The HA Based Robot Navigation using MBS Method

Multiple methods of human-aware navigation are developing in tandem with the emergence of social robots. This article presents a comprehensive standard for the quantitative evaluation of robot navigation methods. System designers may use the Social Robot Planner Benchmark (SRPB), an automated quantitative tool that generates consistent performance indicators for algorithms, to choose the optimum strategy for certain applications. As an alternative to conventional measures of work performance, our standard provides innovative social metrics such as the degree to which humans feel comfortable in the robot’s environment and the degree to which robot actions seem natural, with a focus on how reliable human tracking is. Efficient navigation of service robots in scenarios involving human assistance requires a delicate balance between optimizing the robot’s path and ensuring user comfort and safety. Our approach employs Bayesian inference for predicting the user’s navigation goal and time-dependent path planning to achieve this balance effectively. By leveraging an interaction model and computing the belief about the user’s intended destination, our method provides accurate predictions regularly updated based on new observations. Through a comprehensive evaluation, we demonstrate that our approach maintains a comfortable separation between the robot and the user while complying with social distance norms and minimizing the difference in arrival time. Statistical analysis reveals the superiority of our approach in terms of human-robot distance, significantly enhancing user comfort and safety during navigation scenarios.