MMP-A*: Multimodal Perception Enhanced Incremental Heuristic Search on Path Planning

TL;DR

MMP-A* is a multimodal path planning framework that combines vision-language models with an adaptive heuristic to produce efficient, accurate, and geometry-aware navigation in complex environments.

Contribution

It introduces a novel multimodal framework with an adaptive decay mechanism that improves path planning by grounding high-level reasoning in physical geometry.

Findings

Achieves near-optimal trajectories in cluttered environments

Reduces computational and memory costs significantly

Outperforms text-only guidance methods in complex scenarios

Abstract

Autonomous path planning requires a synergy between global reasoning and geometric precision, especially in complex or cluttered environments. While classical A* is valued for its optimality, it incurs prohibitive computational and memory costs in large-scale scenarios. Recent attempts to mitigate these limitations by using Large Language Models for waypoint guidance remain insufficient, as they rely only on text-based reasoning without spatial grounding. As a result, such models often produce incorrect waypoints in topologically complex environments with dead ends, and lack the perceptual capacity to interpret ambiguous physical boundaries. These inconsistencies lead to costly corrective expansions and undermine the intended computational efficiency. We introduce MMP-A*, a multimodal framework that integrates the spatial grounding capabilities of vision-language models with a novel adaptive decay mechanism. By anchoring high-level reasoning in physical geometry, the framework produces coherent waypoint guidance that addresses the limitations of text-only planners. The adaptive decay mechanism dynamically regulates the influence of uncertain waypoints within the heuristic, ensuring geometric validity while substantially reducing memory overhead. To evaluate robustness, we test the framework in challenging environments characterized by severe clutter and topological complexity. Experimental results show that MMP-A* achieves near-optimal trajectories with significantly reduced operational costs, demonstrating its potential as a perception-grounded and computationally efficient paradigm for autonomous navigation.