UAV Path Planning for Object Observation with Quality Constraints: A Dynamic Programming Approach

TL;DR

This paper addresses a UAV path planning task that seeks to observe a set of objects while satisfying the observation quality constraint and proposes a dynamic programming algorithm that enables the UAV to observe the target objects with the shortest path while subjecting to the observation quality constraint.

Abstract

This paper addresses a UAV path planning task that seeks to observe a set of objects while satisfying the observation quality constraint. A dynamic programming algorithm is proposed that enables the UAV to observe the target objects with the shortest path while subjecting to the observation quality constraint. The objects have their own facing direction and restricted observation range. With an observing order, the algorithm achieves $(1+ε)$-approximation ratio in theory and runs in polynomial time. The extensive results demonstrate that the algorithm produces near-optimal solutions, the effectiveness of which is also tested and proved in the Airsim simulator, a realistic virtual environment.

Figures (13)

• Figure 1: Efficient observation. The UAV cannot observe an object from beyond $d_{max}$, or closer than $d_{min}$, or deviated over an angle $\theta$.
• Figure 2: Discretization result. The observation quality within each segment is considered equal. $\theta$ is the observing angle range around $o_i$.
• Figure 3: Construction of the path from $o_j$ to $o_i$ with the quality $q$. Since the UAV can observe $o_{j+1}$ to $o_{i}$ at $p_i$, it can directly go from $p_j$ to $p_i$, as the green dashed line shows.
• Figure 4: Photos taken by UAV of observed objects and the corresponding recognition results. For each subplot, the recognized string is presented before showing the number of correct letters and the label length.
• Figure 5: Virtual city environment in the simulator

Theorems & Definitions (10)

• Definition 1: Efficient observation
• Lemma 1
• Proof 1
• Definition 2
• Definition 3
• Definition 4
• Lemma 2
• Proof 2
• Theorem 1
• Proof 3: Proof of Theorem 1