Dean Pomerleau | Carnegie Mellon University (original) (raw)

Papers by Dean Pomerleau

Computer Standards & Interfaces, 1999

We describe an optical flow based obstacle detection system for use in detecting vehicles approac... more We describe an optical flow based obstacle detection system for use in detecting vehicles approaching the blind spot of a car on highways and city streets. The system runs at near frame rate (8-15 frames/second) on PC hardware. We will discuss the prediction of a camera image given an implicit optical flow field and comparison with the actual camera image. The advantage to this approach is that we never explicitly calculate optical flow. We will also present results on digitized highway images, and video taken from Navlab 5 while driving on a Pittsburgh highway.

Robotics and Autonomous Systems, 1997

Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on... more Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on the important features in an input scene. Previous work with an autonomous lane following system, ALVINN (Pomerleau, 1993), has yielded good results in uncluttered conditions. This paper presents an artificial neural network based learning approach for handling difficult scenes which will confuse the ALVINN system. This work presents a mechanism for achieving task-specific focus of attention by exploiting temporal coherence. A saliency map, which is based upon a computed expectation of the contents of the inputs in the next time step, indicates which regions of the input retina are important for performing the task. The saliency map can be used to accentuate the features which are important for the task, and de-emphasize those which are not.

The Kluwer International Series in Engineering and Computer Science, 1990

Robot Learning, 1993

Many real world problems quire a degree of flexibility that is diflicult to achieve using hand pr... more Many real world problems quire a degree of flexibility that is diflicult to achieve using hand programmed algorithms. One such domain is vision-based autonomous driving. In this task, the dual challenges of a constantly changing environment coupled with a real t h e processing constrain make the flexibility and efficiency of a machine learning system essential. This chapter describes just such a learning system, called ALVINN (Autonomous Land Vehicle In a Neural Network). It presents the neural network architecture and training techniques that allow &VI" to drive in a variety of circumstanm including singlelane paved and unpaved roads, multilane lined and unlined roads, and obstacle-ridden on-and offroad environments, at speeds of up to 55 miles per hour.

Intelligent vehicles must make real-time tactical level decisions to drive in mixed traffic envir... more Intelligent vehicles must make real-time tactical level decisions to drive in mixed traffic environments. Since repeatable testing of different algorithms in rare and potentially dangerous situations is necessary, we have developed a custom simulator for this task. SHIVA (Simulated Highways for Intelligent Vehicle Algorithms) mirrors many aspects of the Carnegie Mellon Navlab [26, 13] system, enabling algorithms developed in simulation to be implemented on the robot with minimal modification. Realistic sensor models encourage developers to create algorithms that will work on real robots. Incremental development is facilitated through hierarchies for vehicles, sensors and reasoning objects. An integrated simulation and animation environment provides interactive graphical debugging capabilities.

Neural Information Processing Systems, 1993

We have developed an artificial neural network based gaze tracking system which can be customized... more We have developed an artificial neural network based gaze tracking system which can be customized to individual users. A three layer feed forward network, trained with standard error back propagation, is used to determine the position of a user's gaze from the appearance of the user's eye. Unlike other gaze trackers, which normally require the user to wear cumbersome headgear,

Vision based mobile robot guidance has proven difficult for classical machine vision methods beca... more Vision based mobile robot guidance has proven difficult for classical machine vision methods because of the diversity and real time constraints inherent in the task. This book describes a connectionist system called ALVINN (Autonomous Land Vehicle In a Neural Network) that ...

IEEE International Conference on Neural Networks, 1988

Intelligent Transportation Systems, 1998

Intelligent Autonomous Systems, 2000

The use of artificial neural networks in the domain of autonomous vehicle navigation has produced... more 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 within the neural paradigm for autonomous road

Lecture Notes in Computer Science, 1999

Registration between voxel images of human anatomy enables cross-patient diagnosis and post-treat... more Registration between voxel images of human anatomy enables cross-patient diagnosis and post-treatment analysis. However, innate variations in the shape, size, and density of non-pathological anatomical structures between individuals make accurate registration difficult. Characterization of such normal but inherent variations provides guidance for registration.We extracted the pattern of normal variations in the appearances of brain structures from the T1-weighted magnetic resonance imaging (MRI) volumes of 105 subjects. This knowledge serves as a domain-relevant constraint which increases the accuracy of deformable registration.

