Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userNeural Flocking: MPC-based Supervised Learning of Flocking Controllers
76
0
0.0
(
0
)
Added by
Shouvik Roy
Publication date
2019
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We show how a distributed flocking controller can be synthesized using deep learning from a centralized controller which generates the trajectories of the flock. Our approach is based on supervised learning, with the centralized controller providing the training data to the learning agent, i.e., the synthesized distributed controller. We use Model Predictive Control (MPC) for the centralized controller, an approach that has been successfully demonstrated on flocking problems. MPC-based flocking controllers are high-performing but also computationally expensive. By learning a symmetric distributed neural flocking controller from a centralized MPC-based flocking controller, we achieve the best of both worlds: the neural controllers have high performance (on par with the MPC controllers) and high efficiency. Our experimental results demonstrate the sophisticated nature of the distributed controllers we learn. In particular, the neural controllers are capable of achieving myriad flocking-oriented control objectives, including flocking formation, collision avoidance, obstacle avoidance, predator avoidance, and target seeking. Moreover, they generalize the behavior seen in the training data in order to achieve these objectives in a significantly broader range of scenarios.
rate research
Read More
Decentralized deployment of drone swarms usually relies on inter-agent communication or visual markers that are mounted on the vehicles to simplify their mutual detection. This letter proposes a vision-based detection and tracking algorithm that enables groups of drones to navigate without communication or visual markers. We employ a convolutional neural network to detect and localize nearby agents onboard the quadcopters in real-time. Rather than manually labeling a dataset, we automatically annotate images to train the neural network using background subtraction by systematically flying a quadcopter in front of a static camera. We use a multi-agent state tracker to estimate the relative positions and velocities of nearby agents, which are subsequently fed to a flocking algorithm for high-level control. The drones are equipped with multiple cameras to provide omnidirectional visual inputs. The camera setup ensures the safety of the flock by avoiding blind spots regardless of the agent configuration. We evaluate the approach with a group of three real quadcopters that are controlled using the proposed vision-based flocking algorithm. The results show that the drones can safely navigate in an outdoor environment despite substantial background clutter and difficult lighting conditions. The source code, image dataset, and trained detection model are available at https://github.com/lis-epfl/vswarm.
When interacting motile units self-organize into flocks, they realize one of the most robust ordered state found in nature. However, after twenty five years of intense research, the very mechanism controlling the ordering dynamics of both living and artificial flocks has remained unsettled. Here, combining active-colloid experiments, numerical simulations and analytical work, we explain how flocking liquids heal their spontaneous flows initially plagued by collections of topological defects to achieve long-ranged polar order even in two dimensions. We demonstrate that the self-similar ordering of flocking matter is ruled by a living network of domain walls linking all $pm 1$ vortices, and guiding their annihilation dynamics. Crucially, this singular orientational structure echoes the formation of extended density patterns in the shape of interconnected bow ties. We establish that this double structure emerges from the interplay between self-advection and density gradients dressing each $-1$ topological charges with four orientation walls. We then explain how active Magnus forces link all topological charges with extended domain walls, while elastic interactions drive their attraction along the resulting filamentous network of polarization singularities. Taken together our experimental, numerical and analytical results illuminate the suppression of all flow singularities, and the emergence of pristine unidirectional order in flocking matter.
We study the first-order flocking transition of birds flying in low-visibility conditions by employing three different representative types of neural network (NN) based machine learning architectures that are trained via either an unsupervised learning approach called learning by confusion or a widely used supervised learning approach. We find that after the training via either the unsupervised learning approach or the supervised learning one, all of these three different representative types of NNs, namely, the fully-connected NN, the convolutional NN, and the residual NN, are able to successfully identify the first-order flocking transition point of this nonequilibrium many-body system. This indicates that NN based machine learning can be employed as a promising generic tool to investigate rich physics in scenarios associated to first-order phase transitions and nonequilibrium many-body systems.
We show how a high-performing, fully distributed and symmetric neural V-formation controller can be synthesized from a Centralized MPC (Model Predictive Control) controller using Deep Learning. This result is significant as we also establish that under very reasonable conditions, it is impossible to achieve V-formation using a deterministic, distributed, and symmetric controller. The learning process we use for the neural V-formation controller is significantly enhanced by CEGkR, a Counterexample-Guided k-fold Retraining technique we introduce, which extends prior work in this direction in important ways. Our experimental results show that our neural V-formation controller generalizes to a significantly larger number of agents than for which it was trained (from 7 to 15), and exhibits substantial speedup over the MPC-based controller. We use a form of statistical model checking to compute confidence intervals for our neural V-formation controllers convergence rate and time to convergence.
In this paper the optimal control of alignment models composed by a large number of agents is investigated in presence of a selective action of a controller, acting in order to enhance consensus. Two types of selective controls have been presented: an homogeneous control filtered by a selective function and a distributed control active only on a selective set. As a first step toward a reduction of computational cost, we introduce a model predictive control (MPC) approximation by deriving a numerical scheme with a feedback selective constrained dynamics. Next, in order to cope with the numerical solution of a large number of interacting agents, we derive the mean-field limit of the feedback selective constrained dynamics, which eventually will be solved numerically by means of a stochastic algorithm, able to simulate efficiently the selective constrained dynamics. Finally, several numerical simulations are reported to show the efficiency of the proposed techniques.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
