Deep Neuromorphic Controller with Dynamic Topology for Aerial Robots
Deep Neuromorphic Controller with Dynamic Topology for Aerial Robots
复制标题
DOI：
10.1109/icra48506.2021.9561729
复制
发表时间：
2021-05
期刊：
影响因子：
--
通讯作者：
Basaran Bahadir Kocer;Mohamad Abdul Hady;Harikumar Kandath;Mahardhika Pratama;M. Kovač
中科院分区：
文献类型：
--
作者：
Basaran Bahadir Kocer;Mohamad Abdul Hady;Harikumar Kandath;Mahardhika Pratama;M. Kovač
目前的空中机器人越来越具有适应性；它们可以变形以在不断变化的条件下操作，以完成不同的任务。每项任务可能需要机器人执行不同的任务。当系统针对典型环境中的类似任务进行训练时，传统的学习方法可以处理这些变化。然而，它可能会导致对新数据流的过度适应或无法适应，导致性能下降或潜在的崩溃。这些问题可以通过大量的数据和嵌入模型来缓解，但空中机器人的计算能力和内存有限。为了解决模型、环境的变化以及机载计算限制内的任务，我们提出了一种具有可变拓扑的深层神经形态控制器方法来处理每种不同的条件和具有可行的计算和存储分配的数据流。该方法基于深度神经网络(多层和可变层次神经网络)控制器，对每个新数据流进行动态深度和渐进层自适应。该自适应结构与切换函数相结合，构成滑模控制器。网络参数更新规则通过误差动态收敛到滑动面来保证闭环系统的稳定性。作为第一次在空中机器人上的实现，结果表明了该算法的自适应能力、稳定性、计算效率以及实时验证。
Current aerial robots are increasingly adaptive; they can morph to enable operation in changing conditions to complete diverse missions. Each mission may require the robot to conduct a different task. A conventional learning approach can handle these variations when the system is trained for similar tasks in a representative environment. However, it may result in overfitting to the new data stream or the failure to adapt, leading to degradation or a potential crash. These problems can be mitigated with an excessive amount of data and embedded model, but the computational power and the memory of the aerial robots are limited. In order to address the variations in the model, environment as well as the tasks within onboard computation limitations, we propose a deep neuromorphic controller approach with variable topologies to handle each different condition and the data stream with a feasible computation and memory allocation. The proposed approach is based on a deep neuromorphic (multi and variable layered neural network) controller with dynamic depth and progressive layer adaptation for each new data stream. This adaptive structure is combined with a switching function to form a sliding mode controller. The network parameter update rule guarantees the stability of the closed loop system by the convergence of the error dynamics to the sliding surface. Being the first implementation on an aerial robot in this context, the results illustrate the adaptation capability, stability, computational efficiency as well as the real-time validation.