Matching Items (10)
Filtering by
- Genre: Masters Thesis
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
This work presents a communication paradigm, using a context-aware mixed reality approach, for instructing human workers when collaborating with robots. The main objective of this approach is to utilize the physical work environment as a canvas to communicate task-related instructions and robot intentions in the form of visual cues. A vision-based object tracking algorithm is used to precisely determine the pose and state of physical objects in and around the workspace. A projection mapping technique is used to overlay visual cues on tracked objects and the workspace. Simultaneous tracking and projection onto objects enables the system to provide just-in-time instructions for carrying out a procedural task. Additionally, the system can also inform and warn humans about the intentions of the robot and safety of the workspace. It was hypothesized that using this system for executing a human-robot collaborative task will improve the overall performance of the team and provide a positive experience to the human partner. To test this hypothesis, an experiment involving human subjects was conducted and the performance (both objective and subjective) of the presented system was compared with a conventional method based on printed instructions. It was found that projecting visual cues enabled human subjects to collaborate more effectively with the robot and resulted in higher efficiency in completing the task.
ContributorsKalpagam Ganesan, Ramsundar (Author) / Ben Amor, Hani (Thesis advisor) / Yang, Yezhou (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2017
Description
For autonomous vehicles, intelligent autonomous intersection management will be required for safe and efficient operation. In order to achieve safe operation despite uncertainties in vehicle trajectory, intersection management techniques must consider a safety buffer around the vehicles. For truly safe operation, an extra buffer space should be added to account for the network and computational delay caused by communication with the Intersection Manager (IM). However, modeling the worst-case computation and network delay as additional buffer around the vehicle degrades the throughput of the intersection. To avoid this problem, AIM, a popular state-of-the-art IM, adopts a query-based approach in which the vehicle requests to enter at a certain arrival time dictated by its current velocity and distance to the intersection, and the IM replies yes
o. Although this solution does not degrade the position uncertainty, it ultimately results in poor intersection throughput. We present Crossroads, a time-sensitive programming method to program the interface of a vehicle and the IM. Without requiring additional buffer to account for the effect of network and computational delay, Crossroads enables efficient intersection management. Test results on a 1/10 scale model of intersection using TRAXXAS RC cars demonstrates that our Crossroads approach obviates the need for large buffers to accommodate for the network and computation delay, and can reduce the average wait time for the vehicles at a single-lane intersection by 24%. To compare Crossroads with previous approaches, we perform extensive Matlab simulations, and find that Crossroads achieves on average 1.62X higher throughput than a simple VT-IM with extra safety buffer, and 1.36X better than AIM.
o. Although this solution does not degrade the position uncertainty, it ultimately results in poor intersection throughput. We present Crossroads, a time-sensitive programming method to program the interface of a vehicle and the IM. Without requiring additional buffer to account for the effect of network and computational delay, Crossroads enables efficient intersection management. Test results on a 1/10 scale model of intersection using TRAXXAS RC cars demonstrates that our Crossroads approach obviates the need for large buffers to accommodate for the network and computation delay, and can reduce the average wait time for the vehicles at a single-lane intersection by 24%. To compare Crossroads with previous approaches, we perform extensive Matlab simulations, and find that Crossroads achieves on average 1.62X higher throughput than a simple VT-IM with extra safety buffer, and 1.36X better than AIM.
ContributorsAndert, Edward (Author) / Shrivastava, Aviral (Thesis advisor) / Fainekos, Georgios (Committee member) / Ben Amor, Hani (Committee member) / Arizona State University (Publisher)
Created2017
Description
Trajectory forecasting is used in many fields such as vehicle future trajectory prediction, stock market price prediction, human motion prediction and so on. Also, robots having the capability to reason about human behavior is an important aspect in human robot interaction. In trajectory prediction with regards to human motion prediction, implicit learning and reproduction of human behavior is the major challenge. This work tries to compare some of the recent advances taking a phenomenological approach to trajectory prediction. \par The work is expected to mainly target on generating future events or trajectories based on the previous data observed across many time intervals. In particular, this work presents and compares machine learning models to generate various human handwriting trajectories. Although the behavior of every individual is unique, it is still possible to broadly generalize and learn the underlying human behavior from the current observations to predict future human writing trajectories. This enables the machine or the robot to generate future handwriting trajectories given an initial trajectory from the individual thus helping the person to fill up the rest of the letter or curve. This work tests and compares the performance of Conditional Variational Autoencoders and Sinusoidal Representation Network models on handwriting trajectory prediction and reconstruction.