Intelligent Unmanned Ground Vehicles, 1997

As shown in the previous chapter, much progress has been made toward solving the autonomous lane-... more 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 ...

Pattern Recognition, 1999

We study an application of image registration in the medical domain. Based on a 3-D hierarchical ... more We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we developed a prototype for automatic registering a standard atlas to a patient's data to create a customized atlas. The registration algorithm can also be applied to detect asymmetry in the patient data to help indicate the existence and location of any pathology. We have conducted experiments on 11 MRI scans of normal brains, 3 MRI and 1 CT scan of brains with pathologies.

2008 IEEE International Conference on Vehicular Electronics and Safety, 2008

Page 1. From Automated Highways to Urban Challenges Chirs Urmson, Dave Duggins, Todd Jochem, Dean... more Page 1. From Automated Highways to Urban Challenges Chirs Urmson, Dave Duggins, Todd Jochem, Dean Pomerleau and Chuck Thorpe Abstract ... Inc. For both vehicles, the throttle actuation was through the existing cruise control. ...

Neural Information Processing Systems, 1988

Page 1. - ALVINN: N AN AUTONOMOUS LAND VEHICLE aIN A NEURAL NETWORK 00 Technical Report AlP -77 D... more Page 1. - ALVINN: N AN AUTONOMOUS LAND VEHICLE aIN A NEURAL NETWORK 00 Technical Report AlP -77 Dean A. Pomerleau Department of Psychology Carnegie Mellon University IPittsburgh, PA 15213-3890 0 The Artificial Intelligence and Psychology Project DTIC ...

Intelligent Unmanned Ground Vehicles, 1997

In this chapter, we describe one of our early integrated systems which used multiple sensing algo... more In this chapter, we describe one of our early integrated systems which used multiple sensing algorithms, incorporated information from a map, and used an explicit representation of the uncertainty on sensor and position measurements.

Computer Standards & Interfaces, 1999

We describe an optical flow based obstacle detection system for use in detecting vehicles approac... more We describe an optical flow based obstacle detection system for use in detecting vehicles approaching the blind spot of a car on highways and city streets. The system runs at near frame rate (8-15 frames/second) on PC hardware. We will discuss the prediction of a camera image given an implicit optical flow field and comparison with the actual camera image. The advantage to this approach is that we never explicitly calculate optical flow. We will also present results on digitized highway images, and video taken from Navlab 5 while driving on a Pittsburgh highway.

Robotics and Autonomous Systems, 1997

Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on... more Reliable vision-based control of an autonomous vehicle requires the ability to focus attention on the important features in an input scene. Previous work with an autonomous lane following system, ALVINN (Pomerleau, 1993), has yielded good results in uncluttered conditions. This paper presents an artificial neural network based learning approach for handling difficult scenes which will confuse the ALVINN system. This work presents a mechanism for achieving task-specific focus of attention by exploiting temporal coherence. A saliency map, which is based upon a computed expectation of the contents of the inputs in the next time step, indicates which regions of the input retina are important for performing the task. The saliency map can be used to accentuate the features which are important for the task, and de-emphasize those which are not.

The Kluwer International Series in Engineering and Computer Science, 1990

Robot Learning, 1993

Many real world problems quire a degree of flexibility that is diflicult to achieve using hand pr... more Many real world problems quire a degree of flexibility that is diflicult to achieve using hand programmed algorithms. One such domain is vision-based autonomous driving. In this task, the dual challenges of a constantly changing environment coupled with a real t h e processing constrain make the flexibility and efficiency of a machine learning system essential. This chapter describes just such a learning system, called ALVINN (Autonomous Land Vehicle In a Neural Network). It presents the neural network architecture and training techniques that allow &VI" to drive in a variety of circumstanm including singlelane paved and unpaved roads, multilane lined and unlined roads, and obstacle-ridden on-and offroad environments, at speeds of up to 55 miles per hour.

