the cloud on Amazon Braket, Microsoft Azure and Google Cloud and through direct API access.
Disclosure: My company, Moor Insights & Strategy, like all research firms and analysts, provides or has provided research, analysis, advice and/or consultancy to many high-tech companies in the industry. I do not hold any equity position in any of the companies mentioned in this column.
Find more from Moor Insights & Strategy on their website, twitterLinkedIn, Facebook, Google+ and YouTube.