A Bumblebee-Inspired Spatial Memory Navigation Framework for Robotic Odor Source Localization

Odor source localization in turbulent environments remains a major challenge for autonomous robots, as odor plumes are highly intermittent, spatially fragmented, and often lack stable concentration gradients. Here, we propose a bio-inspired navigation framework that translates key principles of bumblebee olfactory cognition into robotic decision-making. First, classical conditioning and olfactorily triggered spatial memory experiments demonstrated that bumblebees could form robust odor memories and that training frequency is positively correlated with both proboscis extension response retention and spatial directional preference. Based on these biological findings, a bio-inspired navigation framework, termed Bio-Nav, is constructed by integrating a Partially Observable Markov Decision Process, a Hidden Markov Model, short-term memory, long-term directional reference memory, fuzzy inference, and value iteration. High-fidelity two-dimensional turbulent simulations show that the proposed algorithm substantially outperforms moth-inspired search, Infotaxis, and standard POMDP-based navigation. In 100 Monte Carlo trials, Bio-Nav achieved a success rate of 96.0%, an average of 20.3 search steps, an average path length of 155.1 cm, and a path-to-straight-line distance ratio of 1.6. Even under strong turbulence, the success rate remained above 91%. These results indicate that memory-perception coupling, inspired by bumblebee navigation, provides an effective and robust strategy for odor source localization in complex turbulent environments, offering a generalizable principle for bio-inspired robotic search under uncertainty.