Matching Items (5)
Filtering by
- All Subjects: Commonsense reasoning
- All Subjects: robotics
Description
Turing test has been a benchmark scale for measuring the human level intelligence in computers since it was proposed by Alan Turing in 1950. However, for last 60 years, the applications such as ELIZA, PARRY, Cleverbot and Eugene Goostman, that claimed to pass the test. These applications are either based on tricks to fool humans on a textual chat based test or there has been a disagreement between AI communities on them passing the test. This has led to the school of thought that it might not be the ideal test for predicting the human level intelligence in machines.
Consequently, the Winograd Schema Challenge has been suggested as an alternative to the Turing test. As opposed to deciding the intelligent behavior with the help of chat servers, like it was done in the Turing test, the Winograd Schema Challenge is a question answering test. It consists of sentence and question pairs such that the answer to the question depends on the resolution of a definite pronoun or adjective in the sentence. The answers are fairly intuitive for humans but they are difficult for machines because it requires some sort of background or commonsense knowledge about the sentence.
In this thesis, I propose a novel technique to solve the Winograd Schema Challenge. The technique has three basic modules at its disposal, namely, a Semantic Parser that parses the English text (both sentences and questions) into a formal representation, an Automatic Background Knowledge Extractor that extracts the Background Knowledge pertaining to the given Winograd sentence, and an Answer Set Programming Reasoning Engine that reasons on the given Winograd sentence and the corresponding Background Knowledge. The applicability of the technique is illustrated by solving a subset of Winograd Schema Challenge pertaining to a certain type of Background Knowledge. The technique is evaluated on the subset and a notable accuracy is achieved.
Consequently, the Winograd Schema Challenge has been suggested as an alternative to the Turing test. As opposed to deciding the intelligent behavior with the help of chat servers, like it was done in the Turing test, the Winograd Schema Challenge is a question answering test. It consists of sentence and question pairs such that the answer to the question depends on the resolution of a definite pronoun or adjective in the sentence. The answers are fairly intuitive for humans but they are difficult for machines because it requires some sort of background or commonsense knowledge about the sentence.
In this thesis, I propose a novel technique to solve the Winograd Schema Challenge. The technique has three basic modules at its disposal, namely, a Semantic Parser that parses the English text (both sentences and questions) into a formal representation, an Automatic Background Knowledge Extractor that extracts the Background Knowledge pertaining to the given Winograd sentence, and an Answer Set Programming Reasoning Engine that reasons on the given Winograd sentence and the corresponding Background Knowledge. The applicability of the technique is illustrated by solving a subset of Winograd Schema Challenge pertaining to a certain type of Background Knowledge. The technique is evaluated on the subset and a notable accuracy is achieved.
ContributorsSharma, Arpita (Author) / Baral, Chita (Thesis advisor) / Lee, Joohyung (Committee member) / Pon-Barry, Heather (Committee member) / Arizona State University (Publisher)
Created2014
Description
Image Understanding is a long-established discipline in computer vision, which encompasses a body of advanced image processing techniques, that are used to locate (“where”), characterize and recognize (“what”) objects, regions, and their attributes in the image. However, the notion of “understanding” (and the goal of artificial intelligent machines) goes beyond factual recall of the recognized components and includes reasoning and thinking beyond what can be seen (or perceived). Understanding is often evaluated by asking questions of increasing difficulty. Thus, the expected functionalities of an intelligent Image Understanding system can be expressed in terms of the functionalities that are required to answer questions about an image. Answering questions about images require primarily three components: Image Understanding, question (natural language) understanding, and reasoning based on knowledge. Any question, asking beyond what can be directly seen, requires modeling of commonsense (or background/ontological/factual) knowledge and reasoning.
Knowledge and reasoning have seen scarce use in image understanding applications. In this thesis, we demonstrate the utilities of incorporating background knowledge and using explicit reasoning in image understanding applications. We first present a comprehensive survey of the previous work that utilized background knowledge and reasoning in understanding images. This survey outlines the limited use of commonsense knowledge in high-level applications. We then present a set of vision and reasoning-based methods to solve several applications and show that these approaches benefit in terms of accuracy and interpretability from the explicit use of knowledge and reasoning. We propose novel knowledge representations of image, knowledge acquisition methods, and a new implementation of an efficient probabilistic logical reasoning engine that can utilize publicly available commonsense knowledge to solve applications such as visual question answering, image puzzles. Additionally, we identify the need for new datasets that explicitly require external commonsense knowledge to solve. We propose the new task of Image Riddles, which requires a combination of vision, and reasoning based on ontological knowledge; and we collect a sufficiently large dataset to serve as an ideal testbed for vision and reasoning research. Lastly, we propose end-to-end deep architectures that can combine vision, knowledge and reasoning modules together and achieve large performance boosts over state-of-the-art methods.
