Chris Rogers’s research while affiliated with Tufts University and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (78)


Figure 1: A visualization of the themes from our 11 interviews with makerspace operators and disabled makers. Word size and color/saturation indicate the prevalence of the code across all interviews.
Figure 3: Artist's rendition of a sampling of participant projects. Details of the projects and features of the makers have been changed to protect their anonymity.
Barriers and Benefits: The Path to Accessible Makerspaces
  • Conference Paper
  • Full-text available

October 2023

·

40 Reads

·

9 Citations

·

Audrey K. Balaska

·

Reuben M. Aronson

·

[...]

·

Elaine Schaertl Short
Download


Introductory Activities for Teaching Robotics with SmartMotors

October 2023

·

38 Reads

·

1 Citation

In this research paper we describe the activities designed for a 5 day engineering design workshop using an educational robotics tool called SmartMotors. SmartMotors are low cost solutions to teach elementary and middle school students about robotics and Artificial Intelligence in under-resourced classrooms. In a few simple steps these motors can be trained by the users to run to various states corresponding to different sensor inputs. We believe that the low cost and trainable aspects of SmartMotors will reduce barriers of entry for both teachers and students in introducing robotics in classrooms and increase student access to robotics and engineering. In the summer of 2022, we used one of our prototypes to run a usability study in a workshop with ten middle school students aged 12–15. The students participated in an hour-long engineering design workshop for five days, and each day they received different prompts along with necessary scaffolding. The participating students had limited prior exposure to robotics and AI. By the end of the workshop, the students were able to train robots in group projects that reflected their individual interests. In this paper, we talk about the students’ journey, starting with building simple projects and subsequently gaining the skills and confidence to showcase diverse and complex designs. We will then discuss the affordances of the tool and explore the opportunities and limitations of SmartMotors in an engineering design workshop.


Fig. 3: GUI layout of the online platform
Introducing Reinforcement Learning to K-12 Students with Robots and Augmented Reality

October 2023

·

353 Reads

·

2 Citations

As artificial intelligence (AI) plays a more prominent role in our everyday lives, it becomes increasingly important to introduce basic AI concepts to K-12 students. To help do this, we combined physical robots and an augmented reality (AR) software to help students learn some of the fundamental concepts of reinforcement learning (RL). We chose RL because it is conceptually easy to understand but has received the least attention in previous research on teaching AI to K-12 students. We designed a series of activities in which students can design their own robots and train them with RL to finish a variety of tasks. We tested our platform with a pilot study conducted with 14 high school students in a rural city. Students’ engagement and learning were assessed through a qualitative analysis of students’ behavior and discussions. The result showed that students were able to understand both high-level AI concepts and specific RL terms through our activities. Also, our approach of combining virtual platforms and physical robots engaged students and inspired their curiosity to self-explore more about RL.



Fig. 1. An example physical build of the robot car and activity environment
Fig. 2. The front side of the placemat instruction used in session 1 and 2. We provide students some example builds and hints to the solution of the challenges. High-resolution images are available at: https://github.com/ZyZhangT/rlplayground/tree/main/Placemats
Fig. 3. GUI layout of 1-D treasure hunting. (The upper part is for students to visualize virtual robot's move in the maze and interact with the GUI. The lower part is for students to visualize agent's assessment on taking different actions in each state.
An Interactive Robot Platform for Introducing Reinforcement Learning to K-12 Students

January 2022

·

296 Reads

·

7 Citations

Advances in Intelligent Systems and Computing

As artificial intelligence (AI) plays a more prominent role in our everyday lives, it becomes increasingly important to introduce basic AI concepts to K-12 students. To help do this, we combined the physical (LEGO® robotics) and the virtual (web-based GUI) worlds for helping students learn some of the fundamental concepts of reinforcement learning (RL). We chose RL because it is conceptually easy to understand but received the least attention in previous research on teaching AI to K-12 students. Our initial pilot study of 6 high school students in an urban city consisted of three separate activities, run remotely on three consecutive Friday afternoons. Students’ engagement and learning were measured through a qualitative assessment of students’ discussions and their answers to our evaluation questions. Even with only three sessions, students were optimizing learning strategies, and understanding key RL concepts and the value of human inputs in RL training.


CORP. A Collaborative Online Robotics Platform

January 2022

·

52 Reads

·

2 Citations

Advances in Intelligent Systems and Computing

In this paper we introduce a novel integrated educational learning development web-based environment intended for learning and teaching, CORP (Collaborative Online Robotics Platform). CORP combines the potential of the Google web-based platform with the educational robot technology of the LEGO Mindstorms EV3 Kit. Designed for students in primary and high school, CORP allows students from different locations to collaboratively interact through a shared Google Slide document with a custom add-on developed to connect to the EV3 robot. In addition to their science, technology, engineering and mathematics (STEM) skills, students also work on their social emotional learning (SEL) skills. Moreover, teachers can analyse log files generated by the platform for insights into student learning.



