Robotics Commons^™

Exploring Cognition And Affect During Human-Cobot Interaction, Angelika T. Canete, Javier Gonzalez-Sanchez, Rafael Guerra Silva

College of Engineering Summer Undergraduate Research Program

Collaborative robots (Cobots) have recently gained popularity due to their capability to work collaboratively with human operators. This collaborative relationship has been named under the robotics discipline of Human-Robot Collaboration (HRC), in which humans and robots work together to accomplish a common task while also being in the same physical space. An important part of collaboration is the human's decision-making, which is largely affected by their affective and cognitive state. A cobot lacks this fundamental understanding of the human operator. In this research, we utilize a server-client program to communicate the affective states of a human user to a Raspberry …

Drones For Marine Science And Agriculture, David Caldera, Sai Murthy

College of Engineering Summer Undergraduate Research Program

Our research project was launched at Cal Poly in 2019 with the goal of assisting researchers at the CSULB Shark Lab in detecting sharks from aerial images. Under the guidance of Dr. Franz J. Kurfess, students trained an object detection algorithm using shark images and were able to achieve high rate of detection. Following this success, the team has constructed multiple drones and expanded their research to include applications in the fields of agriculture and ecology. This summer the goal is to use a iPhone 14 Pro in lieu of a traditional camera system for real-time object recognition. Object detection …

In-Situ Mechanical Tester, Andrrew Murach, Gustavo Marquez, Kosimo Tonn, Jake Vormbaum

Mechanical Engineering

Over the course of the 2022-23 Cal Poly SLO school year, a small tensile tester device was developed specifically for Dr. Long Wang to test thin film materials under a microscope and generate accurate force versus displacement graphs. A tensile tester was manufactured using purchased and machined components, electronics were consolidated in a separate box and connected, and a program and user interface were written to control the motion, provide custom inputs, and organize useful data for the researcher. Tests were conducted to compare the performance of the device to universal tensile testers available in the Composites lab. The device …

Panodepth – Panoramic Monocular Depth Perception Model And Framework, Adley K. Wong

Master's Theses

Depth perception has become a heavily researched area as companies and researchers are striving towards the development of self-driving cars. Self-driving cars rely on perceiving the surrounding area, which heavily depends on technology capable of providing the system with depth perception capabilities. In this paper, we explore developing a single camera (monocular) depth prediction model that is trained on panoramic depth images. Our model makes novel use of transfer learning efficient encoder models, pre-training on a larger dataset of flat depth images, and optimizing the model for use with a Jetson Nano. Additionally, we present a training and optimization framework …

Dual-Axis Precision Imager, Gary Huarng

Computer Engineering

The Dual-Axis Precision Imager (DAPI) is a drawing robot that processes images and draws them on a whiteboard. The system has two modes: a Sobel filter mode that finds the edges of the input image with a Sobel filter, and a tri-tone grayscale mode that approximates the shading of the input image with the colors white, gray, and black. The DAPI consists of an Arduino-controlled XY gantry system with a pen mounted on the gantry head, and a Processing IDE program that processes the original image, converts the processed image into gantry instructions, and sends them to the Arduino for …

The Poly Rover Project, Eric Lei, Alla Alamsi, Neil Patel, Diego Ramos

Computer Engineering

The Polyver Project is an idea born from the curiosity of a few students who wondered what the interaction between a physical person and a rover as the host of random internet users would look like. It is also an experiment to enhance the exploration of real world sites in real time while also having the power of interaction.

The goal of the Polyver Project is to build the foundation for a system that can serve as the interface between the internet and a fleet of rovers. Each rover is equipped with at least a camera, microphone, and a speaker …

Developing A Miniature Smart Boat For Marine Research, Michael Isaac Eirinberg

Computer Engineering

This project examines the development of a smart boat which could serve as a possible marine research apparatus. The smart boat consists of a miniature vessel containing a low-cost microcontroller to live stream a camera feed, GPS telemetry, and compass data through its own WiFi access point. The smart boat also has the potential for autonomous navigation. My project captivated the interest of several members of California Polytechnic State University, San Luis Obispo’s (Cal Poly SLO) Marine Science Department faculty, who proposed a variety of fascinating and valuable smart boat applications.

