Christoph Stiller
KIT, Germany | Title: What should I do here? Visual Semantic Mapping for Automated Automobiles
Abstract: Vehicle automation is among the most fascinating trends in automotive electronics and a huge challenge to Machine Vision. We investigate the information needed by automated vehicles and elaborate on the augmentation of sensor information by prior knowledge from digital maps. We show that cognitive and autonomous vehicles with a few close-to-market sensors are feasible when prior information is available from maps. Vision plays the dominant role in our autonomous vehicle. Methods for automated mapping based on vision are discussed that build the basis for real-time automated decision-making and motion planning.
Extensive experiments are shown in real world scenarios from our AnnieWAY and BerthaOne experimental vehicles, the winner of the 2011 and second winner of the 2016 Grand Cooperative Driving Challenge, respectively. We also discuss lesons learned from the autonomous Bertha Benz memorial tour from Mannheim to Pforzheim through a highly populated area in Germany.
|
Davide Scaramuzza
UZH, Switzerland | Title: Autonomous, Agile, Vision-controlled Drones: from Active to Event Vision
Abstract: Autonomous quadrotors will soon play a major role in search-and-rescue and remote-inspection missions, where a fast response is crucial. Quadrotors have the potential to navigate quickly through unstructured environments, enter and exit buildings through narrow gaps, and fly through collapsed buildings. However, their speed and maneuverability are still far from those of birds. Indeed, agile navigation through unknown, indoor environments poses a number of challenges for robotics research in terms of perception, state estimation, planning, and control. In this talk, I will show that active vision is crucial in order to plan trajectories that improve the quality of perception. Also, I will talk about our recent results on event based vision.
|
Robert Mahney
ANU, Australia | Title: Visual flow and control of aerial robotic vehicles
Abstract: Visual flow is a powerful and rich motion cue that enables robust control of mobile roboic systems. This talk covers some of the results in visual flow and control of robotic vehicles that the speaker has been involved in, from flow based stabilisation and autonomous landing of aerial vehicles, through to recent work on dense real-time flow algorithms for embedded hardware and the novel structure flow formulation.
|
Gerhard Paar
JOANNEUM RESEARCH, Austria | Title: Vision & Visualization Technologies for Planetary Rovers
Abstract: In the last 40 years dozens of robotic probes have successfully landed on other planets and moons. Literally all of them are using cameras to explore the environment and help scientific analysis and navigation. We give an overview of the sensors and techniques used in this context for processing and exploitation of image data, examples from past and ongoing Mars rover missions, as well as reports from preparation work for the currently planned NASA Mars-2020 and ESA ExoMars Rover missions. Current challenges such as data fusion between remote sensing and rover 3D image products are addressed, and scientific use cases are demonstrated by examples from the visualization front-end.
|
CVVT2016
Call for Papers
