POrTAL: Plan-Orchestrated Tree Assembly for Lookahead

2025-12-01

AI Summary

To address the low efficiency and excessive step counts in robotic task planning under partial observability, this paper proposes POMFF, a lightweight probabilistic planning algorithm that integrates FF-Replan’s heuristic forward search capability with POMCP’s uncertainty modeling strength. Methodologically, it constructs a dynamic incremental decision tree, enabling online tree assembly and localized re-planning to ensure long-horizon robustness while substantially reducing computational overhead. Its key contribution lies in the first synergistic integration of a classical deterministic planning framework with Monte Carlo tree search within the POMDP setting, yielding efficient, adaptive real-time decision-making. Experiments across diverse partially observable tasks demonstrate that POMFF reduces average execution steps by 32% and maintains over 95% success rates under stringent time constraints—outperforming existing baseline methods in real-time performance.

Technology Category

• Planning, Routing, and Scheduling: Planning with Markov Models (MDPs, POMDPs)
• Intelligent Robots: Motion and Path Planning
• Multiagent Systems: Multiagent Planning

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods

Abstract

Assigning tasks to robots often involves supplying the robot with an overarching goal, such as through natural language, and then relying on the robot to uncover and execute a plan to achieve that goal. In many settings common to human-robot interaction, however, the world is only partially observable to the robot, requiring that it create plans under uncertainty. Although many probabilistic planning algorithms exist for this purpose, these algorithms can be inefficient if executed with the robot's limited computational resources, or may require more steps than expected to achieve the goal. We thereby created a new, lightweight, probabilistic planning algorithm, Plan-Orchestrated Tree Assembly for Lookahead (POrTAL), that combines the strengths of two baseline planning algorithms, FF-Replan and POMCP. In a series of case studies, we demonstrate POrTAL's ability to quickly arrive at solutions that outperform these baselines in terms of number of steps. We additionally demonstrate how POrTAL performs under varying temporal constraints.

Problem

• Develops a lightweight probabilistic planning algorithm for robots
• Combines strengths of FF-Replan and POMCP to handle uncertainty
• Aims to reduce steps and improve efficiency under constraints

Innovation

• Lightweight probabilistic planning algorithm
• Combines FF-Replan and POMCP strengths
• Quickly achieves fewer-step solutions