麻省理工学院研究人员开发的一种新芯片可以帮助微型,低功率无人机避开障碍物，因为它们在工业暖通空调系统内的狭窄角落里快速移动以检查气体泄漏。
A new chip developed by MIT researchers could help tiny, low-power UAVs avoid obstacles as they zip around tight corners inside an industrial HVAC system to check for gas leaks.
该芯片允许小型自主机器人和其他电池有限的设备仅使用与单个 LED 差不多的电量来实时构建其环境的详细 3D 地图。机器人可以使用这样的地图来规划一条无碰撞路径来到达目标。
The chip allows small autonomous robots and other battery-limited devices to construct detailed 3D maps of their environments in real-time using only about as much power as a single LED. A robot could use such a map to plan a collision-free path to reach its goal.
通常, 生成如此详尽的地图需要耗电的系统和大量内存来构建和存储机器人的 环境中障碍物的3D 表示。
Typically, generating such thorough maps requires power-hungry systems and a great deal of memory to build and store 3D representations of the obstacles in a robot的 environment.
麻省理工学院的研究人员采取了不同的方法，将极其高效的映射算法与专门设计的硬件相结合，旨在加速其工作负载,，从而最大限度地减少内存和功耗。
The MIT researchers took a different approach by combining an extremely efficient mapping algorithm with specialized hardware designed to accelerate its workload, which minimizes memory and power consumption.
该片上系统仅消耗约 6 毫瓦的功率,，只是其他系统所需功率的一小部分。
This system-on-a-chip consumes only about 6 milliwatts of power, a fraction of the power required by other systems.
这种低功耗操作还可以使该芯片非常适合轻型增强现实耳机，可以长时间佩戴,，适用于教育医学模拟或详细维修和组装工作等应用。
This low-power operation could also make the chip well-suited for lightweight augmented reality headsets that can be worn for extended periods, for applications like educational medical simulation or detailed repair and assembly work.
与她共同撰写该论文的还有麻省理工学院研究生 Zih-Sing Fu 和 Peterzhi Xu Li，以及航空航天教授兼 LIDS 主任 Sertac Karaman,。这项工作最近在 IEEE 超大规模集成电路研讨会上进行了展示。
She is joined on the paper by co-lead authors and MIT graduate students Zih-Sing Fu and Peter Zhi Xuan Li as well as Sertac Karaman, a professor of aeronautics and astronautics and the director of LIDS. The work was recently presented at the IEEE Very Large-Scale Integrated Circuits Symposium.
对于机器人,来说，生成包含其环境中的障碍物的3D地图通常需要大量电力，因为它必须存储其相机,捕获的图像并多次处理每个图像中的所有3D像素。
For a robot, generating a 3D map that includes the obstacles in its environment usually demands a lot of power because it must store images captured by its camera, and process all the 3D pixels in each image multiple times.
麻省理工学院的研究人员没有使用 3D 像素,（称为体素, 的立方体）来表示环境，而是使用了一种使用称为高斯的椭球体斑点来映射空间中障碍物的技术。
Instead of representing the environment using 3D pixels, which are cubes called voxels, the MIT researchers utilized a technique that maps the obstacles in space using ellipsoid blobs called Gaussians.
这些椭球体的尺寸,、形状, 和厚度可以平滑地调整,，因此它们比使用刚性, 立方体形状的体素更有效地匹配弯曲物体的形状。
The size, shape, and thickness of these ellipsoids can be smoothly adapted, so they match the shape of curved objects more efficiently than if one uses rigid, cube-shaped voxels.
重要的是, 地图捕获了机器人, 周围的障碍物和自由空间，这些让机器人能够规划一条安全的, 无碰撞路径。使用体素映射障碍物和自由空间通常会消耗大量内存,，这使得传统方法非常耗电。由于高斯可以灵活地拟合几何形状,，因此单个细长椭球体可以表示需要许多体素, 的区域，因此可以更紧凑地捕获占用的表面和自由空间。
Importantly, the map captures the obstacles and free space around the robot, and together these let the robot plan a safe, collision-free path. Mapping obstacles and free space with voxels typically consumes a lot of memory, which makes traditional methods power-hungry. Because Gaussians can flexibly fit the geometry, a single elongated ellipsoid can represent a region that would take many voxels, so occupied surfaces and free space are captured far more compactly.
对于名为 Gleanmer, 的新片上系统,，研究人员采用了他们实验室开发的一种名为 GMMap 的算法，该算法使用高斯函数表示障碍物，有效生成机器人的 环境的 3D 地图。
For their new system-on-a-chip, called Gleanmer, the researchers employed an algorithm their lab developed called GMMap that efficiently generates a 3D map of the robot的 environment using Gaussians to represent obstacles.
使用传统方法,，机器人需要多次加载和处理每个深度图像，以调整椭球体的大小和形状。系统通常会通过比较图像中的所有像素来构建高斯分布。但对于许多边缘设备来说，执行此操作所需的内存量和功耗仍然过高。
With traditional approaches, a robot would need to load and process each depth image several times to adjust the size and shape of the ellipsoids. The system would usually construct Gaussians by comparing all the pixels in an image to each other. But the amount of memory and power needed to do this remains too high for many edge devices.
为了解决这个问题,，麻省理工学院的研究人员发明了一种技术，只需一次通过即可从深度图像生成高精度高斯,，之后他们可以丢弃图像,，因此芯片永远不必立即存储整个图像。
To solve this problem, the MIT researchers invented a technique that can generate highly accurate Gaussians from depth images with only one pass, after which they can discard the images, so the chip never has to store an entire image at once.
