Genetic Informed Trees (GIT*): Path Planning via Reinforced Genetic Programming Heuristics

2025-08-28

AI Summary

Existing optimal path planning methods suffer from suboptimal heuristic design—limited by insufficient exploitation of environmental information (e.g., obstacle repulsion, node dynamism) and structural simplifications—leading to degraded search efficiency and solution quality. To address this, we propose GIT*, a novel framework that synergistically integrates Reinforcement-guided Genetic Programming (RGP) with Effort-Informed Trees (EIT*), enabling adaptive evolutionary optimization of heuristic function structure. RGP takes multi-source environmental data as input to dynamically synthesize and refine genotype-encoded heuristics; EIT* leverages these learned heuristics to guide efficient sampling in high-dimensional configuration spaces (ℝ⁴–ℝ¹⁶). Extensive experiments demonstrate that GIT* significantly outperforms state-of-the-art sampling-based planners under single-query settings. Furthermore, real-world mobile manipulation tasks validate its dual improvements in computational efficiency and path optimality.

Technology Category

• Search and Optimization: Heuristic Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: Motion and Path Planning

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

Abstract

Optimal path planning involves finding a feasible state sequence between a start and a goal that optimizes an objective. This process relies on heuristic functions to guide the search direction. While a robust function can improve search efficiency and solution quality, current methods often overlook available environmental data and simplify the function structure due to the complexity of information relationships. This study introduces Genetic Informed Trees (GIT*), which improves upon Effort Informed Trees (EIT*) by integrating a wider array of environmental data, such as repulsive forces from obstacles and the dynamic importance of vertices, to refine heuristic functions for better guidance. Furthermore, we integrated reinforced genetic programming (RGP), which combines genetic programming with reward system feedback to mutate genotype-generative heuristic functions for GIT*. RGP leverages a multitude of data types, thereby improving computational efficiency and solution quality within a set timeframe. Comparative analyses demonstrate that GIT* surpasses existing single-query, sampling-based planners in problems ranging from R^4 to R^16 and was tested on a real-world mobile manipulation task. A video showcasing our experimental results is available at https://youtu.be/URjXbc_BiYg

Problem

• Improving heuristic functions for optimal path planning
• Integrating diverse environmental data to enhance search efficiency
• Using reinforced genetic programming to refine heuristic guidance

Innovation

• Genetic Informed Trees integrating environmental data
• Reinforced genetic programming mutating heuristic functions
• Improved path planning efficiency and quality