Therapeutic Mechanical Horse, Cade M. Liberty, Aleya Dolorfino, Peter Philips, Zuzanna Dominik, Luke Watts

Mechanical Engineering

Jack's Helping Hand and its hippotherapy participants required a device to serve as an alternative to a live horseback riding experience that could also increase the range of riders. This would provide more clients with equine-assisted therapy that has proven to better the lives of people with both physical and mental disabilities. Horses can be unpredictable, tall, and sometimes anxiety-inducing, especially for new riders. Our group’s aim was to develop a mechanical horse that will be able to reduce these issues for equine therapy centers and the riders they help. When a rider gets to practice sitting on the horse …

Mars Rover Mechanical Arm & Turret, Kendall C. Chappell, Kyle D. Peterson, Rodrigo Gonzalez, Sam Cole

Mechanical Engineering

The Rover Mechanical Arm and Turret (RAT) team was originally tasked with designing and building a mechanical arm to attach to the Exo Mars rover: a project headed by Cal Poly professor, Rich Murray. The rover will be the 3rd in a series of rovers sponsored by Murray. Through ideation, comparison studies, research, and prototyping, the RAT team determined a design capable of fulfilling the sponsor’s specifications. The concept design is lightweight, durable, and capable of 4 degrees of freedom. With two links and a mechanical claw, the rover arm has the capability to retrieve small rock samples from Mars's …

Smartphone Control Of Rc Cars, Weston R. Fitzgerald

Electrical Engineering

The smartphone-controlled RC (remote-controlled) car is an inexpensive remote-controlled car designed to be fast and portable. Instead of manufacturing, packaging, and shipping a separate controller, the remote control is implemented in a phone application, which saves time and money in both the design process and the manufacturing process. Utilizing the user’s smartphone is more cost-effective since mobile devices are a common recurrence, and packaging fewer devices results in overall better portability of the product.

This smartphone-controlled car is speedy and intuitive to learn for typical smartphone users. The user can change the car’s speed and direction wirelessly using their phone; …

Low-Cost Uav Swarm For Real-Time Object Detection Applications, Joel Valdovinos Miranda

Master's Theses

With unmanned aerial vehicles (UAVs), also known as drones, becoming readily available and affordable, applications for these devices have grown immensely. One type of application is the use of drones to fly over large areas and detect desired entities. For example, a swarm of drones could detect marine creatures near the surface of the ocean and provide users the location and type of animal found. However, even with the reduction in cost of drone technology, such applications result costly due to the use of custom hardware with built-in advanced capabilities. Therefore, the focus of this thesis is to compile an …

Snr: Software Library For Introductory Robotics, Spencer F. Shaw

Master's Theses

This thesis introduces "SNR," a Python library for programming robotic systems in the context of introductory robotics courses. Greater demand for roboticists has pressured educational institutions to expand robotics curricula. Students are now more likely to take robotics courses earlier and with less prior programming experience. Students may be attempting to simultaneously learn a systems programming language, a library API, and robotics concepts. SNR is written purely in Python to present familiar semantics, eliminating one of these learning curves. Industry standard robotics libraries such as ROS often require additional build tools and configuration languages. Students in introductory courses frequently lack …

Emergency Landing And Guidance System, Joseph Alarid

Master's Theses

Every year there are thousands of aviation accidents along with hundreds of human deaths that happen around the world. While the data is sparse, it is well documented that many of these happen from emergency landings gone awry. While pilots can generally make great landings in clear daytime conditions, they are significantly handicapped when it comes to landing at night or amongst poor visibility conditions.

Due to the nature of this problem and some of the large scale advances in software technology we propose a solution that provides a significant improvement from the status quo. Using transfer learning on neural …

Short Run Box Maker, Jesus Valdez-Ruelas

General Engineering

Small businesses with short run product catalogs have trouble finding the right size box that will work for multiple products. In turn, this leads most businesses to use oversized boxes resulting in unnecessary shipping fees. The objective of this project was to develop and test a cost-effective prototype of a box making machine that could create a short run of custom sized boxes. A Co2 laser was found to be the best option for cutting cardboard and a vertically standing machine was designed to feed the cardboard via rollers. To control cardboard movement stepper motors were used and controlled using …

Reading Robot, Gillian Watts, Andrew Myers, Sabrinna Tan, Taylor Klein, Omeed Djassemi

General Engineering

Presently, there is an insufficient availability of human experts to assist students in reading competency and comprehension. Our team’s goal was to create an improved socially assistive robot for use by therapists, teachers, and parents to help children and adults develop reading skills while they do not have access to specialists. HAPI is a socially assistive robot that we created with the goal of helping students practice their reading comprehension skills. HAPI enables a student to improve their reading skills without an educator present, while enabling educators to review the student's performance remotely. Design constraints included: physical size, weight, duration …

Rchex: A Radio-Controlled Hexapod, Dominique Sayo

Computer Engineering

rcHex is a radio-controlled hexapod with 18 degrees of freedom, capable of positional and rotational body adjustment as well as omnidirectional travel at variable speeds using three common gaits. Its general-purpose design accessible to hobbyists makes rcHex an platform for further development, whether it be experimentation in advanced robotic movement or retrofitting sensors to utilize technologies such as computer vision and artificial intelligence. This report explores some of the design intricacies of hexapod movement, including gait sequencing and the application of inverse kinematics to multi-jointed limbs.

