Showing posts with label C. (main sources)-cvprtum. Show all posts
Showing posts with label C. (main sources)-cvprtum. Show all posts

2017-03-28

Real-Time Trajectory Replanning for MAVs using Uniform B-splines and 3D Circular Buffer


source: cvprtum    2017年2月25日
Real-Time Trajectory Replanning for MAVs using Uniform B-splines and 3D Circular Buffer
Authors: Vladyslav Usenko, Lukas von Stumberg, Andrej Pangercic and Daniel Cremers
Paper: https://arxiv.org/abs/1703.01416
Code: https://github.com/vsu91/ewok
Web-page: https://vision.cs.tum.edu/research/ro...
Abstract:
In this work we present a real-time approach for local trajectory replanning for MAVs. Current trajectory generation methods for multicopters achieve high success rates in cluttered environments, but assume the environment is static and require prior knowledge of the map. In our work we utilize the results of such planners and extend them with local replanning algorithm that can handle unmodeled (possibly dynamic) obstacles while keeping MAV close to the global trajectory. To make our approach real-time capable we maintain information about the environment around MAV in an occupancy grid stored in 3D circular buffer that moves together with a drone, and represent the trajectories using uniform B-splines. This representation ensures that trajectory is sufficiently smooth and at the same time allows efficient optimization.

2017-03-18

Machine Learning for Computer Vision by Rudolph Triebel (TU München)

# playlist of the 13 videos (click the upper-left icon of the video)

source: cvprtum     2013年11月11日

Visual Navigation for Flying Robots by Jürgen Sturm

# playlist of the 13 videos (click the upper-left icon of the video) 

source: cvprtum     2013年4月18日
Course website: http://vision.in.tum.de/teaching/ss20...
Speaker: Dr. Jürgen Sturm http://vision.in.tum.de/members/sturmju

2017-03-17

Multiple View Geometry (Summer 2013) by Daniel Cremers (TU München)

# playlist of the 17 videos (click the upper-left icon of the video) 

source: cvprtum      2013年5月15日

Variational Methods for Computer Vision by Daniel Cremers (TU München)

# playlist of the 21 videos (click the upper-left icon of the video) 

source: cvprtum   2013年10月17日