Knowledge and reasoning have seen scarce use in image understanding applications. In this thesis, we demonstrate the utilities of incorporating background knowledge and using explicit reasoning in image understanding applications. We first present a comprehensive survey of the previous work that utilized background knowledge and reasoning in understanding images. This survey outlines the limited use of commonsense knowledge in high-level applications. We then present a set of vision and reasoning-based methods to solve several applications and show that these approaches benefit in terms of accuracy and interpretability from the explicit use of knowledge and reasoning. We propose novel knowledge representations of image, knowledge acquisition methods, and a new implementation of an efficient probabilistic logical reasoning engine that can utilize publicly available commonsense knowledge to solve applications such as visual question answering, image puzzles. Additionally, we identify the need for new datasets that explicitly require external commonsense knowledge to solve. We propose the new task of Image Riddles, which requires a combination of vision, and reasoning based on ontological knowledge; and we collect a sufficiently large dataset to serve as an ideal testbed for vision and reasoning research. Lastly, we propose end-to-end deep architectures that can combine vision, knowledge and reasoning modules together and achieve large performance boosts over state-of-the-art methods.
ContributorsAditya, Somak (Author) / Baral, Chitta (Thesis advisor) / Yang, Yezhou (Thesis advisor) / Aloimonos, Yiannis (Committee member) / Lee, Joohyung (Committee member) / Li, Baoxin (Committee member) / Arizona State University (Publisher)
Created2018
Description
Goal specification is an important aspect of designing autonomous agents. A goal does not only refer to the set of states for the agent to reach. A goal also defines restrictions on the paths the agent should follow. Temporal logics are widely used in goal specification. However, they lack the ability to represent goals in a non-deterministic domain, goals that change non-monotonically, and goals with preferences. This dissertation defines new goal specification languages by extending temporal logics to address these issues. First considered is the goal specification in non-deterministic domains, in which an agent following a policy leads to a set of paths. A logic is proposed to distinguish paths of the agent from all paths in the domain. In addition, to address the need of comparing policies for finding the best ones, a language capable of quantifying over policies is proposed. As policy structures of agents play an important role in goal specification, languages are also defined by considering different policy structures. Besides, after an agent is given an initial goal, the agent may change its expectations or the domain may change, thus goals that are previously specified may need to be further updated, revised, partially retracted, or even completely changed. Non-monotonic goal specification languages that can make these changes in an elaboration tolerant manner are needed. Two languages that rely on labeling sub-formulas and connecting multiple rules are developed to address non-monotonicity in goal specification. Also, agents may have preferential relations among sub-goals, and the preferential relations may change as agents achieve other sub-goals. By nesting a comparison operator with other temporal operators, a language with dynamic preferences is proposed. Various goals that cannot be expressed in other languages are expressed in the proposed languages. Finally, plans are given for some goals specified in the proposed languages.
ContributorsZhao, Jicheng (Author) / Baral, Chitta (Thesis advisor) / Kambhampati, Subbarao (Committee member) / Lee, Joohyung (Committee member) / Lifschitz, Vladimir (Committee member) / Liu, Huan (Committee member) / Arizona State University (Publisher)
Created2010
Description
Reasoning with commonsense knowledge is an integral component of human behavior. It is due to this capability that people know that a weak person may not be able to lift someone. It has been a long standing goal of the Artificial Intelligence community to simulate such commonsense reasoning abilities in machines. Over the years, many advances have been made and various challenges have been proposed to test their abilities. The Winograd Schema Challenge (WSC) is one such Natural Language Understanding (NLU) task which was also proposed as an alternative to the Turing Test. It is made up of textual question answering problems which require resolution of a pronoun to its correct antecedent.
