泡泡一分鐘:Perception-aware Receding Horizon Navigation for MAVs

做爲在空中拋擲四旋翼飛行器後恢復的第一步，它須要檢測它使用其加速度計的發射。理想的狀況下，在飛行中，加速度計理想地僅測量因爲施加的轉子推力引發的加速度，即。所以，當四旋翼飛行器發射時，咱們能夠檢測到測量的加速度降低到與當前施加的推力相對應的值。

B. Recovery and Initialization Steps

張寧    Perception-aware Receding Horizon Navigation for MAVs
    "連接：https://pan.baidu.com/s/1uBMIFMFudZ6FXs4lSnUOLw
提取碼：7br1"

To reach a given destination safely and accurately,a micro aerial vehicle needs to be able to avoid obstaclesand minimize its state estimation uncertainty at the sametime. To achieve this goal, we propose a perception-awarereceding horizon approach. In our method, a single forward-looking camera is used for state estimation and mapping.Using the information from the monocular state estimation andmapping system, we generate a library of candidate trajectoriesand evaluate them in terms of perception quality, collisionprobability, and distance to the goal. The best trajectory toexecute is then selected as the one that maximizes a reward function based on these three metrics. To the best of our knowledge, this is the first work that integrates active vision within a receding horizon navigation framework for a goal reaching task. We demonstrate by simulation and real-world experiments on an actual quadrotor that our active approach leads to improved state estimation accuracy in a goal-reaching task when compared to a purely-reactive navigation system,especially in difficult scenes (e.g., weak texture).

爲了安全準確地到達給定目的地，微型飛行器須要可以避開障礙物並同時最小化其狀態估計不肯定性。爲了實現這一目標，咱們提出了一種感知感知的後退視界方法。 在咱們的方法中，單個前視攝像機用於狀態估計和映射。使用來自單眼狀態估計和映射系統的信息，咱們生成候選軌跡庫並根據感知質量，碰撞機率和到目標的距離來評估它們。而後選擇最佳執行軌跡做爲基於這三個度量最大化獎勵函數的軌跡。 就咱們所知，這是第一項將主動視覺與後退地平線導航框架相結合以實現目標任務的工做。咱們經過仿真和現實世界實驗證實，與純反應式導航系統相比，咱們的主動方法能夠在達到目標的任務中提升狀態估計精度，尤爲是在困難場景（例如，弱紋理）中。