OpticalNeuromorphicEikonal_medium_256: 2D Pathfinding Grid with Obstacles and Speed Field

OpticalNeuromorphicEikonal_medium_256 is a 256x256 grid pathfinding benchmark dataset containing 65,536 cells. It was created by Francisco Angulo de Lafuente to evaluate GPU-accelerated navigation algorithms. The dataset simulates a 2D environment with a 20% obstacle density and uniform speed field.

Use Cases

• Benchmarking pathfinding algorithm speed and accuracy based on the described grid structure and obstacle density.
• Evaluating algorithm performance on variable-cost terrains based on the uniform speed field.
• Comparing traditional CPU methods (like Dijkstra) against GPU-accelerated or neuromorphic solvers based on the reported 135x average speedup.
• Testing real-time navigation systems based on the sub-4ms query performance mentioned for similar grids.

Strengths

• Grid dimensions and obstacle density are explicitly defined as 256x256 and 20%.
• Performance benchmarks for the associated solver are provided, including a 135x average speedup and 0.64% mean absolute error.
• The dataset is designed for a specific, reproducible benchmark with a stated random seed of 3.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Francisco Angulo de Lafuente

Collection Method

Simulated 2D grid for algorithm benchmarking.

Time Range

null

Freshness

null

Geography

null