HQC-NBV: A Hybrid Quantum-Classical View Planning Approach

TL;DR

HQC-NBV presents a hybrid quantum-classical framework for Next-Best-View planning in unknown environments, encoding viewpoint decisions into a 10-qubit Hamiltonian and optimizing with a variational circuit featuring bidirectional entanglement. The approach combines a multi-term cost Hamiltonian, a parameter-centric ansatz, and an SPSA-optimized VQE pipeline to achieve higher exploration efficiency than classical NBV methods. Empirical results across varied scenes show substantial improvements in coverage and path efficiency, with quantum components (entanglement structure and coherence terms) playing a key role. The work demonstrates compatibility with NISQ devices and offers a paradigm for integrating quantum variational methods into robotic perception tasks.

Abstract

Efficient view planning is a fundamental challenge in computer vision and robotic perception, critical for tasks ranging from search and rescue operations to autonomous navigation. While classical approaches, including sampling-based and deterministic methods, have shown promise in planning camera viewpoints for scene exploration, they often struggle with computational scalability and solution optimality in complex settings. This study introduces HQC-NBV, a hybrid quantum-classical framework for view planning that leverages quantum properties to efficiently explore the parameter space while maintaining robustness and scalability. We propose a specific Hamiltonian formulation with multi-component cost terms and a parameter-centric variational ansatz with bidirectional alternating entanglement patterns that capture the hierarchical dependencies between viewpoint parameters. Comprehensive experiments demonstrate that quantum-specific components provide measurable performance advantages. Compared to the classical methods, our approach achieves up to 49.2% higher exploration efficiency across diverse environments. Our analysis of entanglement architecture and coherence-preserving terms provides insights into the mechanisms of quantum advantage in robotic exploration tasks. This work represents a significant advancement in integrating quantum computing into robotic perception systems, offering a paradigm-shifting solution for various robot vision tasks.

Figures (8)

• Figure 1: Execution logic of our HQC-NBV. Different from the classical approaches, we do not rely on heuristics but leverage quantum superposition to simultaneously evaluate multiple view parameters and quantum entanglement to capture complex dependencies between movement decisions.
• Figure 2: (Left) The block scheme of the proposed variational ansatz; (Right) The block module with even and odd index. The light red dash line highlights the intra-group entanglement, and the light blue dash line highlights the bidirectional inter-group entanglement.
• Figure 3: The effectiveness of entanglement architecture on the exploration performance: (a) coverage ratio in Scene 1; (b) coverage ratio in Scene 2.
• Figure 4: The evaluation of coherence-preserving term on the exploration performance: (a) coverage ratio in Scene 1; (b) coverage ratio in Scene 2.
• Figure 5: (Left) The smoothed cost against the number of iterations in a single optimization, evaluate the effect of coherence-preserving term on the optimization process; (Right) The coverage against the number of views of our approach in different scenes