ContributorsKota, Venkata Anil (Author) / Ben Amor, Hani (Thesis advisor) / Venkateswara, Hemanth Kumar Demakethepalli (Committee member) / Redkar, Sangram (Committee member) / Arizona State University (Publisher)
Created2021
Description
In this thesis work, a novel learning approach to solving the problem of controllinga quadcopter (drone) swarm is explored. To deal with large sizes, swarm control is
often achieved in a distributed fashion by combining different behaviors such that
each behavior implements some desired swarm characteristics, such as avoiding ob-
stacles and staying close to neighbors. One common approach in distributed swarm
control uses potential fields. A limitation of this approach is that the potential fields
often depend statically on a set of control parameters that are manually specified a
priori. This paper introduces Dynamic Potential Fields for flexible swarm control.
These potential fields are modulated by a set of dynamic control parameters (DCPs)
that can change under different environment situations. Since the focus is only on
these DCPs, it simplifies the learning problem and makes it feasible for practical use.
This approach uses soft actor critic (SAC) where the actor only determines how to
modify DCPs in the current situation, resulting in more flexible swarm control. In
the results, this work will show that the DCP approach allows for the drones to bet-
ter traverse environments with obstacles compared to several state-of-the-art swarm
control methods with a fixed set of control parameters. This approach also obtained
a higher safety score commonly used to assess swarm behavior. A basic reinforce-
ment learning approach is compared to demonstrate faster convergence. Finally, an
ablation study is conducted to validate the design of this approach.
ContributorsFerraro, Calvin Shores (Author) / Zhang, Yu (Thesis advisor) / Ben Amor, Hani (Committee member) / Berman, Spring (Committee member) / Arizona State University (Publisher)
Created2022
Description
Automated driving systems (ADS) have come a long way since their inception. It is clear that these systems rely heavily on stochastic deep learning techniques for perception, planning, and prediction, as it is impossible to construct every possible driving scenario to generate driving policies. Moreover, these systems need to be trained and validated extensively on typical and abnormal driving situations before they can be trusted with human life. However, most publicly available driving datasets only consist of typical driving behaviors. On the other hand, there is a plethora of videos available on the internet that capture abnormal driving scenarios, but they are unusable for ADS training or testing as they lack important information such as camera calibration parameters, and annotated vehicle trajectories. This thesis proposes a new toolbox, DeepCrashTest-V2, that is capable of reconstructing high-quality simulations from monocular dashcam videos found on the internet. The toolbox not only estimates the crucial parameters such as camera calibration, ego-motion, and surrounding road user trajectories but also creates a virtual world in Car Learning to Act (CARLA) using data from OpenStreetMaps to simulate the estimated trajectories. The toolbox is open-source and is made available in the form of a python package on GitHub at https://github.com/C-Aniruddh/deepcrashtest_v2.
ContributorsChandratre, Aniruddh Vinay (Author) / Fainekos, Georgios (Thesis advisor) / Ben Amor, Hani (Thesis advisor) / Pedrielli, Giulia (Committee member) / Arizona State University (Publisher)
Created2022
Description
Multiple robotic arms collaboration is to control multiple robotic arms to collaborate with each other to work on the same task. During the collaboration, theagent is required to avoid all possible collisions between each part of the robotic arms.
Thus, incentivizing collaboration and preventing collisions are the two principles which
are followed by the agent during the training process. Nowadays, more and more
applications, both in industry and daily lives, require at least two arms, instead of
requiring only a single arm. A dual-arm robot satisfies much more needs of different
types of tasks, such as folding clothes at home, making a hamburger in a grill or
picking and placing a product in a warehouse.
The applications done in this paper are all about object pushing. This thesis
focuses on how to train the agent to learn pushing an object away as far as possible.
Reinforcement Learning (RL), which is a type of Machine Learning (ML), is then
utilized in this paper to train the agent to generate optimal actions. Deep Deterministic
Policy Gradient (DDPG) and Hindsight Experience Replay (HER) are the two RL
methods used in this thesis.
ContributorsLin, Steve (Author) / Ben Amor, Hani (Thesis advisor) / Redkar, Sangram (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2023
Description
There have been multiple attempts of coupling neural networks with external memory components for sequence learning problems. Such architectures have demonstrated success in algorithmic, sequence transduction, question-answering and reinforcement learning tasks. Most notable of these attempts is the Neural Turing Machine (NTM), which is an implementation of the Turing Machine with a neural network controller that interacts with a continuous memory. Although the architecture is Turing complete and hence, universally computational, it has seen limited success with complex real-world tasks.
