University of Wisconsin–Madison

Quantum-Assisted Machine Learning for Mobility Studies

Flow chart of QAHMIn this project we explore and provide a proof-of-concept approach to solving ground vehicle mobility-related problems on emerging quantum computing (QC) machines, in particular as embodied in the D-Wave quantum annealer systems.

We identify the problem of generating mobility maps (Go/No-Go and speed-made-good) as a suitable target problem, which can be mapped into a problem amenable to QC, taking into consideration current hardware limitations. Such problems are first cast as machine learning problems and subsequently solved using quantum-assisted algorithms, while relying on classical high-performance computing simulations for the generation of the required training and test sets.

The prediction chart of the QAHM simulationThe premise of this work rests on two observations. First, quantum computing allows in principle for algorithms that provide a speedup over the best known classical counterparts. However, as it is to be expected of such novel and complex tools (both hardware and algorithmic) at this early developmental stage, current quantum algorithms do not always perform well on real-world problems. Second, complex physics-based vehicle and terramechanics models and simulations, currently advocated for high-fidelity ground vehicle — terrain interaction analyses, pose significant computational burden, especially when applied to mobility studies which may require numerous simulation runs.

This work represents a contribution to an ongoing effort of exploring the applicability of the emerging field of quantum computing to challenging engineering and scientific problems.

Contributors: Radu Serban