Matching Items (58)
Description
What if there is a way to integrate prosthetics seamlessly with the human body and robots could help improve the lives of children with disabilities? With physical human-robot interaction being seen in multiple aspects of life, including industry, medical, and social, how these robots are interacting with human becomes even more important. Therefore, how smoothly the robot can interact with a person will determine how safe and efficient this relationship will be. This thesis investigates adaptive control method that allows a robot to adapt to the human's actions based on the interaction force. Allowing the relationship to become more effortless and less strained when the robot has a different goal than the human, as seen in Game Theory, using multiple techniques that adapts the system. Few applications this could be used for include robots in physical therapy, manufacturing robots that can adapt to a changing environment, and robots teaching people something new like dancing or learning how to walk after surgery.
The experience gained is the understanding of how a cost function of a system works, including the tracking error, speed of the system, the robot’s effort, and the human’s effort. Also, this two-agent system, results into a two-agent adaptive impedance model with an input for each agent of the system. This leads to a nontraditional linear quadratic regulator (LQR), that must be separated and then added together. Thus, creating a traditional LQR. This new experience can be used in the future to help build better safety protocols on manufacturing robots. In the future the knowledge learned from this research could be used to develop technologies for a robot to allow to adapt to help counteract human error.
The experience gained is the understanding of how a cost function of a system works, including the tracking error, speed of the system, the robot’s effort, and the human’s effort. Also, this two-agent system, results into a two-agent adaptive impedance model with an input for each agent of the system. This leads to a nontraditional linear quadratic regulator (LQR), that must be separated and then added together. Thus, creating a traditional LQR. This new experience can be used in the future to help build better safety protocols on manufacturing robots. In the future the knowledge learned from this research could be used to develop technologies for a robot to allow to adapt to help counteract human error.
ContributorsBell, Rebecca C (Author) / Zhang, Wenlong (Thesis advisor) / Chiou, Erin (Committee member) / Aukes, Daniel (Committee member) / Arizona State University (Publisher)
Created2019
Description
Reinforcement learning (RL) is a powerful methodology for teaching autonomous agents complex behaviors and skills. A critical component in most RL algorithms is the reward function -- a mathematical function that provides numerical estimates for desirable and undesirable states. Typically, the reward function must be hand-designed by a human expert and, as a result, the scope of a robot's autonomy and ability to safely explore and learn in new and unforeseen environments is constrained by the specifics of the designed reward function. In this thesis, I design and implement a stateful collision anticipation model with powerful predictive capability based upon my research of sequential data modeling and modern recurrent neural networks. I also develop deep reinforcement learning methods whose rewards are generated by self-supervised training and intrinsic signals. The main objective is to work towards the development of resilient robots that can learn to anticipate and avoid damaging interactions by combining visual and proprioceptive cues from internal sensors. The introduced solutions are inspired by pain pathways in humans and animals, because such pathways are known to guide decision-making processes and promote self-preservation. A new "robot dodge ball' benchmark is introduced in order to test the validity of the developed algorithms in dynamic environments.
ContributorsRichardson, Trevor W (Author) / Ben Amor, Heni (Thesis advisor) / Yang, Yezhou (Committee member) / Srivastava, Siddharth (Committee member) / Arizona State University (Publisher)
Created2018
Description
In this thesis, a new approach to learning-based planning is presented where critical regions of an environment with low probability measure are learned from a given set of motion plans. Critical regions are learned using convolutional neural networks (CNN) to improve sampling processes for motion planning (MP).
In addition to an identification network, a new sampling-based motion planner, Learn and Link, is introduced. This planner leverages critical regions to overcome the limitations of uniform sampling while still maintaining guarantees of correctness inherent to sampling-based algorithms. Learn and Link is evaluated against planners from the Open Motion Planning Library (OMPL) on an extensive suite of challenging navigation planning problems. This work shows that critical areas of an environment are learnable, and can be used by Learn and Link to solve MP problems with far less planning time than existing sampling-based planners.
In addition to an identification network, a new sampling-based motion planner, Learn and Link, is introduced. This planner leverages critical regions to overcome the limitations of uniform sampling while still maintaining guarantees of correctness inherent to sampling-based algorithms. Learn and Link is evaluated against planners from the Open Motion Planning Library (OMPL) on an extensive suite of challenging navigation planning problems. This work shows that critical areas of an environment are learnable, and can be used by Learn and Link to solve MP problems with far less planning time than existing sampling-based planners.
ContributorsMolina, Daniel, M.S (Author) / Srivastava, Siddharth (Thesis advisor) / Li, Baoxin (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2019
Description
Knowledge Representation (KR) is one of the prominent approaches to Artificial Intelligence (AI) that is concerned with representing knowledge in a form that computer systems can utilize to solve complex problems. Answer Set Programming (ASP), based on the stable model semantics, is a widely-used KR framework that facilitates elegant and efficient representations for many problem domains that require complex reasoning.