In this thesis, two approaches of developing NLU systems to solve the Winograd Schema Challenge are demonstrated. To this end, a semantic parser is presented, various kinds of commonsense knowledge are identified, techniques to extract commonsense knowledge are developed and two commonsense reasoning algorithms are presented. The usefulness of the developed tools and techniques is shown by applying them to solve the challenge.
In this thesis, two approaches of developing NLU systems to solve the Winograd Schema Challenge are demonstrated. To this end, a semantic parser is presented, various kinds of commonsense knowledge are identified, techniques to extract commonsense knowledge are developed and two commonsense reasoning algorithms are presented. The usefulness of the developed tools and techniques is shown by applying them to solve the challenge.
ContributorsSharma, Arpita (Author) / Baral, Chitta (Thesis advisor) / Lee, Joohyung (Committee member) / Papotti, Paolo (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2019
Description
As robots become mechanically more capable, they are going to be more and more integrated into our daily lives. Over time, human’s expectation of what the robot capabilities are is getting higher. Therefore, it can be conjectured that often robots will not act as human commanders intended them to do. That is, the users of the robots may have a different point of view from the one the robots do.
The first part of this dissertation covers methods that resolve some instances of this mismatch when the mission requirements are expressed in Linear Temporal Logic (LTL) for handling coverage, sequencing, conditions and avoidance. That is, the following general questions are addressed:
* What cause of the given mission is unrealizable?
* Is there any other feasible mission that is close to the given one?
In order to answer these questions, the LTL Revision Problem is applied and it is formulated as a graph search problem. It is shown that in general the problem is NP-Complete. Hence, it is proved that the heuristic algorihtm has 2-approximation bound in some cases. This problem, then, is extended to two different versions: one is for the weighted transition system and another is for the specification under quantitative preference. Next, a follow up question is addressed:
* How can an LTL specified mission be scaled up to multiple robots operating in confined environments?
The Cooperative Multi-agent Planning Problem is addressed by borrowing a technique from cooperative pathfinding problems in discrete grid environments. Since centralized planning for multi-robot systems is computationally challenging and easily results in state space explosion, a distributed planning approach is provided through agent coupling and de-coupling.
In addition, in order to make such robot missions work in the real world, robots should take actions in the continuous physical world. Hence, in the second part of this thesis, the resulting motion planning problems is addressed for non-holonomic robots.
That is, it is devoted to autonomous vehicles’ motion planning in challenging environments such as rural, semi-structured roads. This planning problem is solved with an on-the-fly hierarchical approach, using a pre-computed lattice planner. It is also proved that the proposed algorithm guarantees resolution-completeness in such demanding environments. Finally, possible extensions are discussed.
The first part of this dissertation covers methods that resolve some instances of this mismatch when the mission requirements are expressed in Linear Temporal Logic (LTL) for handling coverage, sequencing, conditions and avoidance. That is, the following general questions are addressed:
* What cause of the given mission is unrealizable?
* Is there any other feasible mission that is close to the given one?
In order to answer these questions, the LTL Revision Problem is applied and it is formulated as a graph search problem. It is shown that in general the problem is NP-Complete. Hence, it is proved that the heuristic algorihtm has 2-approximation bound in some cases. This problem, then, is extended to two different versions: one is for the weighted transition system and another is for the specification under quantitative preference. Next, a follow up question is addressed:
* How can an LTL specified mission be scaled up to multiple robots operating in confined environments?
The Cooperative Multi-agent Planning Problem is addressed by borrowing a technique from cooperative pathfinding problems in discrete grid environments. Since centralized planning for multi-robot systems is computationally challenging and easily results in state space explosion, a distributed planning approach is provided through agent coupling and de-coupling.
In addition, in order to make such robot missions work in the real world, robots should take actions in the continuous physical world. Hence, in the second part of this thesis, the resulting motion planning problems is addressed for non-holonomic robots.
That is, it is devoted to autonomous vehicles’ motion planning in challenging environments such as rural, semi-structured roads. This planning problem is solved with an on-the-fly hierarchical approach, using a pre-computed lattice planner. It is also proved that the proposed algorithm guarantees resolution-completeness in such demanding environments. Finally, possible extensions are discussed.
ContributorsKim, Kangjin (Author) / Fainekos, Georgios (Thesis advisor) / Baral, Chitta (Committee member) / Lee, Joohyung (Committee member) / Berman, Spring (Committee member) / Arizona State University (Publisher)
Created2019