Acting and Planning with Hierarchical Operational Models on a Mobile Robot: A Study with RAE+UPOM
This addresses robotic task execution challenges for mobile robots, but it is incremental as it builds on existing hierarchical models and planning methods.
The paper tackles the inconsistency between symbolic planner models and actual robot control by deploying an integrated actor-planner system, RAE+UPOM, on a mobile manipulator for object collection, demonstrating robust execution under failures and noise.
Robotic task execution faces challenges due to the inconsistency between symbolic planner models and the rich control structures actually running on the robot. In this paper, we present the first physical deployment of an integrated actor-planner system that shares hierarchical operational models for both acting and planning, interleaving the Reactive Acting Engine (RAE) with an anytime UCT-like Monte Carlo planner (UPOM). We implement RAE+UPOM on a mobile manipulator in a real-world deployment for an object collection task. Our experiments demonstrate robust task execution under action failures and sensor noise, and provide empirical insights into the interleaved acting-and-planning decision making process.