他们的算法没有将每个像素与 3D 图像, 中的每个其他像素进行比较，而是假设附近的像素属于相同的高斯,，因此只需将每个像素与其邻居进行比较。
Instead of comparing each pixel to every other pixel in the 3D image, their algorithm assumes that nearby pixels belong in the same Gaussian, so it only needs to compare each pixel to its neighbors.
“在任何时间点,，我们只需要在内存中存储几个像素,，这显着减少了我们的算法所需的内存占用,” Li 说。
“At any point in time, we only need to store a few pixels in memory, which significantly reduces the memory footprint our algorithm requires,” Li says.
但当机器人在空间, 中移动时，它通常会从不同的角度看到同一个物体。当它生成 Gaussians, 时，有些会重叠，因为它们代表相同的对象。这可能会使 3D 地图太大而无法存储在边缘设备上。
But as the robot moves through the space, it usually sees the same object from different viewpoints. When it generates Gaussians, some will overlap because they represent the same object. This can make the 3D map too large to store on an edge device.
融合重叠高斯使地图更加紧凑,，但这样做通常需要算法处理存储在内存中的许多原始像素。研究人员开发了一种新技术，可以直接在重叠的高斯,上执行这种融合过程，而无需重新访问原始像素。由于高斯比像素, 更紧凑，这显着降低了内存和功耗要求。
Fusing overlapping Gaussians makes the map more compact, but doing so typically requires the algorithm to process many raw pixels stored in memory. The researchers developed a novel technique to perform this fusion process directly on overlapping Gaussians, without needing to revisit the original pixels. Since Gaussians are more compact than pixels, this significantly reduces memory and power requirements.
同样的原理贯穿于他们的算法 — 大多数计算直接在紧凑高斯上运行，而不是在原始像素, 上运行，从而实现能源效率。
The same principle runs through their algorithm — most computations operate directly on compact Gaussians rather than the original pixels, enabling energy efficiency.
研究人员利用这一原理设计了一款芯片，将其正在处理的高斯函数保留在计算单元旁边的小型 2C 快速片上存储器中。这是可能的，因为高斯映射是如此紧凑。
The researchers exploit this principle to design a chip that keeps the Gaussians it is actively working on within small, fast on-chip memory right beside the computational units. This is only possible because the Gaussian map is so compact.
机器人接下来需要处理的高斯函数正在片上存储单元,中等待，因此不需要从更远的,耗电,片外存储中获取’t。
The Gaussians the robot needs to work on next are waiting in the on-chip memory units, so they don’t need to be fetched from more distant, power-hungry, off-chip storage.
“通过拥有一个专用内存来存储您’在前几帧中看到的对象,，您可以更有效地访问数据,” Fu 解释道。
“By having a dedicated memory that just stores the objects you’ve seen in the previous few frames, you can access the data much more efficiently,” Fu explains.
他们通过重建一系列不同的, 预先存在的 3D 环境来测试片上系统。该芯片还可以直接根据 iPhone 摄像头传输的实时数据重建障碍物和自由空间。
They tested the system-on-a-chip by reconstructing a range of diverse, pre-existing 3D environments. The chip can also reconstruct obstacles and free space directly from live data streamed from an iPhone camera.
Gleanmer 实时生成详细的 3D 地图，同时消耗约 6 毫瓦的电量。它只需要大约 2.5% 的功率，现有最好的地图构建芯片所需的功率。
Gleanmer generated detailed 3D maps in real-time while consuming about 6 milliwatts of power. It required only about 2.5 percent of the power that the best existing chip for map construction would need.
通过在规划的路径上重复使用紧凑的高斯,，芯片可以让机器人仅使用大约 20% 的能量来绘制安全轨迹。
By reusing compact Gaussians along the path as it plans, the chip lets a robot chart a safe trajectory using only about 20 percent of the energy it would otherwise need.
“我们通过确保算法高效来减少内存消耗。然后，我们加速该高效算法, 执行的工作负载，因此最终, 我们的芯片尽可能高效,” Li 说。
“We reduce the memory consumption by making sure the algorithm is efficient. Then we accelerate the workload that is performed by that efficient algorithm, so in the end, our chip is as efficient as possible,” Li says.
研究人员计划通过将芯片上的处理单元移近收集环境数据的传感器来进一步提高能源效率。他们还可以探索其他应用,，例如使用高斯来表示原理图。这可以帮助人工智能系统更有效地推理复杂的蓝图。
The researchers plan to further improve energy efficiency by moving the processing units on the chip closer to the sensors that gather environmental data. They could also explore additional applications, such as the use of Gaussians to represent schematics. This could help AI systems reason about complex blueprints more efficiently.
“实时 3D 测绘一直是小型自治系统所缺失的部分。检查管道的无人机或在房间中导航的 AR 眼镜都需要立即了解周围的空间—, 连续, 并且几乎没有电力成本。卡拉曼说，Gleanermer 首次在手指可以握住的芯片中实现了这一点,”。
“Real-time 3D mapping has been the missing piece for small autonomous systems. A drone inspecting a pipeline or a pair of AR glasses navigating a room both need to understand the space around them — instantly, continuously, and at almost no power cost. Gleanmer makes that possible for the first time in a chip you can hold between your fingers,” says Karaman.
这项工作的, 部分由 MIT-MathWorks Fellowship,、Amazon,、美国国家科学基金会, 和英特尔支持。
This work is supported, in part, by the MIT-MathWorks Fellowship, Amazon, the U.S. National Science Foundation, and Intel.