scholarly journals LEARNING TO BEHAVE IN SPACE: A QUALITATIVE SPATIAL REPRESENTATION FOR ROBOT NAVIGATION WITH REINFORCEMENT LEARNING

2008 ◽  
Vol 17 (03) ◽  
pp. 465-482 ◽  
Author(s):  
LUTZ FROMMBERGER

The representation of the surrounding world plays an important role in robot navigation, especially when reinforcement learning is applied. This work uses a qualitative abstraction mechanism to create a representation of space consisting of the circular order of detected landmarks and the relative position of walls towards the agent's moving direction. The use of this representation does not only empower the agent to learn a certain goal-directed navigation strategy faster compared to metrical representations, but also facilitates reusing structural knowledge of the world at different locations within the same environment. Acquired policies are also applicable in scenarios with different metrics and corridor angles. Furthermore, gained structural knowledge can be separated, leading to a generally sensible navigation behavior that can be transferred to environments lacking landmark information and/or totally unknown environments.

Robotica ◽  
2009 ◽  
Vol 28 (5) ◽  
pp. 637-648 ◽  
Author(s):  
Hamid Teimoori ◽  
Andrey V. Savkin

SUMMARYThe problem of wheeled mobile robot (WMR) navigation toward an unknown target in a cluttered environment has been considered. The biologically inspired navigation algorithm is the equiangular navigation guidance (ENG) law combined with a local obstacle avoidance technique. The collision avoidance technique uses a system of active sensors which provides the necessary information about obstacles in the vicinity of the robot. In order for the robot to avoid collision and bypass the enroute obstacles, the angle between the instantaneous moving direction of the robot and a reference point on the surface of the obstacle is kept constant. The performance of the navigation strategy is confirmed with computer simulations and experiments with ActivMedia Pioneer 3-DX wheeled robot.


2013 ◽  
Vol 30 (1) ◽  
pp. 106-136 ◽  
Author(s):  
Juan Chen ◽  
Anthony G. Cohn ◽  
Dayou Liu ◽  
Shengsheng Wang ◽  
Jihong Ouyang ◽  
...  

AbstractRepresentation and reasoning with qualitative spatial relations is an important problem in artificial intelligence and has wide applications in the fields of geographic information system, computer vision, autonomous robot navigation, natural language understanding, spatial databases and so on. The reasons for this interest in using qualitative spatial relations include cognitive comprehensibility, efficiency and computational facility. This paper summarizes progress in qualitative spatial representation by describing key calculi representing different types of spatial relationships. The paper concludes with a discussion of current research and glimpse of future work.


Author(s):  
Thiago Pedro Donadon Homem ◽  
Danilo Hernani Perico ◽  
Paulo Eduardo Santos ◽  
Anna Helena Reali Costa ◽  
Reinaldo Augusto da Costa Bianchi

Author(s):  
Chris Barrett

While Chapters 1–3 examine early modern texts that take the work of spatial representation as an opportunity to consider the labor, dangers, and possibilities of representation, the Conclusion (which takes its title from remarks by Richard Hakluyt in describing how as a child he became fascinated by maps) considers three contemporary objects: a mug, a Mapparium, and recent revisions to the famous boot-shaped silhouette of Louisiana. Each of these objects represents a global or regional area in some novel way: foregrounding their artifice in order to exploit the same cartographic anxieties of representation articulated in works by Spenser, Drayton, and Milton, these objects suggest that the contemporary moment’s efforts to reimagine the space of the world in rhetorically affecting if overtly non-mimetic ways reflects the triumph of an early modern poetics of anxiety, a poetics that might be generative still, in the Anthropocene.


2021 ◽  
pp. 191-212
Author(s):  
M. A. Dubova ◽  
N. A. Larina

The question of ways of creating a spatial continuum in the early stories of I. A. Bunin “On the wrong side”, “On the farm” and “On the Donets”, united by a single principle of nomination and included in the first book of the writer’s prose “To the end of the world” (1897) is considered in the article. The semantics of the title actualizes the spatial component of the author’s linguistic picture of the world, which determined the path of linguistic and stylistic analysis of the linguistic material of stories. The authors pay special attention to the means of lexical representation of space as one of the basic linguo-cognitive categories. The novelty of the research lies in the fact that the language material has been identified, systematized and described, which makes it possible to determine the individual author's characteristics in the creation of the spatial continuum of I. A. Bunin’s early stories. The relevance of the study is due to the appeal to the problems of cognitive linguistics. On the basis of statistical, descriptive and linguo-cognitive methods of analysis, the authors identify and describe the means of lexical representation of the spatial model created in the stories of I. A. Bunin, which is characterized by a clear structuredness and individuality of the author’s approach. In the course of the study, the authors come to conclusions that make it possible to characterize the features of the construction of space in the early stories of the writer, taking into account the individual characteristics of the author's world modeling, and also to analyze the linguistic parameters of the idiostyle of I. A. Bunin.


Sign in / Sign up

Export Citation Format

Share Document