Intelligent vehicles must make real-time tactical level decisions to drive in mixed traffic envir... more Intelligent vehicles must make real-time tactical level decisions to drive in mixed traffic environments. Since repeatable testing of different algorithms in rare and potentially dangerous situations is necessary, we have developed a custom simulator for this task. SHIVA (Simulated Highways for Intelligent Vehicle Algorithms) mirrors many aspects of the Carnegie Mellon Navlab [26, 13] system, enabling algorithms developed in simulation to be implemented on the robot with minimal modification. Realistic sensor models encourage developers to create algorithms that will work on real robots. Incremental development is facilitated through hierarchies for vehicles, sensors and reasoning objects. An integrated simulation and animation environment provides interactive graphical debugging capabilities.

Neural Information Processing Systems, 1993

We have developed an artificial neural network based gaze tracking system which can be customized... more We have developed an artificial neural network based gaze tracking system which can be customized to individual users. A three layer feed forward network, trained with standard error back propagation, is used to determine the position of a user's gaze from the appearance of the user's eye. Unlike other gaze trackers, which normally require the user to wear cumbersome headgear,

Vision based mobile robot guidance has proven difficult for classical machine vision methods beca... more Vision based mobile robot guidance has proven difficult for classical machine vision methods because of the diversity and real time constraints inherent in the task. This book describes a connectionist system called ALVINN (Autonomous Land Vehicle In a Neural Network) that ...

IEEE International Conference on Neural Networks, 1988

Intelligent Transportation Systems, 1998

Intelligent Autonomous Systems, 2000

The use of artificial neural networks in the domain of autonomous vehicle navigation has produced... more 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 within the neural paradigm for autonomous road

Lecture Notes in Computer Science, 1999

Registration between voxel images of human anatomy enables cross-patient diagnosis and post-treat... more Registration between voxel images of human anatomy enables cross-patient diagnosis and post-treatment analysis. However, innate variations in the shape, size, and density of non-pathological anatomical structures between individuals make accurate registration difficult. Characterization of such normal but inherent variations provides guidance for registration.We extracted the pattern of normal variations in the appearances of brain structures from the T1-weighted magnetic resonance imaging (MRI) volumes of 105 subjects. This knowledge serves as a domain-relevant constraint which increases the accuracy of deformable registration.

Intelligent Unmanned Ground Vehicles, 1997

As shown in the previous chapter, much progress has been made toward solving the autonomous lane-... more 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 ...

Pattern Recognition, 1999

We study an application of image registration in the medical domain. Based on a 3-D hierarchical ... more We study an application of image registration in the medical domain. Based on a 3-D hierarchical deformable registration algorithm, we developed a prototype for automatic registering a standard atlas to a patient's data to create a customized atlas. The registration algorithm can also be applied to detect asymmetry in the patient data to help indicate the existence and location of any pathology. We have conducted experiments on 11 MRI scans of normal brains, 3 MRI and 1 CT scan of brains with pathologies.

2008 IEEE International Conference on Vehicular Electronics and Safety, 2008

Page 1. From Automated Highways to Urban Challenges Chirs Urmson, Dave Duggins, Todd Jochem, Dean... more Page 1. From Automated Highways to Urban Challenges Chirs Urmson, Dave Duggins, Todd Jochem, Dean Pomerleau and Chuck Thorpe Abstract ... Inc. For both vehicles, the throttle actuation was through the existing cruise control. ...

Neural Information Processing Systems, 1988

Page 1. - ALVINN: N AN AUTONOMOUS LAND VEHICLE aIN A NEURAL NETWORK 00 Technical Report AlP -77 D... more Page 1. - ALVINN: N AN AUTONOMOUS LAND VEHICLE aIN A NEURAL NETWORK 00 Technical Report AlP -77 Dean A. Pomerleau Department of Psychology Carnegie Mellon University IPittsburgh, PA 15213-3890 0 The Artificial Intelligence and Psychology Project DTIC ...

Intelligent Unmanned Ground Vehicles, 1997

In this chapter, we describe one of our early integrated systems which used multiple sensing algo... more In this chapter, we describe one of our early integrated systems which used multiple sensing algorithms, incorporated information from a map, and used an explicit representation of the uncertainty on sensor and position measurements.