1. |
- Saifullah, Mohammad, 1973-
(författare)
-
Biologically-Based Interactive Neural Network Models for Visual Attention and Object Recognition
- 2012
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The main focus of this thesis is to develop biologically-based computational models for object recognition. A series of models for attention and object recognition were developed in the order of increasing functionality and complexity. These models are based on information processing in the primate brain, and specially inspired from the theory of visual information processing along the two parallel processing pathways of the primate visual cortex. To capture the true essence of incremental, constraint satisfaction style processing in the visual system, interactive neural networks were used for implementing our models. Results from eye-tracking studies on the relevant visual tasks, as well as our hypothesis regarding the information processing in the primate visual system, were implemented in the models and tested with simulations.As a first step, a model based on the ventral pathway was developed to recognize single objects. Through systematic testing, structural and algorithmic parameters of these models were fine tuned for performing their task optimally. In the second step, the model was extended by considering the dorsal pathway, which enables simulation of visual attention as an emergent phenomenon. The extended model was then investigated for visual search tasks. In the last step, we focussed on occluded and overlapped object recognition. A couple of eye-tracking studies were conducted in this regard and on the basis of the results we made some hypotheses regarding information processing in the primate visual system. The models were further advanced on the lines of the presented hypothesis, and simulated on the tasks of occluded and overlapped object recognition.On the basis of the results and analysis of our simulations we have further found that the generalization performance of interactive hierarchical networks improves with the addition of a small amount of Hebbian learning to an otherwise pure error-driven learning. We also concluded that the size of the receptive fields in our networks is an important parameter for the generalization task and depends on the object of interest in the image. Our results show that networks using hard coded feature extraction perform better than the networks that use Hebbian learning for developing feature detectors. We have successfully demonstrated the emergence of visual attention within an interactive network and also the role of context in the search task. Simulation results with occluded and overlapped objects support our extended interactive processing approach, which is a combination of the interactive and top-down approach, to the segmentation-recognition issue. Furthermore, the simulation behavior of our models is in line with known human behavior for similar tasks.In general, the work in this thesis will improve the understanding and performance of biologically-based interactive networks for object recognition and provide a biologically-plausible solution to recognition of occluded and overlapped objects. Moreover, our models provide some suggestions for the underlying neural mechanism and strategies behind biological object recognition.
|
|
2. |
- Saifullah, Mohammad, 1973-
(författare)
-
Exploring Biologically-Inspired Interactive Networks for Object Recognition
- 2011
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- This thesis deals with biologically-inspired interactive neural networks for the task of object recognition. Such networks offer an interesting alternative approach to traditional image processing techniques. Although the networks are very powerful classification tools, they are difficult to handle due to their bidirectional interactivity. It is one of the main reasons why these networks do not perform the task of generalization to novel objects well. Generalization is a very important property for any object recognition system, as it is impractical for a system to learn all instances of an object class before classifying. In this thesis, we have investigated the working of an interactive neural network by fine tuning different structural and algorithmic parameters. The performance of the networks was evaluated by analyzing the generalization ability of the trained network to novel objects. Furthermore, the interactivity of the network was utilized to simulate focus of attention during object classification. Selective attention is an important visual mechanism for object recognition and provides an efficient way of using the limited computational resources of the human visual system. Unlike most previous work in the field of image processing, in this thesis attention is considered as an integral part of object processing. Attention focus, in this work, is computed within the same network and in parallel with object recognition.As a first step, a study into the efficacy of Hebbian learning as a feature extraction method was conducted. In a second study, the receptive field size in the network, which controls the size of the extracted features as well as the number of layers in the network, was varied and analyzed to find its effect on generalization. In a continuation study, a comparison was made between learnt (Hebbian learning) and hard coded feature detectors. In the last study, attention focus was computed using interaction between bottom-up and top-down activation flow with the aim to handle multiple objects in the visual scene. On the basis of the results and analysis of our simulations we have found that the generalization performance of the bidirectional hierarchical network improves with the addition of a small amount of Hebbian learning to an otherwise error-driven learning. We also conclude that the optimal size of the receptive fields in our network depends on the object of interest in the image. Moreover, each receptive field must contain some part of the object in the input image. We have also found that networks using hard coded feature extraction perform better than the networks that use Hebbian learning for developing feature detectors. In the last study, we have successfully demonstrated the emergence of visual attention within an interactive network that handles more than one object in the input field. Our simulations demonstrate how bidirectional interactivity directs attention focus towards the required object by using both bottom-up and top-down effects.In general, the findings of this thesis will increase understanding about the working of biologically-inspired interactive networks. Specifically, the studied effects of the structural and algorithmic parameters that are critical for the generalization property will help develop these and similar networks and lead to improved performance on object recognition tasks. The results from the attention simulations can be used to increase the ability of networks to deal with multiple objects in an efficient and effective manner.
