New Algorithm Flies Drones Faster than Human Racing Pilots

利用新算法飞行无人机比竞速飞行员速度更快

For the first time an autonomously flying quadrotor has outperformed two human pilots in a drone race. The success is based on a novel algorithm that was developed by researchers of the University of Zurich. It calculates time-optimal trajectories that fully consider the drones’ limitations.

自主飞行四旋翼无人机首次在无人机竞速比赛中超过两名人类飞行员。此次成功是基于一个由苏黎世大学研究员开发的新型算法。它能够充分考虑无人机的缺点从而找出所需时间最短的航道。

To be useful, drones need to be quick. Because of their limited battery life they must complete whatever task they have – searching for survivors on a disaster site, inspecting a building, delivering cargo – in the shortest possible time. And they may have to do it by going through a series of waypoints like windows, rooms, or specific locations to inspect, adopting the best trajectory and the right acceleration or deceleration at each segment.

无人机只有速度够快，才能起到用处。 因为无人机的电池寿命十分有限，它们必须在最短时间内完成一切任务，如在灾区寻找幸存者，监测大楼，运输货物等。并且他们在执行这些任务的时候可能需要通过一系列的航点，如窗户、房间、或要监视的特定区域，在每个节点采用最优航道以及恰当地加速或减速。

Previous works relied on simplifications of either the quadrotor system or the description of the flight path, and thus they were sub-optimal. “The key idea is, rather than assigning sections of the flight path to specific waypoints, that our algorithm just tells the drone to pass through all waypoints, but not how or when to do that”, adds Philipp Foehn, PhD student and first author of the paper.

该论文作者菲利普说道，“过往的研究都把重点放在简化四旋翼系统或航道的阐述，因此他们并非找出最优的方法。关键点并不在于为特定航点分配航道，我们的算法是让无人机穿过所有的航点，而不是如何或何时通过。”

The researchers had the algorithm and two human pilots fly the same quadrotor through a race circuit. They employed external cameras to precisely capture the motion of the drones and – in the case of the autonomous drone – to give real-time information to the algorithm on where the drone was at any moment. To ensure a fair comparison, the human pilots were given the opportunity to train on the circuit before the race. But the algorithm won: all its laps were faster than the human ones, and the performance was more consistent. This is not surprising, because once the algorithm has found the best trajectory it can reproduce it faithfully many times, unlike human pilots.

研究者用算法和两名人类飞行员在一航道上操作同一架四旋翼无人机。他们采用外置相机准确捕捉无人机的动态轨迹，而自主无人机则是将实时信息传输给算法，就能知晓无人机每一时刻所处的位置。 为了保证公平的对比，人类飞行员在竞速前可以在航道上进行练习。但是最终还是算法操作的获胜了：每一圈都比人类飞行员快，且表现得更连贯。这一结果并非出乎意料，因为一旦算法找到了最佳航道，它便可以节省很多时间。

In future work, the scientists want to use onboard cameras. But the demonstration that an autonomous drone can in principle fly faster than human pilots is promising. “This algorithm can have huge applications in package delivery with drones, inspection, search and rescue, and more”, says Scaramuzza.

未来，科学家想要采用车载相机。但是自主驾驶的无人机原则上是比人类飞行员飞得更快。这一算法在无人机送货、监测、搜寻和营救等方面都有巨大的用处。

Operating a Drone Across the Ocean, with only a Standard Cellphone Connection: Skypersonic Demonstrates it Can Be Done

Skypersonic向我们证明了如何仅靠一部普通的手机便可实现隔海操控无人机

Industrial drone company and Red Cat Holdings subsidiary Skypersonic conducted a visual inspection of the interior of a fully operational utility plant in Turin, Italy, via a drone controlled from 4,800 miles away in Orlando, Florida. The operation was conducted using only the internet connection from a standard cell phone.

工业无人机公司及Red Cat Holdings子公司Skypersonic在 4,800 英里外的佛罗里达州奥兰多，通过一架无人机对意大利都灵一家全面运营的公用事业工厂的内部进行监查。

Drew Camden, the Orlando-based pilot and president of Red Cat subsidiary Rotor Riot, possessed no prior knowledge of the Iren district heating-network plant in Turin. Camden piloted the Skypersonic “Skycopter” drone using only the drone’s video feed, which enabled him to see and react to the building’s interior in near-real time, with a latency of only 68 milliseconds. The Skycopter can be piloted without GPS, which is unavailable indoors and in enclosed spaces.

Red Cat子公司Rotor Riot总裁及奥兰多飞行员Drew Camden，对于都灵伊伦地区供热网工厂毫无了解。 Camdenc操控无人机，仅使用无人机的视频监视功能便能看到建筑内部接近实时的画面，仅延时68毫秒。Skycopter无需GPS导航也可以正常航行，特别是GPS在室内和密闭区域信号特别差。

Using drones flown by on-site pilots to inspect industrial facilities brings significant savings in time and money over the traditional method of erecting scaffolding and hoisting personnel in the air – as well as being immeasurably safer.

现场飞行员操控无人机监视工业设施比起搭建脚架和吊装人员的传统方法，更节省时间和金钱也相对来说安全得多。

Travel expenses are eliminated completely and, because no travel is involved, the pilot’s time commitment drops from days to hours, which also means that a pilot can conduct several inspections on the same day with drones operating thousands of miles away while remaining in the same place.

无需旅行开支，飞行员的时间投入也从以天为单位降到以时为单位，这也意味着一个飞行员能在一个地点，目的地万里之外操控无人机同时进行几项监测。