Online Planning and Navigation of a Quadcopter through Obstacle-dense Environments

This video is a demonstration of the results published in the paper: “A Hybrid Method for Online Trajectory Planning of Mobile Robots in Cluttered Environments” by Leobardo Campos-Macías, David Gómez-Gutiérrez, Rodrigo Aldana-López, Rafael de la Guardia and José I. Parra Vilchis. IEEE Robotics and Automation Letters, 2017 eISSN: 2377-3766, DOI: 10.1109/LRA.2017.2655145
To illustrate the effectiveness of this approach for online planning, the proposed method was applied to the fluid autonomous navigation of a quadcopter Crazyflie 2.0 platform in multiple environments consisting of up to two hundred obstacles. The scenarios hereinafter presented are some of the most densely cluttered experiments for online planning and navigation reported to date.
The publisher version and the full citation details can be found at:
dx.doi.org/10.1...
The contents of this paper were also selected for presentation at the International Conference on Robotics and Automation, 2017.

[@violent_bebop9687]

Can you guys get together with the Department of Transportation and fcking fix the disaster that is automobile traffic?

[@rfyorfyo5022]

what if it would fly with no planning but avoid obstacles by itself?

[@bugrahana3395]

it can be stop at some point because of local minima. but if you can convexified your obstacle through control input quadratic metric, you can achieve this task but obstacles is very different shape especially in second experiment. so you can not formulate each obstacle to implement convexification. therefore , you need planning first..