Todd Jochem

Carnegie Mellon University | CMU · Robotics Institute

As shown in the previous chapter, much progress has been made toward solving the autonomous lane-keeping problem. Systems which can drive robot vehicles at high speeds for long distances have been demonstrated. Some systems use road models to determine where lane markings are expected[5.2][5.6][5.7], while others are based on artificial neural netw...

the testbed vehicle on which much of this work was conducted. The views and conclusions contained in this document are those of the author and should not be interpreted as representing the official policies, either expressed or implied, of the funding agencies. Keywords: Mobile robots, autonomous driving, active vision, virtual cameras, lane transi...

This paper describes autonomous vehicle and driver assistance research beginning with the 1997 National Automated Highway System Consortium Demonstration. As a microcosm of the community at large we discuss how Carnegie Mellon autonomous vehicle research has progressed in the last decade. Since the demonstration we have formed two companies: Assist...

Obstacle detection, and more generally, terrain classification are two of the most important and fundamental perception functions required for robust unmanned off-road vehicle operation. To better address these tasks, we have developed a novel method that uses multiple readings from multiple sensor modalities to compute a vector measure of the phys...

Obstacle detection, and more generally, terrain classification are two of the most important and fundamental perception functions required for robust unmanned off-road vehicle operation. To better address these tasks, we have developed a novel method that uses multiple readings from multiple sensor modalities to compute a vector measure of the phys...

This paper describes an integrated MMW radar and vision sensor system for autonomous on-road navigation. The radar sensor has a range of approximately 200 metres and uses a linear array of receivers and wavefront reconstruction techniques to compute range and bearing of objects within the field of view. It is integrated with a vision based lane kee...

The use of artificial neural networks in the domain of autonomous vehicle navigation has produced promising results. ALVINN [Pomerleau, 1991] has shown that a neural system can drive a vehicle reliably and safely on many different types of roads, ranging from paved paths to interstate highways. Even with these impressive results, several areas with...

In recent years, significant progress has been made towards achieving autonomous roadway navigation using video images. None of the systems developed take full advantage of all the information in the 512 Theta 512 pixel, 30 frame/second color image sequence. This can be attributed to the large amount of data which is present in the color video imag...

In August of 1997, The US National Automated Highway System Consortium (NAHSC) presented a proof of technical feasibility demonstration of automated driving. The 97 Demo took place on car-pool lanes on I–15 in San Diego, California. Members of the Consortium demonstrated many different functions, including: Vision-based road following Lane departur...

this document is strongly based on these two tenets. To facilitate this work, a new sensor called a virtual camera is used. Developing more robust autonomous road following systems and improving driving performance is possible using virtual cameras. Virtual cameras are the fundamental tool upon which all other virtual active vision tools and techni...

this document is strongly based on these two tenets. To facilitate this work, a new sensor called a virtual camera is used. Developing more robust autonomous road following systems and improving driving performance is possible using virtual cameras. Virtual cameras are the fundamental tool upon which all other virtual active vision tools and techni...

In August 1997, the US National Automated Highway System Consortium (NAHSC) presented a proof of technical feasibility demonstration of automated driving. It took place on I-15, in San Diego, California. Members of the consortium demonstrated many different functions: vision-based road following, following magnetic nails, following a radar reflecti...

This paper describes an integrated MMW radar and vision sensor system for autonomous on-road navigation. The radar sensor has a range of approximately 200 metres and uses a linear array of receivers and wavefront reconstruction techniques to compute range and bearing of objects within the field of view. It is integrated with a vision based lane kee...

Much progress has been made toward understanding the autonomous on-road navigation problem using vision based methods. A next step in this evolution is the intelligent detection and traversal of road junctions and intersections. The techniques presented in this paper are based on a data driven, active philosophy of vision based intersection navigat...

Giving robots the ability to operate in the real world has been, and continues to be, one of the most difficult tasks in AI research. Since 1987, researchers at Carnegie Mellon University have been investigating one such task. Their research has been focused on using adaptive, vision-based systems to increase the driving performance of the Navlab l...

The Ralph vision system helps automobile drivers steer, by sampling an image, assessing the road curvature, and determining the lateral offset of the vehicle relative to the lane center. Ralph has performed well under extensive tests, including a coast-to-coast, 2,850-mile drive

Many systems have been created which can keep an autonomous vehicle within a driving lane, but little experimental work has been reported that describes methods to transition a vehicle between lanes. Three techniques to accomplish lane transition using the ALVINN lane keeping system are reported here. The most basic involves intelligently switching...

Research into self driving vehicles and driver monitoring systems has reached the point where long duration and distance field testing has become feasible. However, vehicle and computer systems which provide the functionality to accomplish these tests have been too expensive or inconvenient. This paper describes a simple, yet powerful platform, des...

AURORA is a vision-based system designed to warn a vehicle driver of possible impending roadway departure accidents. It employs a downward looking color video camera with a wide angle lens, a digitizer, and a portable Sun Sparc workstation. Using a binormalized adjustable template correlation algorithm, it reliably detects lane markers on structure...

The use of artificial neural networks in the domain of autonomous driving has produced promising results. ALVINN has shown that a neural system can drive a vehicle reliably and safely on many different types of roads, ranging from paved paths to interstate highways. The next step in the evolution of autonomous driving systems is to intelligently ha...

The use of artificial neural networks in the domain of autonomous driving has produced promising results. ALVINN has shown that a neural system can drive a vehicle reliably and safely on many different types of roads, ranging from paved paths to interstate highways (9). The next step in the evolution of autonomous driving systems is to intelligentl...

Significant progress has been made towards achieving autonomous roadway navigation using video images. However, none of the systems developed take full advantage of all the information in the 512 × 512 pixel, 30 frame/second color image sequence. This can be attributed to the large amount of data which is present in the color video image stream (22...

In 1991, Karl Sims presented work on artificial evolution in which he used genetic algorithms to evolve complex structures for use in computer generated images and animations. The evolution of the computer generated images progressed from simple, randomly generated shapes to interesting images which the users interactively created. The evolution ad...