However, while ASP is effective on deterministic problem domains, it is not suitable for applications involving quantitative uncertainty, for example, those that require probabilistic reasoning. Furthermore, it is hard to utilize information that can be statistically induced from data with ASP problem modeling.
This dissertation presents the language LP^MLN, which is a probabilistic extension of the stable model semantics with the concept of weighted rules, inspired by Markov Logic. An LP^MLN program defines a probability distribution over "soft" stable models, which may not satisfy all rules, but the more rules with the bigger weights they satisfy, the bigger their probabilities. LP^MLN takes advantage of both ASP and Markov Logic in a single framework, allowing representation of problems that require both logical and probabilistic reasoning in an intuitive and elaboration tolerant way.
This dissertation establishes formal relations between LP^MLN and several other formalisms, discusses inference and weight learning algorithms under LP^MLN, and presents systems implementing the algorithms. LP^MLN systems can be used to compute other languages translatable into LP^MLN.
The advantage of LP^MLN for probabilistic reasoning is illustrated by a probabilistic extension of the action language BC+, called pBC+, defined as a high-level notation of LP^MLN for describing transition systems. Various probabilistic reasoning about transition systems, especially probabilistic diagnosis, can be modeled in pBC+ and computed using LP^MLN systems. pBC+ is further extended with the notion of utility, through a decision-theoretic extension of LP^MLN, and related with Markov Decision Process (MDP) in terms of policy optimization problems. pBC+ can be used to represent (PO)MDP in a succinct and elaboration tolerant way, which enables planning with (PO)MDP algorithms in action domains whose description requires rich KR constructs, such as recursive definitions and indirect effects of actions.
However, while ASP is effective on deterministic problem domains, it is not suitable for applications involving quantitative uncertainty, for example, those that require probabilistic reasoning. Furthermore, it is hard to utilize information that can be statistically induced from data with ASP problem modeling.
This dissertation presents the language LP^MLN, which is a probabilistic extension of the stable model semantics with the concept of weighted rules, inspired by Markov Logic. An LP^MLN program defines a probability distribution over "soft" stable models, which may not satisfy all rules, but the more rules with the bigger weights they satisfy, the bigger their probabilities. LP^MLN takes advantage of both ASP and Markov Logic in a single framework, allowing representation of problems that require both logical and probabilistic reasoning in an intuitive and elaboration tolerant way.
This dissertation establishes formal relations between LP^MLN and several other formalisms, discusses inference and weight learning algorithms under LP^MLN, and presents systems implementing the algorithms. LP^MLN systems can be used to compute other languages translatable into LP^MLN.
The advantage of LP^MLN for probabilistic reasoning is illustrated by a probabilistic extension of the action language BC+, called pBC+, defined as a high-level notation of LP^MLN for describing transition systems. Various probabilistic reasoning about transition systems, especially probabilistic diagnosis, can be modeled in pBC+ and computed using LP^MLN systems. pBC+ is further extended with the notion of utility, through a decision-theoretic extension of LP^MLN, and related with Markov Decision Process (MDP) in terms of policy optimization problems. pBC+ can be used to represent (PO)MDP in a succinct and elaboration tolerant way, which enables planning with (PO)MDP algorithms in action domains whose description requires rich KR constructs, such as recursive definitions and indirect effects of actions.
ContributorsWang, Yi (Author) / Lee, Joohyung (Thesis advisor) / Baral, Chitta (Committee member) / Kambhampati, Subbarao (Committee member) / Natarajan, Sriraam (Committee member) / Srivastava, Siddharth (Committee member) / Arizona State University (Publisher)
Created2019
Description
Recent advancements in external memory based neural networks have shown promise
in solving tasks that require precise storage and retrieval of past information. Re-
searchers have applied these models to a wide range of tasks that have algorithmic
properties but have not applied these models to real-world robotic tasks. In this
thesis, we present memory-augmented neural networks that synthesize robot navigation policies which a) encode long-term temporal dependencies b) make decisions in
partially observed environments and c) quantify the uncertainty inherent in the task.
We extract information about the temporal structure of a task via imitation learning
from human demonstration and evaluate the performance of the models on control
policies for a robot navigation task. Experiments are performed in partially observed
environments in both simulation and the real world
in solving tasks that require precise storage and retrieval of past information. Re-
searchers have applied these models to a wide range of tasks that have algorithmic
properties but have not applied these models to real-world robotic tasks. In this
thesis, we present memory-augmented neural networks that synthesize robot navigation policies which a) encode long-term temporal dependencies b) make decisions in
partially observed environments and c) quantify the uncertainty inherent in the task.
We extract information about the temporal structure of a task via imitation learning
from human demonstration and evaluate the performance of the models on control
policies for a robot navigation task. Experiments are performed in partially observed
environments in both simulation and the real world
ContributorsSrivatsav, Nambi (Author) / Ben Amor, Hani (Thesis advisor) / Srivastava, Siddharth (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2018
Description
In this article we present a low-cost force-sensing quadrupedal laminate robot platform. The robot has two degrees of freedom on each of four independent legs, allowing for a variety of motion trajectories to be created at each leg, thus creating a rich control space to explore on a relatively low-cost robot. This platform allows a user to research complex motion and gait analysis control questions, and use different concepts in computer science and control theory methods to permit it to walk. The motion trajectory of each leg has been modeled in Python. Critical design considerations are: the complexity of the laminate design, the rigidity of the materials of which the laminate is constructed, the accuracy of the transmission to control each leg, and the design of the force sensing legs.
