DARPA Urban Challenge Research Articles

Darpa Urban Challenge 2007

A driverless car race through urban traffic was the task facing the teams in the Darpa Urban Challenge 2007. Without any human assistance, a 2007 Chevy Tahoe called “Boss” navigated its way to the finishing line and won this year’s rally. What sounds like the storyline from a science fiction film is in fact the future of driver assistance systems for safe and autonomous driving.

Darpa Urban Challenge 2007

A driverless car race through urban traffic was the task facing the teams in the Darpa Urban Challenge 2007. Without any human assistance, a 2007 Chevy Tahoe called “Boss” navigated its way to the finishing line and won this year’s rally. What sounds like the storyline from a science fiction film is in fact the future of driver assistance systems for safe and autonomous driving.

Empirical Evaluation of an Autonomous Vehicle in an Urban Environment

The DARPA Urban Challenge is providing an opportunity for interested scientists to compete in designing and proving an unmanned vehicle. The autonomous vehicle must avoid collisions, operate in compromised conditions and be robust and independent of human operators. Navigation may be achieved by a varied number of methods. Most will rely on Global Positioning System (GPS) for waypoints, checkpoints and general travel. A route file will be provided for the test site that contains information related to GPS coordinates throughout the course. Vehicles must safely navigate to checkpoints while maintaining road rules with safety. In the event that GPS is lost or compromised, the vehicles must still navigate to the checkpoints while determining traversable pathways. Optional techniques have been developed in order to navigate without GPS. We build a map of all of the waypoints along with other route information. Whenever we need to navigate to a checkpoint or gate in the absence of GPS, we identify the location we want to head to and use that as a directional bias compared to our current location.We then follow road rules to get through correct gates to the checkpoint using modified orienteering techniques.

Route Navigation in the Urban Grand Challenge with Compromised GPS

The DARPA Urban Challenge is providing an opportunity for interested scientists to compete in designing and proving an unmanned vehicle.The autonomous vehicle must avoid collisions, operate in compromised conditions and be robust and independent of human operators. Navigation may be achieved by a varied number of methods. Most will rely on Global Positioning System (GPS) for waypoints, checkpoints and general travel. A route file will be provided for the test site that contains information related to GPS coordinates throughout the course. Vehicles must safely navigate to checkpoints while maintaining road ruleswithsafety.IntheeventthatGPSislostorcompromised,thevehiclesmuststillnavigate to the checkpoints while determining traversable pathways. Optional techniques have been developed in order to navigate without GPS. We build a map of all of the waypoints along with other route information. Whenever we need to navigate to a checkpoint or gate in the absence of GPS, we identify the location we want to head to and use that as a directional bias compared to our current location. We then follow road rules to get through correct gates to the checkpoint using modified orienteering techniques.

Special Issue on the DARPA Urban Challenge Autonomous Vehicle Competition

Special Issue on the DARPA Urban Challenge Autonomous Vehicle Competition

Planning Continuous Curvature Paths Using Constructive Polylines

Previous methods for planning clothoid based continuous curvature paths aim at minimizing path length. However, minimal length paths are not always smooth, natural, and drivable. We discuss a method of generating clothoid-based trajectories using constructive polylines. The goal of the motion planner is to create a path for a large car-like vehicle in human driving environments, thus, the trajectories must be smooth, drivable, and natural enough to be used on roadways. We show several examples of trajectories developed for a DARPA Urban Challenge vehicle.

Team Gator Nation's Autonomous Vehicle Development for the 2007 DARPA Urban Challenge

This paper describes the system design developed for Team Gator Nation’s submission to the 2007 DARPA Urban Challenge. A hybrid Toyota Highlander has been automated and instrumented with pose estimation (GPS and inertial) and object detection (vision and ladar) sensors. The control architecture consists of four primary elements, i.e. Planning Element, Perception Element, Intelligence Element, and Control Element. The Intelligence Element implements the Adaptive Planning Framework developed by researchers at the University of Florida. This framework provides a means for situation assessment, behavior mode evaluation, and behavior selection and execution. The architecture is implemented on a system distributed over ten dual-core computers that intercommunicate via the Joint Architecture for Unmanned Systems (JAUS) version 3.2 protocol. This work’s primary contribution addresses the technical challenges of (a) the reconciliation of differences in estimated global pose, a priori data, and sensed information, (b) the determination of the appropriate behavior mode, and (c) the smooth transition of vehicle control between behavior modes. The processes that perform these tasks as well as the other necessary processes that perform perception, data integration, planning, and control are described in detail together with their design rationale. Finally, testing results accomplished to date are presented.

