| 1. |
- Benferhat, Salem, et al.
(author)
-
Belief functions and default reasoning
- 2000
-
In: Artificial Intelligence. - 0004-3702 .- 1872-7921. ; 122:1-2, s. 1-69
-
Journal article (peer-reviewed)abstract
- We present a new approach to deal with default information based on the theory of belief functions. Our semantic structures, inspired by Adams' epsilon semantics, are epsilon-belief assignments, where mass values are either close to 0 or close to 1. In the first part of this paper, we show that these structures can be used to give a uniform semantics to several popular non-monotonic systems, including Kraus, Lehmann and Magidor's system P, Pearl's system Z, Brewka's preferred sub-theories, Geffner's conditional entailment, Pinkas' penalty logic, possibilistic logic, and the lexicographic approach. In the second part, we use epsilon-belief assignments to build a new system, called LCD, and we show that this system correctly addresses the well-known problems of specificity, irrelevance, blocking of inheritance, ambiguity, and redundancy
|
|
| 2. |
- Bloch, I., et al.
(author)
-
On the representation of fuzzy spatial relations in robot maps
- 2003
-
In: Intelligent systems for information processing. - Amsterdam : Elsevier. - 0444513795 ; , s. 47-57
-
Conference paper (peer-reviewed)abstract
- Spatial directional relations, like "north of," play an important role in the modeling of the environment by an autonomous robot. We propose an approach to represent spatial relations grounded in fuzzy set theory and fuzzy mathematical morphology. We show how this approach can be applied to robot maps, and suggest that these relations can be used for self-localization and for reasoning about the environment. We illustrate our approach on real data collected by a mobile robot in an office environment
|
|
| 3. |
- Bloch, Isabelle, et al.
(author)
-
Why robots should use fuzzy mathematical morphology
- 2002
-
Conference paper (peer-reviewed)abstract
- Mobile robots must represent and reason about spatial knowledge acquired from sensor data which are inherently approximate and uncertain. While techniques based on fuzzy sets are increasingly used in this domain, the use of these techniques often rests on intuitive grounds. In this paper, we show that fuzzy mathematical morphology, a theory often used in image processing but mostly ignored in the robotic tradition, can provide a well grounded approach to the treatment of imprecise spatial knowledge in robotics
|
|
| 4. |
- Broxvall, Mathias, et al.
(author)
-
Have another look on failures and recovery planning in perceptual anchoring
- 2004
-
Conference paper (peer-reviewed)abstract
- An important requirement for autonomous systems is the ability to detect and recover from exceptional situations such as failures in observations. In this paper we demonstrate how techniques for planning with sensing under uncertainty can play a major role in solving the problem of recovering from such situations. In this first step we concentrate on failures in perceptual anchoring, that is how to connect a symbol representing an object to the percepts of that object. We provide a classification of failures and present planning-based methods for recovering from them. We illustrate our approach by showing tests run on a mobile robot equipped with a color camera.
|
|
| 5. |
- Broxvall, Mathias, et al.
(author)
-
Steps toward detecting and recovering from perceptual failures
- 2004
-
In: Proceedings of the 8th international conference on intelligent autonomous systems. ; , s. 793-800
-
Conference paper (peer-reviewed)abstract
- An important requirement for autonomous systems is the ability to detect and recover from exceptional situations such as failures in observations. In this paper we investigate how traditional AI planning techniques can be used to reason about observations and to recover from these situations. In this first step we concentrate on failures in perceptual anchoring. We illustrate our approach by showing experiments run on a mobile robot equipped with a color camera.
|
|
| 6. |
- Buschka, Pär, et al.
(author)
-
A virtual sensor for room detection
- 2002
-
In: Proceedings of the IEEE/RSJ international conference on intelligent robots and systems. - 0780373987 ; , s. 637-642
-
Conference paper (peer-reviewed)abstract
- Indoor environments typically consist of sets of connected room-like spaces. We present a local technique that uses range data to detect these spaces during navigation. Our technique includes two parts: segmentation, which isolates room-like spaces and detects when the robot has entered a new one; and feature extraction, which associates each space with a set of geometric features useful for navigation or recognition. Many such features can be considered: here we propose a new method to compute width and length of a rectangular room in a way which is largely invariant with respect to the configuration of the furniture. We report experimental results that show the performance of our technique, and hint at a possible use of this technique for coarse localization on a topological map
|
|
| 7. |
- Buschka, Pär, et al.
(author)
-
Fuzzy landmark-based localization for a legged robot
- 2000
-
In: Proceedings, 2000 IEEE/RSJ International Conference on Intelligent Robots and Systems. - 0780363485 ; , s. 1205-1210
-
Conference paper (peer-reviewed)abstract
- We describe a new technique for landmark-based self-localization which is suitable for robots with poor odometry. This technique uses fuzzy logic to account for errors and imprecision in visual recognition, and for extreme uncertainty in the estimate of the robot's motion. It only requires an approximate model of the sensor system and a qualitative estimate of the robot's displacement, and it has a moderate computational cost. We show examples of use of our technique on a Sony AIBO legged robot in the RoboCup domain.
|
|
| 8. |
- Buschka, Pär, et al.
(author)
-
Room detection for topology-based map building
- 2002
-
In: Proceedings of the 2nd Swedish workshop on autonomous robots. ; , s. 39-44
-
Conference paper (pop. science, debate, etc.)abstract
- Indoor environments typically consist of sets of connected room-like spaces. We present a local technique that uses range data to detect these spaces during navigation. This is done by a segmentation which isolates room-like spaces and detects when the robot has entered a new one. These spaces can be seen as nodes in a topological map and we show how to incrementally build such a map. We also report experimental results that show the performance of our technique
|
|
| 9. |
- Buschka, Pär, et al.
(author)
-
Some notes on the use of hybrid maps for mobile robots
- 2004
-
In: Proceedings of the 8th international conference on intelligent autonomous systems. ; , s. 547-556
-
Conference paper (peer-reviewed)abstract
- Hybrid maps are quickly becoming popular in the field of mobile robotics. There is, however, little understanding of the general principles that can be used to combine different maps into a hybrid one, and to make these maps to cooperate. In this note, we propose a definition and a classification of hybrid maps, and discuss the synergies that can make a hybrid map something more than the sum of its parts. We illustrate these points with experimental results obtained on a metric-topological map.
|
|
| 10. |
- Canovas, Juan-Pedro, et al.
(author)
-
Cooperative object localization using fuzzy logic
- 2003
-
In: Proceedings of the IEEE international conference on methods and models in automation and robotics. ; , s. 773-778
-
Conference paper (peer-reviewed)abstract
- Cooperative localization of objects is an important challenge in multi-robot systems. We propose a new approach to cooperative object localization by a group of communicating robots. In our approach we see each robot as an expert which provides unreliable information about the location of objects. The information provided by different robots is combined using fuzzy logic techniques, in order to reach agreement between the robots. This contrasts with current techniques, which average the information provided by different robots, and can incur well-known problems when information is unreliable. We have tested our technique on a team of Sony AIBO robots in the RoboCup domain. We present experimental results obtained by sharing information about the location of the ball
|
|
