GundamQ: Multi-Scale Spatio-Temporal Representation Learning for Robust Robot Path Planning

2025-09-12

AI Summary

To address two key challenges in robot path planning under dynamic and uncertain environments—insufficient multi-scale temporal dependency modeling and poor exploration-exploitation trade-off—this paper proposes a dual-module framework integrating multi-granularity spatiotemporal awareness and adaptive policy optimization. The method employs hierarchical feature extraction and multi-scale temporal modeling to enhance prediction and reactive capability toward partially observable dynamic obstacles; it further introduces a constrained policy optimization mechanism to ensure smooth, low-collision policy updates. Within a deep reinforcement learning framework, the approach unifies spatiotemporal representation learning with decision robustness. Experimental results demonstrate that, compared to state-of-the-art methods, our approach achieves a 15.3% improvement in task success rate and a 21.7% enhancement in path quality, significantly boosting adaptability to dynamic scenarios and decision robustness.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In dynamic and uncertain environments, robotic path planning demands accurate spatiotemporal environment understanding combined with robust decision-making under partial observability. However, current deep reinforcement learning-based path planning methods face two fundamental limitations: (1) insufficient modeling of multi-scale temporal dependencies, resulting in suboptimal adaptability in dynamic scenarios, and (2) inefficient exploration-exploitation balance, leading to degraded path quality. To address these challenges, we propose GundamQ: A Multi-Scale Spatiotemporal Q-Network for Robotic Path Planning. The framework comprises two key modules: (i) the Spatiotemporal Perception module, which hierarchically extracts multi-granularity spatial features and multi-scale temporal dependencies ranging from instantaneous to extended time horizons, thereby improving perception accuracy in dynamic environments; and (ii) the Adaptive Policy Optimization module, which balances exploration and exploitation during training while optimizing for smoothness and collision probability through constrained policy updates. Experiments in dynamic environments demonstrate that GundamQ achieves a 15.3% improvement in success rate and a 21.7% increase in overall path quality, significantly outperforming existing state-of-the-art methods.

Problem

• Improving robot path planning in dynamic uncertain environments
• Addressing insufficient multi-scale temporal dependency modeling
• Solving inefficient exploration-exploitation balance in planning

Innovation

• Hierarchical multi-scale spatiotemporal feature extraction
• Adaptive exploration-exploitation policy optimization
• Constrained updates for smooth collision-free paths