Optimization of Robot-Trajectory Planning with Nature-Inspired and Hybrid Quantum Algorithms

We solve robot trajectory planning problems at industry-relevant scales. Our end-to-end solution integrates highly versatile random-key algorithms with model stacking and ensemble techniques, as well path relinking for refinement. The core optimization module consists of a biased genetic algorithm. Through distinct separation problem-independent problem-dependent modules, we achieve an efficient problem representation, native encoding constraints. show that generalizations to alternative algorithmic paradigms such simulated annealing are straightforward. provide numerical benchmark results industry-scale data sets. approach is found consistently outperform greedy baseline results. To assess the capabilities today's quantum hardware, complement classical obtained on using qbsolv Amazon Braket. Finally, how latter can be integrated into our larger pipeline, providing quantum-ready hybrid problem.