Miscellaneous


Controlling Self Driving Cars

Published on Jul 21, 2015

This is a video introduction to controlling self-driving cars, specifically using PID-control. Special emphasis is placed on how the proportional, integral, and derivative gains affect the performance of the vehicle.
 

UpHex's John Feminella on Adding Data Sensors to Cars

Published on Jul 28, 2015

From OSCON 2015: an interview with the co-founder of UpHex on the benefits of adding data-gathering sensors to cars.

About John Feminella:
John Feminella is an avid technologist, occasional public speaker, and frequent instigator of assorted shenanigans. He recently co-founded UpHex, a startup providing analytics management for digital agencies and their clients. John is also a guest lecturer at the University of Virginia, mentors budding entrepreneurs, and has earned a lot of meaningless Internet points. He lives in Charlottesville, VA and likes meta-jokes, milkshakes, and referring to himself in the third person in speaker bios.
 

Your Robo-Chauffeur Is Ready to Pick You Up

Published on Sep 30, 2015

MIT and Stanford are building research centers that will study how robots can help us be safer on the road.

Would you trust the keys over to a robot? Or would you be more comfortable with robot-assisted tech instead?
 

Can an autonomous car beat a human driver?

Published on Oct 7, 2015

Do you believe in a world with autonomous cars, a world with robots and control systems? Become a student Systems & Control at Eindhoven University of Technology and your dream might be closer than you can imagine.
 

RI Seminar: Ryan Eustice : University of Michigan’s Work Toward Autonomous Cars

Started on Oct 30, 2015

Ryan Eustice
Associate Professor, University of Michigan

Abstract
Self-driving test vehicles have become a reality on roadways and there is an ever present push toward making them a consumer product in the not so distant future. In this talk, I will give an overview of some of our on-going work (in collaboration with Ford Motor Company) in full-scale automated driving. In particular, we’ll look at some of our successes in high definition map building and precision localization, including our recent work in cross-modality localization using vision within a priori LIDAR maps. We’ll also review our work in multipolicy decision making in dynamic environments and discuss our new unique Mcity test facility for connected and automated driving.

Speaker Biography
Ryan M. Eustice is an Associate Professor in the Department of Naval Architecture and Marine Engineering at the University of Michigan where he additionally holds joint appointments in the Department of Electrical Engineering and Computer Science, and the Department of Mechanical Engineering. He is the Director of the Perceptual Robotics Laboratory (PeRL), a mobile robotics laboratory focused on algorithm development in the areas of robotic perception, navigation, and mapping. His active research projects include applications to autonomous underwater ship hull inspection, multi-vehicle cooperative underwater navigation, benthic high-resolution mapping, and automotive active safety and self-driving capabilities. Prior to joining the University of Michigan in 2006, he was a Postdoctoral Scholar at the Dynamical Systems and Controls Lab at The Johns Hopkins University and holds a B.S. degree in Mechanical Engineering from Michigan State University (1998) and a Ph.D. in Ocean Engineering from the MIT/WHOI Joint-Program (2005). He is recipient of a NSF CAREER Award and ONR Young Investigator Award, and is an Associate Editor for IEEE Transactions on Robotics, IEEE Robotics and Automation Letters, and IEEE Journal of Oceanic Engineering. His work on self-driving cars is in cooperation with Ford Motor Company on the Next Generation Vehicle project.
 

Stewart
from Felix Ros
June 3, 2015

Stewart is a tactile interface designed for a fully autonomous car. Self-driving cars offer obvious benefits such as faster travel and enhanced safety. However, they also eliminate a sense of freedom, expression, and control while driving.
Stewart’s objective is to accommodate a healthy relation between man and machine, to be achieved by an intuitive and expressive form of interaction. Stewart provides you with constant updates about the car’s behaviour and its intentions. If you don’t agree on the car’s next course of action, you can manipulate Stewart to change this. Stewart will learn from you as you can learn from Stewart, hopefully resulting in a mutually trustful relation.
Interaction through Stewart will bring about a haptic discussion about what the car’s next move will be. Who will win this discussion? Who knows best?

more info at: felixros.com/stewart.html
LinkedIn: nl.linkedin.com/in/rosfelix
Final Bachelor Project
Eindhoven University of Technology
Department of Industrial Design
2015


Stewart - software and hardware process video
December 13, 2015

Stewart is the result if an open ended design brief that focused on the "essential" details in design. The concept development and prototyping took a total of four months.
During the project, I used an iterative design approach where I made four working prototypes in the process. Two short qualitative user tests have been used for user feedback and prototype validation, the first user test was half way the project to test out the first functioning prototype and the other at the end of the project. Both tests consisted out of an improvised car simulation were the mapping of Stewart’s haptic feedback could be tested and validated.

The biggest challenge or this project was to go form a very abstract idea towards an understandable experience that raises the discussion of what a self driving car could be.
The project involved a lot of programming (Arduino and Processing), engineering, calculus and reflecting.
 

Imagine a Driverless Future

Published on Nov 18, 2015

A future with autonomous vehicles is fast approaching, but what will it look like? Researchers in the field visualize how a typical morning with a driverless car might go, and discuss what steps need to be taken for that future to be realized, including mention of the University of Michigan's new driverless proving ground - M city.
 

Sight Lines
November 10, 2015

To see how driverless cars might perceive — and misperceive — the world, ScanLAB Projects drove a 3-D laser scanner through the streets of London.
Music: Eternity by Dick Walter

Article "The Dream Life of Driverless Cars"
Autonomous vehicles might remain an expensive novelty, or they might utterly transform
society. Either way, they have much to teach us about how to look at the cities we live in.

by Geoff Manaughnov
November 11, 2015
 

Smarter Driver: How safe are self-driving cars?

Published on Dec 10, 2015

Are self-driving cars safer than human-driven vehicles? Brian Cooley discusses new research that shows what we've learned so far about the safety of autonomous vehicles.
 
Back
Top