A Genetic Approach to Gradient-Free Kinodynamic Planning in Uneven Terrains

2025-04-17

IEEE Robotics and Automation Letters

AI Summary

This paper addresses the challenge of path planning for car-like robots navigating uneven, triangulated-mesh terrains. We propose GAKD—a gradient-free, dynamics-feasible model predictive trajectory optimization method. GAKD employs a genetic algorithm enhanced with a novel heuristic mutation operator explicitly designed to adapt to dynamic terrain normal variations, enabling efficient generation of kinematically and dynamically feasible trajectories without requiring gradient information. Crucially, all control inputs are rigorously confined within physically admissible bounds. Compared to MPPI and log-MPPI, GAKD achieves comparable path lengths while reducing traversability cost by 20%, thereby significantly improving navigation robustness and real-time adaptability in complex, unstructured terrains.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

Abstract

This paper proposes a genetic algorithm-based kinodynamic planning algorithm (GAKD) for car-like vehicles navigating uneven terrains modeled as triangular meshes. The algorithm's distinct feature is trajectory optimization over a fixed-length receding horizon using a genetic algorithm with heuristic-based mutation, ensuring the vehicle's controls remain within its valid operational range. By addressing challenges posed by uneven terrain meshes, such as changing face normals, GAKD offers a practical solution for path planning in complex environments. Comparative evaluations against Model Predictive Path Integral (MPPI) and log-MPPI methods show that GAKD achieves up to 20 percent improvement in traversability cost while maintaining comparable path length. These results demonstrate GAKD's potential in improving vehicle navigation on challenging terrains.

Problem

• Develops gradient-free kinodynamic planning for uneven terrains
• Optimizes vehicle trajectories using genetic algorithms
• Improves traversability cost by 20% over existing methods

Innovation

• Genetic algorithm for gradient-free kinodynamic planning
• Heuristic-based mutation for trajectory optimization
• Fixed-length receding horizon control approach