ONRAP: Occupancy-driven Noise-Resilient Autonomous Path Planning

2026-02-14

AI Summary

This work addresses the challenge of reliable dynamic path planning under perceptual noise, localization uncertainty, and incomplete semantic information. We propose a nonlinear spatial-domain optimization framework based on occupancy grids that dispenses with handcrafted heuristics and uniformly handles unknown obstacles and heterogeneous dynamic agents within pure occupancy space. By integrating optional occupancy flow prediction, an enhanced bicycle kinematic model, and an explicit collision penalty mechanism, our approach generates ego-centric trajectories that satisfy kinematic constraints while ensuring safety. The method achieves real-time performance at over 10 Hz in both high-noise simulations and real-world F1TENTH vehicle experiments, robustly navigating narrow passages and complex scenarios without fine-tuned parameters, thereby significantly improving planning robustness and generalization capability.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Motion and Path Planning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Dynamic path planning must remain reliable in the presence of sensing noise, uncertain localization, and incomplete semantic perception. We propose a practical, implementation-friendly planner that operates on occupancy grids and optionally incorporates occupancy-flow predictions to generate ego-centric, kinematically feasible paths that safely navigate through static and dynamic obstacles. The core is a nonlinear program in the spatial domain built on a modified bicycle model with explicit feasibility and collision-avoidance penalties. The formulation naturally handles unknown obstacle classes and heterogeneous agent motion by operating purely in occupancy space. The pipeline runs in real-time (faster than 10 Hz on average), requires minimal tuning, and interfaces cleanly with standard control stacks. We validate our approach in simulation with severe localization and perception noises, and on an F1TENTH platform, demonstrating smooth and safe maneuvering through narrow passages and rough routes. The approach provides a robust foundation for noise-resilient, prediction-aware planning, eliminating the need for handcrafted heuristics. The project website can be accessed at https://honda-research-institute.github.io/onrap/

Problem

• noise-resilient planning
• dynamic path planning
• occupancy grid
• perception uncertainty
• localization noise

Innovation

• occupancy-driven planning
• noise-resilient autonomy
• nonlinear trajectory optimization
• occupancy-flow prediction
• real-time path planning