|
|
3. |
- Fonooni, Benjamin, 1980-
(författare)
-
Cognitive Interactive Robot Learning
- 2014
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Building general purpose autonomous robots that suit a wide range of user-specified applications, requires a leap from today's task-specific machines to more flexible and general ones. To achieve this goal, one should move from traditional preprogrammed robots to learning robots that easily can acquire new skills. Learning from Demonstration (LfD) and Imitation Learning (IL), in which the robot learns by observing a human or robot tutor, are among the most popular learning techniques. Showing the robot how to perform a task is often more natural and intuitive than figuring out how to modify a complex control program. However, teaching robots new skills such that they can reproduce the acquired skills under any circumstances, on the right time and in an appropriate way, require good understanding of all challenges in the field. Studies of imitation learning in humans and animals show that several cognitive abilities are engaged to learn new skills correctly. The most remarkable ones are the ability to direct attention to important aspects of demonstrations, and adapting observed actions to the agents own body. Moreover, a clear understanding of the demonstrator's intentions and an ability to generalize to new situations are essential. Once learning is accomplished, various stimuli may trigger the cognitive system to execute new skills that have become part of the robot's repertoire. The goal of this thesis is to develop methods for learning from demonstration that mainly focus on understanding the tutor's intentions, and recognizing which elements of a demonstration need the robot's attention. An architecture containing required cognitive functions for learning and reproduction of high-level aspects of demonstrations is proposed. Several learning methods for directing the robot's attention and identifying relevant information are introduced. The architecture integrates motor actions with concepts, objects and environmental states to ensure correct reproduction of skills. Another major contribution of this thesis is methods to resolve ambiguities in demonstrations where the tutor's intentions are not clearly expressed and several demonstrations are required to infer intentions correctly. The provided solution is inspired by human memory models and priming mechanisms that give the robot clues that increase the probability of inferring intentions correctly. In addition to robot learning, the developed techniques are applied to a shared control system based on visual servoing guided behaviors and priming mechanisms. The architecture and learning methods are applied and evaluated in several real world scenarios that require clear understanding of intentions in the demonstrations. Finally, the developed learning methods are compared, and conditions where each of them has better applicability are discussed.
|
|
4. |
- Rosén, Julia
(författare)
-
What did you expect? : A human-centered approach to investigating and reducing the social robot expectation gap
- 2024
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- We live in a complex world where we proactively plan and execute various behaviors by forming expectations in real time. Expectations are beliefs regarding the future state of affairs and they play an integral part of our perception, attention, and behavior. Over time, our expectations become more accurate as we interact with the world and others around us. People interact socially with other people by inferring others' purposes, intentions, preferences, beliefs, emotions, thoughts, and goals. Similar inferences may occur when we interact with social robots. With anthropomorphic design, these robots are designed to mimic people physically and behaviorally. As a result, users predominantly infer agency in social robots, often leading to mismatched expectations of the robots' capabilities, which ultimately influences the user experience. In this thesis, the role and relevance of users' expectations in first-hand social human-robot interaction (sHRI) was investigated. There are two major findings. First, in order to study expectations in sHRI, the social robot expectation gap evaluation framework was developed. This framework supports the systematic study and evaluation of expectations over time, considering the unique context where the interaction is unfolding. Use of the framework can inform sHRI researchers and designers on how to manage users’ expectations, not only in the design, but also during evaluation and presentation of social robots. Expectations can be managed by identifying what kinds of expectations users have and aligning these through design and dissemination which ultimately creates more transparent and successful interactions and collaborations. The framework is a tool for achieving this goal. Second, results show that previous experience has a strong impact on users’ expectations. People have different expectations of social robots and view social robots as both human-like and as machines. Expectations of social robots can vary according to the source of the expectation, with those who had previous direct experiences of robots having different expectations than those who relied on indirect experiences to generate expectations. One consequence of these results is that expectations can be a confounding variable in sHRI research. Previous experience with social robots can prime users in future interactions with social robots. These findings highlight the unique experiences users have, even when faced with the same robot. Users' expectations and how they change over time shapes the users’ individual needs and preferences and should therefore be considered in the interpretation of sHRI. In doing so, the social robot expectation gap can be reduced.
|
|