In this thesis, I introduce an extension of the Neural Turing Machine, the Neural Harvard Machine, that implements a fully differentiable Harvard Machine framework with a feed-forward neural network controller. Unlike the NTM, it has two different memories - a read-only program memory and a read-write data memory. A sufficiently complex task is divided into smaller, simpler sub-tasks and the program memory stores parameters of pre-trained networks trained on these sub-tasks. The controller reads inputs from an input-tape, uses the data memory to store valuable signals and writes correct symbols to an output tape. The output symbols are a function of the outputs of each sub-network and the state of the data memory. Hence, the controller learns to load the weights of the appropriate program network to generate output symbols.
A wide range of experiments demonstrate that the Harvard Machine framework learns faster and performs better than the NTM and RNNs like LSTM, as the complexity of tasks increases.
In this thesis, I introduce an extension of the Neural Turing Machine, the Neural Harvard Machine, that implements a fully differentiable Harvard Machine framework with a feed-forward neural network controller. Unlike the NTM, it has two different memories - a read-only program memory and a read-write data memory. A sufficiently complex task is divided into smaller, simpler sub-tasks and the program memory stores parameters of pre-trained networks trained on these sub-tasks. The controller reads inputs from an input-tape, uses the data memory to store valuable signals and writes correct symbols to an output tape. The output symbols are a function of the outputs of each sub-network and the state of the data memory. Hence, the controller learns to load the weights of the appropriate program network to generate output symbols.
A wide range of experiments demonstrate that the Harvard Machine framework learns faster and performs better than the NTM and RNNs like LSTM, as the complexity of tasks increases.
ContributorsBhatt, Manthan Bharat (Author) / Ben Amor, Hani (Thesis advisor) / Zhang, Yu (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2020
Description
Humans have an excellent ability to analyze and process information from multiple domains. They also possess the ability to apply the same decision-making process when the situation is familiar with their previous experience.
Inspired by human's ability to remember past experiences and apply the same when a similar situation occurs, the research community has attempted to augment memory with Neural Network to store the previously learned information. Together with this, the community has also developed mechanisms to perform domain-specific weight switching to handle multiple domains using a single model. Notably, the two research fields work independently, and the goal of this dissertation is to combine their capabilities.
This dissertation introduces a Neural Network module augmented with two external memories, one allowing the network to read and write the information and another to perform domain-specific weight switching. Two learning tasks are proposed in this work to investigate the model performance - solving mathematics operations sequence and action based on color sequence identification. A wide range of experiments with these two tasks verify the model's learning capabilities.
Inspired by human's ability to remember past experiences and apply the same when a similar situation occurs, the research community has attempted to augment memory with Neural Network to store the previously learned information. Together with this, the community has also developed mechanisms to perform domain-specific weight switching to handle multiple domains using a single model. Notably, the two research fields work independently, and the goal of this dissertation is to combine their capabilities.
This dissertation introduces a Neural Network module augmented with two external memories, one allowing the network to read and write the information and another to perform domain-specific weight switching. Two learning tasks are proposed in this work to investigate the model performance - solving mathematics operations sequence and action based on color sequence identification. A wide range of experiments with these two tasks verify the model's learning capabilities.
ContributorsPatel, Deep Chittranjan (Author) / Ben Amor, Hani (Thesis advisor) / Banerjee, Ayan (Committee member) / McDaniel, Troy (Committee member) / Arizona State University (Publisher)
Created2020
Description
Robotic assisted devices in gait rehabilitation have not seen penetration into clinical settings proportionate to the developments in this field. A possible reason for this is due to the development and evaluation of these devices from a predominantly engineering perspective. One way to mitigate this effect is to further include the principles of neurophysiology into the development of these systems. To further include these principles, this research proposes a method for grounded evaluation of three machine learning algorithms to gain insight on what modeling approaches are able to both replicate therapist assistance and emulate therapist strategies. The algorithms evaluated in this paper include ordinary least squares regression (OLS), gaussian process regression (GPR) and inverse reinforcement learning (IRL). The results show that grounded evaluation is able to provide evidence to support the algorithms at a higher resolution. Also, it was observed that GPR is likely the most accurate algorithm to replicate therapist assistance and to emulate therapist adaptation strategies.
ContributorsSmith, Mason Owen (Author) / Zhang, Wenlong (Thesis advisor) / Ben Amor, Hani (Committee member) / Sugar, Thomas (Committee member) / Arizona State University (Publisher)
Created2021