Media Summary: Using camera based detection of the calibration pattern and open loop control to Lane following with supervised learning DB17. Maximilian Stölzle and Stefan Lionar from ETH Zurich implement advanced and robust object detection for

Duckietown System Identification Demo - Detailed Analysis & Overview

Using camera based detection of the calibration pattern and open loop control to Lane following with supervised learning DB17. Maximilian Stölzle and Stefan Lionar from ETH Zurich implement advanced and robust object detection for Project by: Marco Stalder, Simon Muntwiler, Anna Dai, Manuel Breitenstein, Andreas Aumiller, Miguel De La Iglesia at ETHZ ... Bruno Fournier and Sébastien Biner develop and evaluate reinforcement learning (RL) techniques for safe and autonomous ... The Robot Vision module of Self-Driving cars with

Example of a fun project: a Duckiebot DB21 hardware mod (added arms to the front) synched with external camera feed click and ... DB17 Duckiebots performing intersection coordination and navigation. Duckiebots communicate at intersections, in absence of a ... One of the most important computer vision tasks for autonomous driving is to detect, classify and localize different kinds of objects. While intersection navigation might look simple, it is actually a relatively complex autonomous driving behavior. Duckiebots need ... Link to original video: Check out other interesting projects: ...

Photo Gallery

Duckietown - System Identification Demo
Duckietown Lane Following Demo
Duckietown auto-parking demo
Duckietown - Supervised learning demo
YOLO-based Robust Object Detection in Duckietown
Duckietown Lane following demo
Duckietown Functionality at IEEE ICRA 2017, Singapore
Duckietown - Improving lane detection and control
Reinforcement Learning for the Control of Autonomous Robots
Duckietown Camera Calibration
Duckietown City Rescue Demo
Click-and-move Duckiebot with front facing arm
Sponsored
Sponsored
View Detailed Profile
Sponsored
Sponsored