Software & Systems Engineering Process and Tools for the Development of Autonomous Driving Intelligence

When a large number of people with heterogeneous knowledge and skills run a project together, it is important to use a sensible engineering process. This especially holds for a project building an intelligent autonomously driving car to participate in the 2007 DARPA Urban Challenge. In this article, we present essential elements of a software and systems engineering process for the development of artificial intelligence capable of driving autonomously in complex urban situations. The process includes agile concepts, like test first approach, continuous integration of every software module and a reliable release and configuration management assisted by software tools in integrated development environments. However, the most important ingredients for an efficient and stringent development are the ability to efficiently test the behavior of the developed system in a flexible and modular simulator for urban situations. I. I ntroduction O CUSED research is often centered around interesting challenges and awards. The airplane industry started off with awards for the first flight over the British Channel as well as the Atlantic Ocean. The Human Genome Project, the Robo Cups and the series of DARPA Grand Challenges for autonomous vehicles serve this very same purpose to foster research and development in a particular direction. The 2007 DARPA Urban Challenge 16

Steering Control of the Autonomous Vehicle: CajunBot

This paper describes the steering controller of the CajunBot II, an autonomous vehicle designed for the DARPA Urban Challenge. The autonomous vehicle is a modified Jeep Wrangler Rubicon equipped with INS/GPS for localization, three sets of sensors and three single board computers. The control objective is to make the lateral error at a certain point ahead of the vehicle zero. The distance of this point from the vehicle is called the look-ahead distance. A proportional Integral controller augmented with a moving average filter to dump the yaw internal dynamics is proposed to achieve this objective. The steering controller was tested under full-scale conditions and its dynamic performances are discussed here.

Robotic Cars Tackle Crosstown Traffic--and Not One Another

ROBOTICSVICTORVILLE, CALIFORNIA-- In DARPA's Urban Challenge, cars that drive themselves face off in a strange, soulless rush hour. Are human drivers about to go the way of the buggy whip? (For more on robotics, see this week's [special section][1].) [1]: http://www.sciencemag.org/cgi/content/short/318/5853/1083

A Robotic Future

![Figure][1] CREDIT: DAVID FIERSTEIN In Douglas Adams' science fiction series The Hitchhiker's Guide to the Galaxy , the Sirius Cybernetics Corporation defined a robot as “your plastic pal who's fun to be with,” but it was a corporation whose complaints department occupied the major landmasses of three planets and was the only division to constantly show a profit. Technology and automation have provided a huge number of labor-saving devices and have at times relieved humans from having to do monotonous and dangerous jobs such as painting sheet metal or cleaning oil pipelines. However, there are times when one really needs to interact with another human being, and at these times, the automated “customer service” or banking machine is a poor substitute for a human. What differentiates robots from other pieces of technology is their ability to combine automation with action and at times a considerable amount of mobility. They are not only able to do static tasks such as dispense money or direct phone calls, but they can also lift, walk, weld, paint, vacuum, or explore. Unlike most devices that are designed to be used by a human operator, robots are increasingly being built to function within a human environment and are thus becoming more and more humanoid. Perhaps for this reason we view them in a different light than other technologies. This special section looks at robots and robotics from a wide range of perspectives. Bellingham and Rajan (p. 1098) tell how robots with an increasing sense of autonomy are being used to explore the hostile environments under the oceans and in outer space. Pfeifer, Lungarella, and Iida (p. 1088) examine recent efforts to design robots based on lessons learned from biological organisms. They show that robots can improve their performance by borrowing living body plans and substructures. Madden (p. 1094) reviews the progress that has been made in developing artificial muscles that can compete with the properties of human muscle and may one day enable untethered robots to run, leap, jump, or climb. But even as robots become more lifelike, the biological function of self-replication still eludes them, as Cho (p. 1084) reports. The last two pieces take us from body to brain. In a story by Lester (p. [1086][2]), we find that robots are increasingly used in secondary schools and undergraduate programs as tools to interest students in engineering and computer science. From a different direction, a Perspective from Edelman (p. [1103][3]) describes a research program in which robots equipped with brainlike devices learn to carry out tasks in the presence of visual cues and other sensory feedback. These “Darwin” bots may teach us something about our own ways of thinking and learning. Outside the special section are two stories in News Focus. Service (p. [1056][4]) looks at future exploration of the Northeast Pacific Ocean using partly robotic platforms, and Cho (p. [1060][5]) covers the DARPA Urban Challenge, an international competition for self-navigating driverless cars held in California earlier this month. In looking to the future it is also prudent to look at the past. In an Editorial by Sawyer (p. 1037), we learn how the science fiction literature has long considered a robotic future and the many ethical questions this will raise. They most certainly won't be all plastic, and they may not be our pals, but robots are going to play an increasing role in both scientific and everyday life. It will certainly be interesting to see where we take them and where they are able to take us. [1]: pending:yes [2]: /lookup/doi/10.1126/science.318.5853.1086 [3]: /lookup/doi/10.1126/science.1148677 [4]: /lookup/doi/10.1126/science.318.5853.1056 [5]: /lookup/doi/10.1126/science.318.5853.1060

Why we compete in DARPA's Urban Challenge autonomous robot race

The robots will have to find their own way, sensing and predicting their whereabouts through automated perception, planning, and control.

CMU robot car first in DARPA Urban Challenge

CMU robot car first in DARPA Urban Challenge