Semantic Risk-Aware Heuristic Planning for Robotic Navigation in Dynamic Environments: An LLM-Inspired Approach
2026-05-04 • Robotics
Robotics
AI summaryⓘ
The authors created a new robot navigation method called Semantic Risk-Aware Heuristic (SRAH) that helps robots avoid risky or cluttered areas by using ideas inspired by large language models. They tested SRAH on a grid with both fixed and moving obstacles and found it was better at successfully completing tasks than two other common methods. Their approach also balances planning speed with safety and adjusts well to different levels of obstacle difficulty. Overall, the authors show that simple heuristics inspired by language models can make robot navigation safer and more reliable.
Large Language ModelsRobot Path PlanningA* SearchHeuristicDynamic ObstaclesBreadth-First SearchReplanningSemantic CostNavigation Safety
Authors
Hamza Ahmed Durrani, Rafay Suleman Durrani
Abstract
The integration of Large Language Model (LLM) reasoning principles into classical robot path planning represents a rapidly emerging research direction. In this paper, we propose a Semantic Risk-Aware Heuristic (SRAH) planner that encodes LLM-inspired cost functions penalising geometrically cluttered or high-risk zones into an A$^*$ search framework, augmented with closed-loop replanning upon dynamic obstacle detection. We evaluate SRAH against two established baselines Breadth-First Search (BFS) with replanning and a Greedy heuristic without replanning across 200 randomised trials in a $15{\times}15$ grid-world with 20\% static obstacle density and stochastic dynamic obstacles. SRAH achieves a task success rate of 62.0\%, outperforming BFS (56.5\%) by 9.7\% relative improvement and Greedy (4.0\%) by a large margin. We further analyse the trade-off between planning overhead, path efficiency, and failure-recovery count, and demonstrate via an obstacle-density ablation that semantic cost shaping consistently improves navigation across environments of varying difficulty. Our results suggest that even lightweight, LLM-inspired heuristics provide measurable safety and robustness gains for autonomous robot navigation.