Vision-Based Autonomous Navigation Using Supervised Learning Techniques

@inproceedings{Souza2011VisionBasedAN,
  title={Vision-Based Autonomous Navigation Using Supervised Learning Techniques},
  author={Jefferson Rodrigo de Souza and Gustavo Pessin and Fernando Santos Os{\'o}rio and Denis Fernando Wolf},
  booktitle={EANN/AIAI},
  year={2011}
}
This paper presents a mobile control system capable of learn behaviors based on human examples. Our approach is based on image processing, template matching, finite state machine, and template memory. The system proposed allows image segmentation using neural networks in order to identify navigable and non-navigable regions. It also uses supervised learning techniques which work with different levels of memory of the templates. As output our system is capable controlling speed and steering for… 

Vision and GPS-based autonomous vehicle navigation using templates and artificial neural networks

This paper presents a vehicle control system capable of learning to navigate autonomously. Our approach is based on image processing, road and navigable area identification, template matching

Accuracy improvement in 3D laser scanner based on dynamic triangulation for autonomous navigation system

TLDR
A new signal provided by an encoder is used to reduce the error generated by variations in angular velocity in the proposed method to improve accuracy on laser vision systems based on dynamic triangulation for mobile robots.

Robust Approach to Supervised Deep Neural Network Training for Real-Time Object Classification in Cluttered Indoor Environment

TLDR
This study proposes mission specific input data augmentation techniques and the design of light-weight deep neural network architecture that is capable of real-time object classification and a sequential gradient descent algorithm was implemented.

References

SHOWING 1-10 OF 20 REFERENCES

Template-based autonomous navigation in urban environments

TLDR
The proposed system allows to train an image segmentation algorithm in order to identify navigable and non-navigable regions (inside/outside roads), generating as output the steering control for an Electric Autonomous Vehicle, that should stay following the road.

Anticipatory Driving for a Robot-Car Based on Supervised Learning

TLDR
This work shows how a learning-based system can be extended to planning, needing little a priori knowledge, and achieves a novel form of velocity control, based only on information in image coordinates.

A Road Following Approach Using Artificial Neural Networks Combinations

TLDR
An analyses of terrain identification based on different visual information using a MLP artificial neural network and combining responses of many classifiers is described.

Vision For Intelligent Road Vehicles

  • V. Graefe
  • Computer Science
    Proceedings of the Intelligent Vehicles '93 Symposium
  • 1993
TLDR
A system of visual object recognition modules developed within the EUREKA project PROMETHEUS constitute a basis for an intelligent road vehicle, able to recognize traffic situations in real time and to react accordingly.

ALVINN: An Autonomous Land Vehicle in a Neural Network

TLDR
ALVINN (Autonomous Land Vehicle In a Neural Network) is a 3-layer back-propagation network designed for the task of road following that can effectively follow real roads under certain field conditions.

Model Based Vehicle Tracking for Autonomous Driving in Urban Environments

TLDR
The tracking module provides reliable tracking of moving vehicles from a high-speed moving platform using laser range finders and models both dynamic and geometric properties of the tracked vehicles and estimates them using a single Bayes filter per vehicle.

Model Based Vehicle Tracking in Urban Environments

TLDR
This work shows how to build consistent and efficient 2D representations out of 3D range data and how to detect poorly visible black vehicles.

Self-supervised Monocular Road Detection in Desert Terrain

TLDR
This method for identifying drivable surfaces in difficult unpaved and offroad terrain conditions as encountered in the DARPA Grand Challenge robot race achieves robustness by combining sensor information from a laser range finder, a pose estimation system and a color camera.

Robotics: Science and Systems XV

TLDR
The papers presented cover a range of topics, including computer vision, mapping, terrain identification, distributed systems, localization, manipulation, collision avoidance, multibody dynamics, obstacle detection, microrobotic systems, pursuit-evasion, grasping and manipulation, tracking, spatial kinematics, machine learning, and sensor networks.

An intelligent driving system for automatically anticipating and negotiating road curves

TLDR
Recent work on intelligent speed adaptation and steering control (ISASC) presents a novel feature of which is the ability to anticipate the road profile and negotiate curves safely, and shows the robustness of the system in learning the desired human driving expertise and applying this knowledge to negotiate new unseen roads.