About Me

I want to make the world as smart as possible. I study artificial intelligence and robotics from a perspective inspired by human cognition. My life goal lies at the intersection of intelligence and system design; I want to create machine intelligence that will increase access to education and further general technological progress.


Mark Edmonds


University of California, Los Angeles

PhD in Computer Science, Artificial Intelligence concentration Present

University of California, Los Angeles

M.S. in Computer Science June 2017

University of Dayton

B.S. in Computer Engineering, Magna Cum Laude May 2015


Feburary 2020 Journal publication accepted at Engineering
December 2019 Science Robotics article covered in IEEE Spectrum, UCLA Samueli School of Engineering, and Tech Xplore
November 2019 Journal publication accepted at Science Robotics
November 2019 Paper accepted for an oral presentation at AAAI 2020
April 2019 Paper accepted at CogSci 2019
September 2018 Invited talk at ONR MURI meeting
August 2018 Journal publication accepted at IEEE TPDS
June 2018 Invited talk at RSS Causal Imitation Workshop
April 2018 Paper accepted for an oral presentation at CogSci 2018
January 2018 Paper accepted at ICRA 2018
November 2017 Invited Lightning Talk at CoRL 2017
August 2017 Invited talk at ONR MURI meeting
June 2017 Two papers accepted at IROS 2017


A tale of two explanations: Enhancing human trust by explaining robot behavior
M. Edmonds, F. Gao*, H. Liu*, X. Xie*, S. Qi, B. Rothrock, Y. Zhu, Y.N. Wu, H. Lu, S.C. Zhu
* equal contributors

Science Robotics, Volume 4, Issue 37, 2019

system architecture GEP explanation
Journal Publication Explainable AI (XAI)

Theory-based Causal Transfer: Integrating Instance-level Induction and Abstract-level Structure Learning
M. Edmonds, X. Ma, S. Qi, Y. Zhu, H. Lu, S.C. Zhu

Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2020

causal hierarchy model result
Conference Paper Oral Presentation Causal Learning

Decomposing Human Causal Learning: Bottom-up Associative Learning and Top-down Schema Reasoning

41st Annual Meeting of the Cognitive Science Society (CogSci), 2019

causal simulator causal learning hierarchy
Conference Paper Causal Learning

Hardware Accelerated Semantic Declarative Memory Systems through CUDA and MapReduce
M. Edmonds, T. Atahary, S. Douglass, T. Taha.

IEEE Transactions on Parallel and Distributed Systems (TDPS), March 2019

causal simulator causal structures
Journal Publication Declarative Memory

Human Causal Transfer: Challenges for Deep Reinforcement Learning
M. Edmonds*, J. Kubricht*, C. Summers, Y. Zhu, B. Rothrock, S.C. Zhu, H. Lu.
* equal contributors

40th Annual Meeting of the Cognitive Science Society (CogSci), 2018

causal simulator causal structures
Conference Paper Oral Presentation Causal Learning

Unsupervised Learning of Hierarchical Models for Hand-Object Interactions
X. Xie*, H. Liu*, M. Edmonds, F. Gao, S. Qi, Y. Zhu, B. Rothrock, S.C. Zhu.
* equal contributors

International Conference on Robotics and Automation (IRCA), 2018

action clustering temporal and-or graph
Conference Paper Learning from Demonstration

Feeling the Force: Integrating Force and Pose for Fluent Discovery through Imitation Learning to Open Medicine Bottles
M. Edmonds*, F. Gao*, X. Xie, H. Liu, S. Qi, Y. Zhu, B. Rothrock, S.-C. Zhu.
* equal contributors

International Conference on Intelligent Robots and Systems (IROS), 2017

Open bottle demo 1 Open bottle demo 2
Conference Paper Learning from Demonstration

A Glove-based System for Studying Hand-Object Manipulation via Pose and Force Sensing
H. Liu*, X. Xie*, M. Millar*, M. Edmonds, F. Gao, Y. Zhu, V. Santos, B. Rothrock, S.C. Zhu.
* equal contributors

International Conference on Intelligent Robots and Systems (IROS), 2017

Glove visualization 1 Glove visualization 2
Conference Paper Learning from Demonstration

High Performance Declarative Memory Systems through MapReduce
M. Edmonds, T. Atahary, S. Douglass, T. Taha.

Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD), 2015

declarative memory declarative memory fan optimzation
Conference Paper Declarative Memory

Brain Machine Interface Using Emotiv EPOC to Control Robai Cyton Robotic Arm

Aerospace and Electronics Conference (NAECON), 2015.