Autonomous Butter Robot, David Chau, Michael Hegglin

Computer Engineering

Don’t you wish your butter would come to you? Well now it can with the patented Michael and David butter robot! Based on an idea from a TV show, our team set out to see if a similar robot was possible to make in real life. The objective was simple. Can we make a small table sized robot that can bring a person butter using image detection software? With that question in mind we set out buying our components. We wanted to keep it small, so we looked up devices that could do simple image processing and from there we …

Surface Autonomous Vehicle For Emergency Rescue, Max Emerick, Ryan Shields, Christopher Feickert, Raymond Impara

Mechanical Engineering

The goal of this document is to clearly define the problem parameters and project objectives and to clearly describe the design process, planned final design, and manufacturing and testing procedures for the senior design project of Team 26: SAVER -- the Surface Autonomous Vehicle for Emergency Rescue. This is both for the purpose of project planning and for clear communication between all parties involved in the project.

The objective of the SAVER project is to develop a proof of concept for an autonomous maritime search and rescue vehicle for aiding in man-overboard missions. To accomplish this goal, a list of …

Flexible Fault Tolerance For The Robot Operating System, Sukhman S. Marok

Master's Theses

The introduction of autonomous vehicles has the potential to reduce the number of accidents and save countless lives. These benefits can only be realized if autonomous vehicles can prove to be safer than human drivers. There is a large amount of active research around developing robust algorithms for all parts of the autonomous vehicle stack including sensing, localization, mapping, perception, prediction, planning, and control. Additionally, some of these research projects have involved the use of the Robot Operating System (ROS). However, another key aspect of realizing an autonomous vehicle is a fault-tolerant design that can ensure the safe operation of …

Lawn Buddy, Jayson Johnston, Andrew Brown, Jacob Maljian

Electrical Engineering

Grass lawns are a common hallmark of the American home. In 2019, a survey from the National Association of Landscape Professionals found that 81% of all Americans owned a lawn [1]. Mowing is a time consuming and costly chore that is part of maintaining a grass lawn. The manual labor in mowing a lawn can exceed 40 hours per year [2]. People commonly incur weekly costs on mowing services to save time. Traditional gas powered mowers are physically demanding and use engines that need routine maintenance. They operate loudly enough that users should be wearing hearing protection and the noise …

Decentralized, Noncooperative Multirobot Path Planning With Sample-Basedplanners, William Le

Master's Theses

In this thesis, the viability of decentralized, noncooperative multi-robot path planning algorithms is tested. Three algorithms based on the Batch Informed Trees (BIT*) algorithm are presented. The first of these algorithms combines Optimal Reciprocal Collision Avoidance (ORCA) with BIT*. The second of these algorithms uses BIT* to create a path which the robots then follow using an artificial potential field (APF) method. The final algorithm is a version of BIT* that supports replanning. While none of these algorithms take advantage of sharing information between the robots, the algorithms are able to guide the robots to their desired goals, with the …

Reasoning From Point Clouds, Joey Wilson

Computer Engineering

Over the past two years, 3D object detection has been a major area of focus across industry and academia. This is primarily due to the difficulty of learning data from point clouds. While camera images are fixed size and can therefore be easily trained on using convolution, point clouds are unstructured series of points in three dimensions. Therefore, there is no fixed number of features, or a structure to run convolution on. Instead, researchers have developed many ways of attempting to learn from this data, however there is no clear consensus on what is the best method, as each has …

An Application Of Sliding Mode Control To Model-Based Reinforcement Learning, Aaron Thomas Parisi

Master's Theses

The state-of-art model-free reinforcement learning algorithms can generate admissible controls for complicated systems with no prior knowledge of the system dynamics, so long as sufficient (oftentimes millions) of samples are available from the environ- ment. On the other hand, model-based reinforcement learning approaches seek to leverage known optimal or robust control to reinforcement learning tasks by mod- elling the system dynamics and applying well established control algorithms to the system model. Sliding-mode controllers are robust to system disturbance and modelling errors, and have been widely used for high-order nonlinear system control. This thesis studies the application of sliding mode control …

