Predictive control of aerial swarms in cluttered environments

  title={Predictive control of aerial swarms in cluttered environments},
  author={Enrica Soria and Fabrizio Schiano and Dario Floreano},
  journal={Nat. Mach. Intell.},
Classical models of aerial swarms often describe global coordinated motion as the combination of local interactions that happen at the individual level. Mathematically, these interactions are represented with Potential Fields. Despite their explanatory success, these models fail to guarantee rapid and safe collective motion when applied to aerial robotic swarms flying in cluttered environments of the real world, such as forests and urban areas. Moreover, these models necessitate a tight… 

Figures and Tables from this paper

Swarm of micro flying robots in the wild

This work develops miniature but fully autonomous drones with a trajectory planner that can function in a timely and accurate manner based on limited information from onboard sensors and is integrated into the developed palm-sized swarm platform with onboard perception, localization, and control.

Bio-inspired control for collective motion in swarms of drones

This approach aims at implementing a coordination model directly inspired from the interactions and behaviors that a small fish, the rummy-nose tetra, adopts to display collective movements in the deployment of a group of UAVs inside a circular arena.

Multi-Agent Spatial Predictive Control with Application to Drone Flocking (Extended Version)

—We introduce the novel concept of Spatial Predictive Control (SPC) to solve the following problem: given a collection of agents (e.g., drones) with positional low-level controllers (LLCs) and a

On the Scalability of Vision-based Drone Swarms in the Presence of Occlusions

Vonoi-based interactions enable vision-based swarms to remain collision-free, ordered, and cohesive in the presence of occlusions, and show that the destabilizing effects of visibility switches can be mitigated if agents select their neighbors from adjacent Voronoi regions.

AGDS: adaptive goal-directed strategy for swarm drones flying through unknown environments

This paper aims to address a challenging problem of a drone swarm for a specific mission by reaching a desired region, through an unknown environment by developing a bio-inspired flocking algorithm with adaptive goal-directed strategy (AGDS).

Categories, Quantum Computing, and Swarm Robotics: A Case Study

A robot-instantiated theoretical framework and a quantitative worked-out example of a quantitative simulation of a toy model using quantum computing to shed light on potentialities of quantum computing in the realm of swarm robotics.

Collaborative Target Search with a Visual Drone Swarm: An Adaptive Curriculum Embedded Multi-stage Reinforcement Learning Approach

An adaptive embedded curriculum, where the task level can be adaptively adjusted according to the success rate achieved in training, and the effectiveness and generalization capability of the approach are validated using simulations and actual tests.

Fast Joint Multi-Robot Trajectory Optimization by GPU Accelerated Batch Solution of Distributed Sub-Problems

A joint multi-robot trajectory optimizer that can compute trajectories for tens of robots in aerial swarms within a small fraction of a second and demonstrates remarkable improvements in computation time its scaling with respect to the number of robots.

Nonlinear model predictive control for improving range-based relative localization by maximizing observability

Wireless ranging measurements have been proposed for enabling multiple Micro Air Vehicles (MAVs) to localize with respect to each other. However, the high-dimensional relative states are weakly

Swarms of flying robots in unknown environments

An optimal planning algorithm enables swarms of flying robots to explore unknown environments autonomously and safely. Description An optimal planning algorithm enables swarms of flying robots to



Optimized flocking of autonomous drones in confined environments

This paper numerically demonstrated that the induced swarm behavior remained stable under realistic conditions for large flock sizes and notably for large velocities, and showed that coherent and realistic collective motion patterns persisted even around perturbing obstacles.

Indoor navigation with a swarm of flying robots

A new autonomous flight methodology is presented using relative positioning sensors in reference to nearby static robots that relies solely on local sensing without requiring absolute positioning, environment maps, powerful computation or long-range communication.

Outdoor flocking and formation flight with autonomous aerial robots

This work presents the first decentralized multi-copter flock that performs stable autonomous outdoor flight with up to 10 flying agents and demonstrates that the local broadcast-type communication and the decentralized autonomous control method allows for the scalability of the model for much larger flocks.

Learning Vision-Based Flight in Drone Swarms by Imitation

This letter proposes an entirely visual approach to coordinate markerless drone swarms based on imitation learning and shows that the convolutional neural network trained on the visual inputs of the drone can learn not only robust inter-agent collision avoidance but also cohesion of the swarm in a sample-efficient manner.

Minimal navigation solution for a swarm of tiny flying robots to explore an unknown environment

The collective aspects of SGBA are studied, demonstrating that it allows a group of 33-g commercial off-the-shelf quadrotors to successfully explore a real-world environment and lay the basis for tackling other similarly complex missions with robot swarms in the future.

Online Trajectory Generation With Distributed Model Predictive Control for Multi-Robot Motion Planning

Simulation results show that the proposed collision avoidance method can reduce, on average, around 50% of the travel time required to complete a multi-agent point-to-point transition when compared to the well-studied Buffered Voronoi Cells (BVC) approach.

Reynolds flocking in reality with fixed-wing robots: Communication range vs. maximum turning rate

This work focuses on deploying a swarm of small fixed-wing flying robots that are required to maintain forward motion to avoid stalling and typically adopt low turn rates because of physical or energy constraints.

Model Predictive Trajectory Tracking and Collision Avoidance for Reliable Outdoor Deployment of Unmanned Aerial Vehicles

A novel approach for optimal trajectory tracking for unmanned aerial vehicles (UAV), using a linear model predictive controller (MPC) in combination with non-linear state feedback, which allows safe outdoors execution of multi-UAV experiments without the need for in-advance collision-free planning.

Decentralized Nonlinear Model Predictive Control for 3D Formation of Multirotor Micro Aerial Vehicles with Relative Sensing and Estimation

In order to deploy highly autonomous multi-rotor MAVs in non-trivial environments, several researchers focus on elaborating local and relative sensing in formation control and try to solve its limitations.

Nonlinear MPC for Collision Avoidance and Control of UAVs With Dynamic Obstacles

This letter proposes a Novel Nonlinear Model Predictive Control (NMPC) for navigation and obstacle avoidance of an Unmanned Aerial Vehicle (UAV) and applies a classification scheme to differentiate between different kinds of trajectories to predict future obstacle positions.