Efficient Robot-Aided Outdoor Cleaning with a Glasius Bio-Inspired Neural Network and Vision-Based Adaptation

Robot-aided outdoor cleaning is a challenging task with plenty of room for improvement. The cleaning profile of a robot should be adjusted based on the availability of litter to ensure proper and efficient cleaning. This article proposes a novel system that integrates a Glasius Bio-Inspired Neural Network (GBNN) for coverage path planning with a vision-based cleaning profile adaptation scheme. The vision-based adaptation occurs based on the presence of leaves on the ground. The proposed system operates in two phases: an initial phase with low-power cleaning to cover areas with no leaves, while localizing leaf spots that require high-power cleaning, and a secondary phase focusing on cleaning these detected leaf spots using a high-power cleaning profile. This cleaning profile adaptation enables more efficient and effective cleaning. Simulation results showed a 47% improvement in energy efficiency for the proposed method compared to a method with no cleaning profile adaptation. Robot hardware tests conducted using the Panthera 2.0 outdoor cleaning robot have demonstrated the real-world applicability of the proposed method.