完全神经形态的视觉和控制自主无人机飞行.
F Paredes-Vallés1, J J Hagenaars1, J Dupeyroux1
1Micro Air Vehicle Laboratory, Faculty of Aerospace Engineering, Delft University of Technology, Delft, Netherlands.
Science robotics
|May 15, 2024
概括
研究人员为无人机开发了一种神经形象视觉控制系统,使用基于事件的摄像头和尖端神经网络实现了自主飞行. 这种低功耗系统展示了高效的机器人感知和行动,用于复杂的机动作.
科学领域:
- 机器人技术 机器人技术 机器人技术
- 神经形态工程的神经形态工程
- 人工智能的人工智能
背景情况:
- 生物系统通过异步,稀疏的处理实现了低延迟,高能效的感知和行动.
- 神经形态硬件和尖端神经网络 (SNN) 旨在在机器人学中复制这些特征.
- 目前SNN的机器人应用受到处理器限制和训练复杂性的限制.
研究的目的:
- 为自主无人机飞行提供一个完全神经形态的视觉控制管道.
- 证明SNN能够处理基于事件的原始摄像头数据以实时控制.
- 为了实现机载机器人系统的高效,低功耗运行.
主要方法:
- 用自主监督学习训练一个拥有28800个神经元的五层SNN,将事件数据映射到自我运动估计.
- 在无人机模拟器中使用进化算法训练了用于控制操作的单个解码层.
- 该管道在英特尔的Loihi神经形态处理器上进行了实施和测试,用于模拟到真实传输.
主要成果:
- 神经形态管道成功实现了基于视觉的自主飞行,包括悬浮,降落和复杂的机动,如同时侧向运动和打哈哈.
- 该系统在机器人实验中展示了精确的自我运动控制,验证了模拟到真实转移.
- 车载实施实现了高效率,运行在200Hz的最低功耗 (0.94W空,7-12mW额外的活跃时).
结论:
- 一个完全神经形态的,事件驱动的视觉控制系统可以在无人机中实现复杂的自主飞行.
- 这种方法为实现高能效和低延迟的机器人感知和控制提供了一条途径.
- 结果突出了神经形态处理在创造昆虫大小智能机器人的潜力.
相关概念视频
01:24One-Degree-of-Freedom System
487
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...
487
01:18Hierarchy of Motor Control
2.6K
The hierarchy of motor control refers to the different levels of organization and processing involved in controlling movement in the body. These levels range from higher cortical areas involved in planning and decision-making to lower spinal cord reflexes that respond automatically to external stimuli.
2.6K