Skip to main content
main-content

Über dieses Buch

Alexander Schaub examines how a reactive instinctive behavior, similar to instinctive reactions as incorporated by living beings, can be achieved for intelligent mobile robots to extend the classic reasoning approaches. He identifies possible applications for reactive approaches, as they enable a fast response time, increase robustness and have a high abstraction ability, even though reactive methods are not universally applicable. The chosen applications are obstacle avoidance and relative positioning – which can also be utilized for navigation – and a combination of both. The implementation of reactive instinctive behaviors for the identified tasks is then validated in simulation together with real world experiments.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Motivation

Abstract
Autonomous mobile robots still have deficiencies to cope with unknown and changing environments, while living creatures ranging from insects to human beings solve this with their adaptability and the ability to abstract. A deciding factor is not the reasoning performance of autonomous agents, which is obviously suffcient when comparing the processing power of a highly developed mobile robot to e.g. an insect, but they (often) lack a capability comparable to instinct or intuition.
Alexander Schaub

Chapter 2. Related Work

Abstract
This chapter discusses relevant work for the implementation of a reactive instinctive behavior, while considering all three aspects of an artificial intelligence agent. Therefore, the accordance of the state of the art with our proposed characteristics is evaluated considering hardware, sensors and algorithms.
Alexander Schaub

Chapter 3. Vision-Based Reactive Controllers

Abstract
First, this chapter motivates in Section 3.1 cameras as a well-suited choice for implementing reactive instinctive behaviors and recalls basic models and computer vision principles. After that, a novel principle for estimating the Time-to-Collision for single image points is presented in Section 3.2, before Section 3.3 introduces three representations for obstacle avoidance, navigation, and a concurrent execution of both respectively. Finally, Section 3.4 demonstrates how each of the three representations could be utilized for planning.
Alexander Schaub

Chapter 4. The ROboMObil

Abstract
This chapter describes the German Aerospace Center’s ROboMObil (ROMO), which is an electric vehicle conceptualized as robotic system. The ROMO is the test vehicle used to evaluate the approaches proposed in this work (compare also Chapter 5). After the hardware and the concept is introduced in Section 4.1, the autonomous systems architecture is described in Section 4.2, which explicitly considers the reactive instinctive tasks.
Alexander Schaub

Chapter 5. Results

Abstract
This chapter will evaluate and validate the concepts regarding the representational forms and their utilization for planning which were introduced and discussed in Chapter 3. The test platform is the ROboMObil, which enables all the necessary tests that are not feasible with a conventional vehicle due to its 3 DOF.
Alexander Schaub

Chapter 6. Conclusion

Abstract
This thesis has the goal to conceptualize autonomous vehicles with reactive instinctive behavior similar to the intuition of a human driver. For establishing the desired behavior, all three basic elements of an Artificial Intelligence Agent, of which autonomous mobile robots and more specifically autonomous vehicles form a sub-group, have to be considered explicitly: sensor, actuator, and the artificial intelligence itself connecting both.
Alexander Schaub

Backmatter

Weitere Informationen