As intelligent agents become pervasive in our lives, they are expected to not only achieve tasks alone but also engage in tasks with humans in the loop. In such cases, the human naturally forms an understanding of the agent, which affects his perception of the agent’s behavior. However, such an understanding inevitably deviates from the ground truth due to reasons such as the human’s lack of understanding of the domain or misunderstanding of the agent’s capabilities. Such differences would result in an unmatched expectation of the agent’s behavior with the agent’s optimal behavior, thereby biasing the human’s assessment of the agent’s performance. In this dissertation, I focus on when these differences are due to a biased belief about domain dynamics. I especially investigate the impact of such a biased belief on the agent’s decision-making process in two different problem settings from a learning perspective. In the first setting, the agent is tasked to accomplish a task alone but must infer the human’s objectives from the human’s feedback on the agent’s behavior in the environment. In such a case, the human biased feedback could mislead the agent to learn a reward function that results in a sub-optimal and, potentially, undesired policy. In the second setting, the agent must accomplish a task with a human observer. Given that the agent’s optimal behavior may not match the human’s expectation due to the biased belief, the agent’s optimal behavior may be viewed as inexplicable, leading to degraded performance and loss of trust. Consequently, this dissertation proposes approaches that (1) endow the agent with the ability to be aware of the human’s biased belief while inferring the human’s objectives, thereby (2) neutralize the impact of the model differences in a reinforcement learning framework, and (3) behave explicably by reconciling the human’s expectation and optimality during decision-making.

Self-Driving cars are a long-lasting ambition for many AI scientists and engineers. In the last decade alone, many self-driving cars like Google Waymo, Tesla Autopilot, Uber, etc. have been roaming the streets of many cities. As a rapidly expanding field, researchers all over the world are attempting to develop more safe and efficient AI agents that can navigate through our cities. However, driving is a very complex task to master even for a human, let alone the challenges in developing robots to do the same. It requires attention and inputs from the surroundings of the car, and it is nearly impossible for us to program all the possible factors affecting this complex task. As a solution, imitation learning was introduced, wherein the agents learn a policy, mapping the observations to the actions through demonstrations given by humans. Through imitation learning, one could easily teach self-driving cars the expected behavior in many scenarios. Despite their autonomous nature, it is undeniable that humans play a vital role in the development and execution of safe and trustworthy self-driving cars and hence form the strongest link in this application of Human-Robot Interaction. Several approaches were taken to incorporate this link between humans and self-driving cars, one of which involves the communication of human's navigational instruction to self-driving cars. The communicative channel provides humans with control over the agent’s decisions as well as the ability to guide them in real-time. In this work, the abilities of imitation learning in creating a self-driving agent that can follow natural language instructions given by humans based on environmental objects’ descriptions were explored. The proposed model architecture is capable of handling latent temporal context in these instructions thus making the agent capable of taking multiple decisions along its course. The work shows promising results that push the boundaries of natural language instructions and their complexities in navigating self-driving cars through towns.

Social media has become the norm of everyone for communication. The usage of social media has increased exponentially in the last decade. The myriads of Social media services such as Facebook, Twitter, Snapchat, and Instagram etc allow people to connect with their friends, and followers freely. The attackers who try to take advantage of this situation has also increased at an exponential rate. Every social media service has its own recommender systems and user profiling algorithms. These algorithms use users current information to make different recommendations. Often the data that is formed from social media services is Linked data as each item/user is usually linked with other users/items. Recommender systems due to their ubiquitous and prominent nature are prone to several forms of attacks. One of the major form of attacks is poisoning the training set data. As recommender systems use current user/item information as the training set to make recommendations, the attacker tries to modify the training set in such a way that the recommender system would benefit the attacker or give incorrect recommendations and hence failing in its basic functionality. Most existing training set attack algorithms work with ``flat" attribute-value data which is typically assumed to be independent and identically distributed (i.i.d.). However, the i.i.d. assumption does not hold for social media data since it is inherently linked as described above. Usage of user-similarity with Graph Regularizer in morphing the training data produces best results to attacker. This thesis proves the same by demonstrating with experiments on Collaborative Filtering with multiple datasets.

In a collaborative environment where multiple robots and human beings are expected

to collaborate to perform a task, it becomes essential for a robot to be aware of multiple

agents working in its work environment. A robot must also learn to adapt to

different agents in the workspace and conduct its interaction based on the presence

of these agents. A theoretical framework was introduced which performs interaction

learning from demonstrations in a two-agent work environment, and it is called

Interaction Primitives.

This document is an in-depth description of the new state of the art Python

Framework for Interaction Primitives between two agents in a single as well as multiple

task work environment and extension of the original framework in a work environment

with multiple agents doing a single task. The original theory of Interaction

Primitives has been extended to create a framework which will capture correlation

between more than two agents while performing a single task. The new state of the

art Python framework is an intuitive, generic, easy to install and easy to use python

library which can be applied to use the Interaction Primitives framework in a work

environment. This library was tested in simulated environments and controlled laboratory

environment. The results and benchmarks of this library are available in the

related sections of this document.

Human-Robot collaboration can be a challenging exercise especially when both the human and the robot want to work simultaneously on a given task. It becomes difficult for the human to understand the intentions of the robot and vice-versa. To overcome this problem, a novel approach using the concept of Mixed-Reality has been proposed, which uses the surrounding space as the canvas to augment projected information on and around 3D objects. A vision based tracking algorithm precisely detects the pose and state of the 3D objects, and human-skeleton tracking is performed to create a system that is both human-aware as well as context-aware. Additionally, the system can warn humans about the intentions of the robot, thereby creating a safer environment to work in. An easy-to-use and universal visual language has been created which could form the basis for interaction in various human-robot collaborations in manufacturing industries.

An objective and subjective user study was conducted to test the hypothesis, that using this system to execute a human-robot collaborative task would result in higher performance as compared to using other traditional methods like printed instructions and through mobile devices. Multiple measuring tools were devised to analyze the data which finally led to the conclusion that the proposed mixed-reality projection system does improve the human-robot team's efficiency and effectiveness and hence, will be a better alternative in the future.

Robots are becoming an important part of our life and industry. Although a lot of robot control interfaces have been developed to simplify the control method and improve user experience, users still cannot control robots comfortably. With the improvements of the robot functions, the requirements of universality and ease of use of robot control interfaces are also increasing. This research introduces a graphical interface for Linear Temporal Logic (LTL) specifications for mobile robots. It is a sketch based interface built on the Android platform which makes the LTL control interface more friendly to non-expert users. By predefining a set of areas of interest, this interface can quickly and efficiently create plans that satisfy extended plan goals in LTL. The interface can also allow users to customize the paths for this plan by sketching a set of reference trajectories. Given the custom paths by the user, the LTL specification and the environment, the interface generates a plan balancing the customized paths and the LTL specifications. We also show experimental results with the implemented interface.