TinyOdom:硬件意识高效的神经惯性导航
Swapnil Sayan Saha1, Sandeep Singh Sandha1, Luis Antonio Garcia2
1University of California - Los Angeles, USA.
Proceedings of the ACM on interactive, mobile, wearable and ubiquitous technologies
|March 22, 2024
概括
在资源有限的设备上,TinyOdom 可实现实时的神经惯性测距. 该框架显著减少了模型大小,并提高了各种应用程序的本地化准确性,克服了当前深度学习方法的局限性.
科学领域:
- 机器人技术和自主系统
- 机器学习用于导航.
- 嵌入式系统工程 嵌入式系统工程
背景情况:
- 深度惯性测距在GPS被拒绝的地区提供高分辨率的轨迹估计.
- 现有的神经惯性死亡计算系统对于超资源受限 (URC) 设备来说过于资源密集.
- 目前的方法面临诸如重力污染,传感器干扰和高度估计失败等挑战.
研究的目的:
- 开发TinyOdom,一个用于训练和部署轻量级神经惯性模型在URC硬件上的框架.
- 为了提高对环境和传感器干扰的稳定性,以实现准确的死亡计算.
- 为了在具有有限内存,功率和计算能力的设备上实现实时,高性能惯性测距.
主要方法:
- 利用了硬件意识和量子化意识的贝叶斯神经架构搜索 (NAS) 与时间卷积网络 (TCN) 骨架.
- 介绍了一种新的磁力计,物理和以速度为中心的序列学习公式.
- 扩展了2D到3D学习,配有无模型的气压测量g-h过器,可进行可靠的高度估计.
主要成果:
- 在各种应用 (行人,动物,空中,水下) 中,TinyOdom实现了31×至134×的模型尺寸缩小.
- 在60秒内以2.5m至12m的误差证明了定位准确性,超过了最先进的方法.
- 气压过器保持高度跟踪在±0.1m以内,对干扰具有坚固的耐用性.
结论:
- TinyOdom 便于在 URC 设备上直接部署先进的神经惯性测距仪.
- 拟议的序列学习和气压过技术显著提高了本地化性能和稳定性.
- 这项工作弥合了高性能惯性测距和嵌入式系统的限制之间的差距.
相关概念视频
01:03Inertial Frames of Reference
7.1K
Newton’s first law is usually considered to be a statement about reference frames. It provides a method for identifying a special type of reference frame: the inertial reference frame. In principle, we can make the net force on a body zero. If its velocity relative to a given frame is constant, then that frame is said to be inertial. So, by definition, an inertial reference frame is a reference frame where Newton's first law holds valid. Newton's first law applies to objects with...
7.1K
01:27Non-inertial Frames of Reference
5.9K
A reference frame accelerating or decelerating relative to an inertial frame is a non-inertial frame. To help understand this, consider what taking off in an airplane, turning a corner in a car, riding a merry-go-round, and the circular motion of a tropical cyclone all have in common. All these systems are accelerating, decelerating, or rotating relative to the Earth; hence, they all are non-inertial frames. All these systems exhibit inertial forces, which merely seem to arise from motion,...
5.9K
01:24One-Degree-of-Freedom System
488
In mechanical engineering, one-degree-of-freedom systems form the basis of a wide range of electrical and mechanical components. Using these models, engineers can predict the behavior of various parts in a larger system, which gives them insight into how different forces interact with each other.
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
A one-degree-of-freedom system is defined by an independent variable that determines its state and behavior. One example of a one-degree-of-freedom system is a simple harmonic oscillator, such as a...
488
01:02Gyroscope
3.0K
A gyroscope is defined as a spinning disk in which the axis of rotation is free to assume any orientation. When spinning, the orientation of the spin axis is unaffected by the orientation of the body that encloses it. The body or vehicle enclosing the gyroscope can be moved from place to place, while the orientation of the spin axis remains the same. This makes gyroscopes very useful in navigation, especially where magnetic compasses cannot be used, such as in crewed and crewless spacecraft,...
3.0K
01:24Gyroscope: Precession
4.1K
Precession can be demonstrated effectively through a spinning top. If a spinning top is placed on a flat surface near the surface of the Earth at a vertical angle and is not spinning, it will fall over due to the force of gravity producing a torque acting on its center of mass. However, if the top is spinning on its axis, it precesses about the vertical direction, rather than topple over due to this torque. Precessional motion is a combination of a steady circular motion of the axis and the...
4.1K