Figure 1: Users play with the RL activity and robot with the AR application installed in their mobile devices.
Figure 2: The interface was separated into three sections which students could use three buttons to fold and unfold each of them based on what they want to visualize.
Figure 3: Different information that can be shown on the virtual grid. Including 1) a visualization of Q-table; 2) How many times each state-action pair has been visited; 3) An animation of Robot's trajectory in the last episode
An Augmented Reality Platform for Introducing Reinforcement Learning to K-12 Students with Robots

October 2021

·

89 Reads

Interactive reinforcement learning, where humans actively assist during an agent's learning process, has the promise to alleviate the sample complexity challenges of practical algorithms. However, the inner workings and state of the robot are typically hidden from the teacher when humans provide feedback. To create a common ground between the human and the learning robot, in this paper, we propose an Augmented Reality (AR) system that reveals the hidden state of the learning to the human users. This paper describes our system's design and implementation and concludes with a discussion on two directions for future work which we are pursuing: 1) use of our system in AI education activities at the K-12 level; and 2) development of a framework for an AR-based human-in-the-loop reinforcement learning, where the human teacher can see sensory and cognitive representations of the robot overlaid in the real world.



Citations (60)


... It fosters the students' autonomous learning, and provides frequent accompaniment and feedback to students during their academic term, and CS instructors on the overall learning progress of their students. Like LEGO (McNamara et al., 1999), this approach pretends the students to guide their customized "learning route", following significant learning. The Significant Learning Model (Baque-Reyes and Portilla-Faican, 2021) constitutes a constructivist teaching model, where the student is not only a receiver, but the protagonist of their learning process. ...

Reference:

RetoñosApp: Work in Progress on a Platform to Support the Teaching of Programming in CS through the Automation and Customization of Learning Processes Guided by Artificial Intelligence
Lego Brick Sculptures And Robotics In Education
  • Citing Conference Paper
  • June 1999

... While specialized assistive technologies (ATs) exist to address different challenges BLV individuals face in life, they often provide generic solutions that do not consider individual differences among users [43]. Consequently, BLV individuals have become experts at customizing and "hacking" ATs to suit their unique needs, instead of attempting -often pointlessly so -to convince corporations of the needed features and their market viability [6,44]. ...

Barriers and Benefits: The Path to Accessible Makerspaces

... Smart Motors [20] are low-cost robotics kits developed at the Center for Engineering Education and Outreach at Tufts University, designed to be used in engineering design workshops in elementary and middle schools [21]. Smart Motors teach the concept of training datasets which is a core concept in Machine Learning. ...

Introductory Activities for Teaching Robotics with SmartMotors
  • Citing Chapter
  • October 2023

... Others, such as the AlphAI software, allow the training of learning robots and the visualization of AI algorithms (developed at the CNRS, France [12], and commercialized by Learning Robots, France). A large number of other AI robot initiatives have been proposed in the science education field [21]. This development of robots linked to AI software raises the question of the added value of using AI robots over more traditional robots. ...

Introducing Reinforcement Learning to K-12 Students with Robots and Augmented Reality

... In typical scenarios, instructors use existing technology (i.e., metaverse from studio.gometa.io), but there are few studies in which teachers develop their own XR applications for their classes (Shiradkar et al., 2021;Sans-Cope et al., 2021;Zhao et al., 2022). Effectiveness in the development of virtual environments for learning requires a design that includes the creation of learning experiences that transfer knowledge in an emotionally safe environment, and promote autonomy and selfregulation; all this to keep the student engaged (Dumulescu et al., 2021;Pishchukhina, 2022;Alblehia, 2022). ...

A novel Collaborative Online Robotics Platform to address engagement and social emotional challenges in remote learning environment
  • Citing Conference Paper
  • October 2021

... We evaluate our platform in a study with 14 high school students using a three-day curriculum, including a short session of playing with an online RL learning platform we developed in 2020 [10]. Our results showed that students were engaged and excited during the three classes, and they constructed a comprehensive understanding of both general and specific RL concepts. ...

An Interactive Robot Platform for Introducing Reinforcement Learning to K-12 Students

Advances in Intelligent Systems and Computing

... LEGO Robotics has demonstrated satisfactory results among many robotics kits when several factors are taken into account [33]. This robotic tool has been used in various research projects and has beenintegrated into both classrooms and online platforms [30]. ...

CORP. A Collaborative Online Robotics Platform
  • Citing Chapter
  • January 2022

Advances in Intelligent Systems and Computing

... They provide students with a few images of example builds, some guidance to get them started, and activity specific background knowledge. However, they do not provide step-by-step instructions or dictate the creation of a single "correct" solution [29]. For this activity, students used two different placemat instructions showed in Figure 2. The goal of using the placemat instructions was to support students in getting started with the RL activities without telling them exactly what to do and how to do it. ...

Placemat Instructions for Open-Ended Robotics Challenges
  • Citing Chapter
  • January 2021

Advances in Intelligent Systems and Computing

... As long as the future of education is concerned, the scenarios are many, but none of them sound that likely. Most of the scenarios present a mix of physical and virtual classrooms, which will allow children that come from remote areas or live in conditions that do not allow them to be transported to school to be a part of their classroom through remote teaching and there are researchers that present the use of telerobotics, meaning robotic devices that represent the students in class [11]; [12]; [13], while the fanatical users of technology imagine virtual classrooms with VR or virtual worlds [14]; [15]. ...

Remote Sensing And Tele Robotics For Elementary And Middle School Via The Internet
  • Citing Conference Paper
  • June 2003

... There is a vast history of using LEGO ® bricks in education. Projects that use the RCX programmable brick have included a wide variety of projects and courses ranging from robot competitions [1][2][3] to laboratory experiments [4][5][6][7][8][9][10] to project based learning [11][12][13][14][15][16][17] . There have also been a few recent publications dealing specifically with computer programming [18][19][20] , which is the focus of the study described herein. ...

Data Acquisition In The Dorm Room: Teaching Experimentation Techniques Using Lego Materials
  • Citing Conference Paper
  • June 2001