Mobile Robots for Environment-Aware Navigation: A Code-Free Approach with Topometric Maps for Non-Expert Users

The growing use of mobile robots in unconventional environments demands new programming approaches to make them accessible to non-expert users. Indeed, traditional programming methods require specialized expertise in robotics and programming, limiting robots’ accessibility to a broader audience. End-user robot programming has emerged to overcome these limitations, aiming to simplify robot programming through intuitive methods. In this work, we propose a code-free approach for programming mobile robots to autonomously execute navigation tasks, i.e., reach a desired goal location from an arbitrary initial position. Our method relies on instructing the robot on new paths through demonstrations while creating and continuously updating a topometric map of the environment. Moreover, by leveraging the information gathered during the instruction phase, the robot can perceive slight environmental changes and autonomously make the best decision in response to unexpected situations (e.g., adjusting its path, stopping, or requesting user intervention). Experiments conducted in both simulated and real-world environments support the validity of our approach, as they show that the robot can successfully reach its assigned goal location in the vast majority of cases.