Learning-accelerated A* Search for Risk-aware Path Planning

TL;DR

This work introduces an additional safety dimension to the traditional A* (called ASD A*), enabling A* to handle Constrained Shortest Path (CSP) problem, and develops a custom learning-based heuristic using transformer-based neural networks, which significantly reduces the computational load and improves the performance of the ASD A* algorithm.

Abstract

Safety is a critical concern for urban flights of autonomous Unmanned Aerial Vehicles. In populated environments, risk should be accounted for to produce an effective and safe path, known as risk-aware path planning. Risk-aware path planning can be modeled as a Constrained Shortest Path (CSP) problem, aiming to identify the shortest possible route that adheres to specified safety thresholds. CSP is NP-hard and poses significant computational challenges. Although many traditional methods can solve it accurately, all of them are very slow. Our method introduces an additional safety dimension to the traditional A* (called ASD A*), enabling A* to handle CSP. Furthermore, we develop a custom learning-based heuristic using transformer-based neural networks, which significantly reduces the computational load and improves the performance of the ASD A* algorithm. The proposed method is well-validated with both random and realistic simulation scenarios.

Figures (7)

• Figure 1: an 11*11 risk map example, where grayscale represents risk value.
• Figure 2: Example risk map
• Figure 3: Example path found in risk map
• Figure 4: Input layer
• Figure 5: Backbone and output layer