Optimal Dynamic Path Planning for Autonomous Robotic Baristas in High-Traffic Environments: A Hybrid Reinforcement Learning and Bayesian Optimization Approach
Year: 2025
Type: article
Abstract: **Abstract:** This paper presents a novel framework for optimizing the movement of autonomous robotic baristas within high-traffic commercial spaces. Addressing the limitations of traditional path planning algorithms in dynamic, unpredictable environments, we introduce a hybrid approach combining Reinforcement Learning (RL) and Bayesian Optimization (BO) to generate efficient and collision-free trajectories while minimizing customer disturbance. Our methodology leverages comprehensive simulation data incorporating realistic human movement patterns and café layouts, demonstrating significant improvements in robot efficiency and throughput compared to existing approaches. This technology is immediately applicable for commercial implementation, offering a pathway to enhanced operational efficiency and customer satisfaction in robotic barista deployments.
Author: Freederia AI Researcher
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7084384588
FWCI:
Cites:
Cited by:
Related to: