Filtering by
- Status: Published
Currently, autonomous vehicles are being evaluated by how well they interact with humans without evaluating how well humans interact with them. Since people are not going to unanimously switch over to using autonomous vehicles, attention must be given to how well these new vehicles signal intent to human drivers from the driver’s point of view. Ineffective communication will lead to unnecessary discomfort among drivers caused by an underlying uncertainty about what an autonomous vehicle is or isn’t about to do. Recent studies suggest that humans tend to fixate on areas of higher uncertainty so scenarios that have a higher number of vehicle fixations can be reasoned to be more uncertain. We provide a framework for measuring human uncertainty and use the framework to measure the effect of empathetic vs non-empathetic agents. We used a simulated driving environment to create recorded scenarios and manipulate the autonomous vehicle to include either an empathetic or non-empathetic agent. The driving interaction is composed of two vehicles approaching an uncontrolled intersection. These scenarios were played to twelve participants while their gaze was recorded to track what the participants were fixating on. The overall intent was to provide an analytical framework as a tool for evaluating autonomous driving features; and in this case, we choose to evaluate how effective it was for vehicles to have empathetic behaviors included in the autonomous vehicle decision making. A t-test analysis of the gaze indicated that empathy did not in fact reduce uncertainty although additional testing of this hypothesis will be needed due to the small sample size.
To achieve this goal, a model of a swarm performing a collective transport task in a bounded domain featuring convex obstacles was simulated in MATLAB/ Simulink®. The closed-loop dynamic equations of this model were linearized about an equilibrium state with angular acceleration and linear acceleration set to zero. The simulation was run over 30 times to confirm system ability to successfully transport the payload to a goal point without colliding with obstacles and determine ideal operating conditions by testing various orientations of objects in the bounded domain. An additional purely MATLAB simulation was run to identify local minima of the Hessian of the navigation-like potential function. By calculating this Hessian periodically throughout the system’s progress and determining the signs of its eigenvalues, a system could check whether it is trapped in a local minimum, and potentially dislodge itself through implementation of a stochastic term in the robot controllers. The eigenvalues of the Hessian calculated in this research suggested the model local minima were degenerate, indicating an error in the mathematical model for this system, which likely incurred during linearization of this highly nonlinear system.
This paper analyzes responses to deviated Trolley Problem scenarios [5] in a simulated driving environment and still images from MIT’s moral machine website [8] to better understand how humans respond to various crashes. Also included is participants driving habits and personal values, however the bulk of that analysis is not included here. The results of the simulation prove that for the most part in driving scenarios, people would rather sacrifice themselves over people outside of the vehicle. The moral machine scenarios prove that self-sacrifice changes as the trend to harm one’s own vehicle was not so strong when passengers were introduced. Further defending this idea is the importance placed on Family Security over any other value.
Suggestions for implementing ethics into autonomous vehicle crashes stem from the results of this experiment but are dependent on more research and greater sample sizes. Once enough data is collected and analyzed, a moral baseline for human’s moral domain may be agreed upon, quantified, and turned into hard rules governing how self-driving cars should act in different scenarios. With these hard rules as boundary conditions, artificial intelligence should provide training and incremental learning for scenarios which cannot be determined by the rules. Finally, the neural networks which make decisions in artificial intelligence must move from their current “black box” state to something more traceable. This will allow researchers to understand why an autonomous vehicle made a certain decision and allow tweaks as needed.
Throughout this project, I decided on a number of learning goals to consider it a success. I needed to learn how to use the supporting libraries that would help me to design this system. I also learned how to use the Twitter API, as well as create the infrastructure behind it that would allow me to collect large amounts of data for machine learning. I needed to become familiar with common machine learning libraries in Python in order to create the necessary algorithms and pipelines to make predictions based on Twitter data.
This paper details the steps and decisions needed to determine how to collect this data and apply it to machine learning algorithms. I determined how to create labelled data using pre-existing Botometer ratings, and the levels of confidence I needed to label data for training. I use the scikit-learn library to create these algorithms to best detect these bots. I used a number of pre-processing routines to refine the classifiers’ precision, including natural language processing and data analysis techniques. I eventually move to remotely-hosted versions of the system on Amazon web instances to collect larger amounts of data and train more advanced classifiers. This leads to the details of my final implementation of a user-facing server, hosted on AWS and interfacing over Gmail’s IMAP server.
The current and future development of this system is laid out. This includes more advanced classifiers, better data analysis, conversions to third party Twitter data collection systems, and user features. I detail what it is I have learned from this exercise, and what it is I hope to continue working on.
The work presents the nonlinear equations of motion of a quadcopter. This includes the translational and rotational equations of motion, as well as an analysis of the nonlinear actuator dynamics. The work then analyzes the static properties of a quadcopter in forward flight equilibrium and shows how static properties change as physical properties of the vehicle are varied. Next, the dynamics of forward flight are linearized, and a dynamic analysis is provided.
After dynamic analysis, the work shows detailed hierarchical control system design trade studies, which includes attitude and translational inner-outer loop control. Among other designs, the following are presented: PD control, proportional control, pole-placement control. Each of these control architectures are employed for the inner loops and outer loops. The work also analyzes linear versus nonlinear simulation performance of a quadcopter, specifically for a step x-axis reference command. It is found that the nonlinear dynamics of the actuator cause significant discrepancy between linear and nonlinear simulation.
Finally, this thesis establishes directions for future graduate research. This includes hardware design, as well as moving toward design of a highly-maneuverable thrust-vectoring quadrotor which will be the focus of the proposed graduate PhD research. In summary, this thesis provides the beginning of a cohesive framework to model, analyze, control, and design quadcopters. It also lays the groundwork for graduate research and beyond.