ContributorsShuch, Benjamin David (Author) / Aukes, Daniel (Thesis director) / Sodemann, Angela (Committee member) / Engineering Programs (Contributor) / Barrett, The Honors College (Contributor)
Created2018-05
Description
This project is investigating the impact curvature, buckling, and anisotropy play when used passively to enhance jumping capability. In this paper we employ a curved structure to allow a rigid link to collapse preferentially in one direction when it encounters aerodynamic drag forces. A joint of this nature could be used for passively actuated jump gliding, where wings would collapse immediately on takeoff and passively redeploy during descent, allowing the jumping robot to extend its horizontal range via gliding. A passively actuated joint is simpler and more lightweight than active solutions, allowing for a lighter glider and higher jumps. To test this, several prototype collapsing gliding wings of different diameters were tested by dropping them from a consistent height above the ground and by launching them upwards and recording their initial velocity. A model was constructed in Python using the data gathered through the experiments and was tuned so that its outputs were as close as possible to the experimental results. As expected, increasing the wing diameter increased the total fall time, and increasing the payload mass decreased the total fall time. Orientation of the wings around the vertical axis of the glider relative to the direction of horizontal motion was also found to have an effect on the length of time between when the gliding platform was launched and when it made contact with the ground, with a configuration where the axis between the wings was parallel to the direction of motion granting added stability.
ContributorsLighthouse, Guston Heqian (Author) / Aukes, Daniel (Thesis director) / Sodemann, Angela (Committee member) / Engineering Programs (Contributor, Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
Classical planning is a field of Artificial Intelligence concerned with allowing autonomous agents to make reasonable decisions in complex environments. This work investigates
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.
ContributorsNakhleh, Julia Blair (Author) / Srivastava, Siddharth (Thesis director) / Fainekos, Georgios (Committee member) / Computer Science and Engineering Program (Contributor) / School of International Letters and Cultures (Contributor) / Barrett, The Honors College (Contributor)
Created2019-05
Description
The technological advances in the past few decades have made possible creation and consumption of digital visual content at an explosive rate. Consequently, there is a need for efficient quality monitoring systems to ensure minimal degradation of images and videos during various processing operations like compression, transmission, storage etc. Objective Image Quality Assessment (IQA) algorithms have been developed that predict quality scores which match well with human subjective quality assessment. However, a lot of research still remains to be done before IQA algorithms can be deployed in real world systems. Long runtimes for one frame of image is a major hurdle. Graphics Processing Units (GPUs), equipped with massive number of computational cores, provide an opportunity to accelerate IQA algorithms by performing computations in parallel. Indeed, General Purpose Graphics Processing Units (GPGPU) techniques have been applied to a few Full Reference IQA algorithms which fall under the. We present a GPGPU implementation of Blind Image Integrity Notator using DCT Statistics (BLIINDS-II), which falls under the No Reference IQA algorithm paradigm. We have been able to achieve a speedup of over 30x over the previous CPU version of this algorithm. We test our implementation using various distorted images from the CSIQ database and present the performance trends observed. We achieve a very consistent performance of around 9 milliseconds per distorted image, which made possible the execution of over 100 images per second (100 fps).
ContributorsYadav, Aman (Author) / Sohoni, Sohum (Thesis advisor) / Aukes, Daniel (Committee member) / Redkar, Sangram (Committee member) / Arizona State University (Publisher)
Created2016
Description
With the advent of GPGPU, many applications are being accelerated by using CUDA programing paradigm. We are able to achieve around 10x -100x speedups by simply porting the application on to the GPU and running the parallel chunk of code on its multi cored SIMT (Single instruction multiple thread) architecture. But for optimal performance it is necessary to make sure that all the GPU resources are efficiently used, and the latencies in the application are minimized. For this, it is essential to monitor the Hardware usage of the algorithm and thus diagnose the compute and memory bottlenecks in the implementation. In the following thesis, we will be analyzing the mapping of CUDA implementation of BLIINDS-II algorithm on the underlying GPU hardware, and come up with a Kepler architecture specific solution of using shuffle instruction via CUB library to tackle the two major bottlenecks in the algorithm. Experiments were conducted to convey the advantage of using shuffle instru3ction in algorithm over only using shared memory as a buffer to global memory. With the new implementation of BLIINDS-II algorithm using CUB library, a speedup of around 13.7% was achieved.
ContributorsWadekar, Ameya (Author) / Sohoni, Sohum (Thesis advisor) / Aukes, Daniel (Committee member) / Redkar, Sangram (Committee member) / Arizona State University (Publisher)
Created2017