Utilizing Trajectory Optimization In The Training Of Neural Network Controllers, Nicholas Kimball

Master's Theses

Applying reinforcement learning to control systems enables the use of machine learning to develop elegant and efficient control laws. Coupled with the representational power of neural networks, reinforcement learning algorithms can learn complex policies that can be difficult to emulate using traditional control system design approaches. In this thesis, three different model-free reinforcement learning algorithms, including Monte Carlo Control, REINFORCE with baseline, and Guided Policy Search are compared in simulated, continuous action-space environments. The results show that the Guided Policy Search algorithm is able to learn a desired control policy much faster than the other algorithms. In the inverted pendulum …

Weight Controlled Electric Skateboard, Zachary Barram, Carson Bertozzi, Vishnu Dodballapur

Computer Engineering

Technology and the way that humans interact is becoming more vital and omnipresent with every passing day. However, human interface device designers suffer from the increasingly popular “designed for me or people like me” syndrome. This design philosophy inherently limits accessibility and usability of technology to those like the designer. This places severe limits of usability to those who are not fully able as well as leaves non-traditional human interface devices unexplored. This project set out to explore a previously uncharted human interface device, on an electric skateboard, and compare it send user experience with industry leading human interface devices.

Labeling Paths With Convolutional Neural Networks, Sean Wallace, Kyle Wuerch

Computer Engineering

With the increasing development of autonomous vehicles, being able to detect driveable paths in arbitrary environments has become a prevalent problem in multiple industries. This project explores a technique which utilizes a discretized output map that is used to color an image based on the confidence that each block is a driveable path. This was done using a generalized convolutional neural network that was trained on a set of 3000 images taken from the perspective of a robot along with matching masks marking which portion of the image was a driveable path. The techniques used allowed for a labeling accuracy …

The Soul Annoyed Robot: A Senior Project Report, Dayton Andrew Muxlow, Christian Johansen

Computer Engineering

Our goal for this senior project was to create a competitive robot designed to com- pete in Roborodentia 2019. Our project started during the Winter 2019 quarter, and ended with the competition on May 18, 2019. During that time, we developed an accurate solenoid shooting mechanism, an elevated conveyor belt to carry poker chips, and a servo arm to scoop in stacks of poker chips. These hardware compo- nents were attached to a circular differential-drive wooden base designed to be easy to control. We also planned out our match strategy and implemented this strategy with software written in C/Wiring to …

Planr.: Planar Learning Autonomous Navigation Robot, Gabrielle S. Santamorena, Daniel Kasman, Jesus Mercado, Ben Klave, Andrew Weisman, Anthony Fortner

Computer Engineering

PLANR is a self-contained robot capable of mapping a space and generating 2D floor plans of a building while identifying objects of interest. It runs Robot Operating System (ROS) and houses four main hardware components. An Arduino Mega board handles the navigation, while an NVIDIA Jetson TX2, holds most of the processing power and runs ROS. An Orbbec Astra Pro stereoscopic camera is used for recognition of doors, windows and outlets and the RPLiDAR A3 laser scanner is able to give depth for wall detection and dimension measurements. The robot is intended to operate autonomously and without constant human monitoring …

Robot Navigation In Cluttered Environments With Deep Reinforcement Learning, Ryan Weideman

Master's Theses

The application of robotics in cluttered and dynamic environments provides a wealth of challenges. This thesis proposes a deep reinforcement learning based system that determines collision free navigation robot velocities directly from a sequence of depth images and a desired direction of travel. The system is designed such that a real robot could be placed in an unmapped, cluttered environment and be able to navigate in a desired direction with no prior knowledge. Deep Q-learning, coupled with the innovations of double Q-learning and dueling Q-networks, is applied. Two modifications of this architecture are presented to incorporate direction heading information that …

Surveying Underwater Shipwrecks With Probabilistic Roadmaps, Amy Jeannette Lewis

Master's Theses

Almost two thirds of the Earth's surface is covered in ocean, and yet, only about 5% of it is mapped. There are an unknown amount of sunken ships, planes, and other artifacts hidden below the sea. Extensive search via boat and a sonar tow fish following a standard lawnmower pattern is used to identify sites of interest. Then, if a site has been determined to potentially be historically significant, the most common next step is a survey by either a human dive team or remotely operated vehicle. These are time consuming, error prone, and potentially dangerous options, but autonomous underwater …