Conference Paper Brain Machine Interface


Causal Learning & Reinforcement Learning

Center for Vision, Cognition, Learning, and Autonomy, UCLA August 2017 - Present

This project seeks to examine how causal learning and reasoning can be connected to reinforcement learning. We developed a simulator with a latent causal model and examined how well humans converge to the optimal policy. Next, we examined how well state-of-the-art reinforcement learning algorithms can learn the optimal policy in this environment. Future work will include training model-based reinforcement learning to successfully accomplish the task with faster and better convergence than model-free reinforcement learnig.

simulator screen
Center for Vision, Cognition, Learning and Autonomy logo
Jet Propulsion Laboratory logo

Human Robot Collaboration

Center for Vision, Cognition, Learning, and Autonomy, UCLA Sept 2016 - August 2017

The Human Robot Collaboration Project aims to create a robot platform capable of autonomously collaborating with humans to accomplish meaningful, everday tasks. Currently, the project aims to transfer causal knowledge from human demonstrators to robots. This transfer focuses on using a tactile glove to capture visually latent states in the demonstration that are irrecoverable from vision along (e.g. forces exerted by the hand). From these demonstrations, we transfer the knowledge to the robot using an And-Or graph. In the future, we plan to expand this system to include intention prediction so the robot can take an active and collaborative role assisting with human tasks.

Engineering contributions:
  • Neural network training for action planning and embodiment mapping between a human demonstrator and a robot
  • Localization using SLAM, IMU, and wheel odometry combined with Kalman filtering using a Microsoft Kinect and Velodyne VLP16
  • ROS navigation stack, including a dynamic footprint based on current position of arms
Center for Vision, Cognition, Learning and Autonomy logo
Jet Propulsion Laboratory logo

Declarative Memory

Wright Patterson Air Force Base, University of Dayton January 2014 - September 2015

My undergraduate thesis was focused on accelerating the declarative memory module of the CECEP cognitive architecture, a derivative of ACT-R. The research centered on leveraging the parallel computing abilities of the CUDA programming platform to accelerate declarative retrieval. The initial, C++ implementation produced a 20 times speedup over the fastest previous implementation of declarative memory. The CUDA implementation accelerates declarative memory by a factor of 100 times while providing massive scalability. The work was jointly supported by the Air Force Research Lab and the University of Dayton Research Institute.

University of Dayton logo
Air Force Research Lab logo

Robotic Arm Brain Machine Interface

University of Dayton Senior Design Project August 2014 - May 2015

This project expanded the capability of a brain machine interface through EEG signals and a robotic arm. The research centered on adding additional gestures and improving the universality of the interface. The team implemented 6 new useful actions for the robotic and developed a in-house EEG signal classifier using liner discriminate analysis. The EEG classifier currently can successfully distinguish between two states but successive senior design teams will increase the number of distinguishable states.

University of Dayton logo


Robotics Research Engineer Intern

International Center for AI and Robot Autonomy June 2018 - Present

Working on transfer learning approaches for robotics research to transfer symbolic and haptic information between environments and embodiments.

Adjunct Professor

Santa Monica College June 2016 - Present

  • CS 80, Internet Programming, a class focused on HTML, CSS, JavaScript, MySQL, and PHP
  • CS 50, Introduction to C Programming
  • CS 52, Introduction to C++ Programming

Software Engineering Intern

Garmin International May 2013 - August 2013

Interned as a member of the Datalink team in the Aviation department of Garmin. Contributed to the ACARS protocol for Garmin Avionics software.

Tutor and Teacher

Cristo Rey Kansas City May 2011 - August 2012

Taught pre-calculus, chemistry, and physics at an inner city high school during summer and winter breaks.


  • Your work is going to fill a large part of your life, and the only way to be truly satisfied is to do what you believe is great work. And the only way to do great work is to love what you do. If you haven't found it yet, keep looking. Don't settle. As with all matters of the heart, you'll know when you find it.

    Steve Jobs
  • One finds limits by pushing them.

    Herbert Simon
  • The world needs dreamers and the world needs doers. But above all, the world needs dreamers who do.

    Sarah Ban Breathnach
  • People think that computer science is the art of geniuses but the actual reality is the opposite, just many people doing things that build on each other, like a wall of mini stones.

    Donald Knuth
  • I've always tried to go a step past wherever people expected me to end up.

    Beverly Sills

Get In Touch.

If you have any questions about me, my research interests, or my work, please reach out. Interesting thoughts from interesting people are always welcome. mark@mjedmonds.com