Akira Taniguchi ^* Shuya Ito Tadahiro Taniguchi

• Ritsumeikan University, Kyoto, Japan

Assisting individuals in their daily activities through autonomous mobile robots, especially for users without specialized knowledge, is a significant concern. Specifically, the capability of robots to navigate to destinations based on human speech instructions is crucial. Although robots can take different paths toward the same objective, the shortest path is not always the most suitable. A preferred approach is to accommodate waypoint specifications flexibly, for the planning of an improved alternative path, even with detours. Furthermore, robots require real-time inference capabilities. Spatial representations include semantic, topological, and metric-level representations, each capturing different aspects of the environment. This study aimed to realize a hierarchical spatial representation using a topometric semantic map and path planning with speech instructions, including waypoints. This paper presents a hierarchical path-planning method called Spatial Concept-based Topometric Semantic Mapping for Hierarchical Path Planning (SpCoTMHP), which integrates place connectivity. This approach provides a novel integrated probabilistic generative model and fast approximate inference with interaction among the hierarchy levels. A formulation based on control as probabilistic inference theoretically supports the proposed path planning algorithm. We conducted experiments in home environments using the Toyota Human Support Robot on the SIGVerse simulator and in a lab-office environment with the real robot, Albert. The user issues speech commands that specify the waypoint and goal, such as "Go to the bedroom via the corridor." Navigation experiments using speech instruction with a waypoint demonstrated the performance improvement of the SpCoTMHP compared to the baseline, hierarchical path planning method with heuristic path costs (HPP-I), in terms of the weighted success rate at which the robot reaches the closest target and passes the correct waypoints, by 0.590. The computation time was significantly accelerated by 7.14 sec with the SpCoTMHP compared to baseline HPP-I in advanced tasks. Thus, hierarchical spatial representations provide a mutually understandable form for humans and robots, thus enabling language-based navigation tasks.