Mark Edmonds

Mark Edmonds

Auto-generated profile, based on publicly available information

Mark Edmonds

Department of Computer Science, University of California, Los Angeles, Los Angeles, CA 90095, USA

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2020 in Engineering
Verified
Journal Article
Open access
YZYixin Zhu
Yixin Zhu
TGTao Gao
Tao Gao
LFLifeng Fan
Lifeng Fan
SHSiyuan Huang
Siyuan Huang
MEMark Edmonds
Mark Edmonds
SZSong-Chun Zhu
Song-Chun Zhu

18 December 2019 in Science Robotics
Verified
Journal Article
Open access
PDF file
MEMark Edmonds
Mark Edmonds
FGFeng Gao
Feng Gao
HLHangxin Liu
Hangxin Liu
XXXu Xie
Xu Xie
SQSiyuan Qi
Siyuan Qi
SZSong-Chun Zhu
Song-Chun Zhu
Forms of explanation that are best suited to foster trust do not necessarily correspond to those components contributing to the best task performance.

27 July 2022 in Science Robotics
Verified
Journal Article
Closed access
LYLuyao Yuan
Luyao Yuan
XGXiaofeng Gao
Xiaofeng Gao
ZZZilong Zheng
Zilong Zheng
MEMark Edmonds
Mark Edmonds
YWYingnian Wu
Yingnian Wu
SZSong-Chun Zhu
Song-Chun Zhu
A prerequisite for social coordination is bidirectional communication between teammates, each playing two roles simultaneously: as receptive listeners and expressive speakers. For robots working with humans in complex situations with multiple goals that differ in importance, failure to fulfill the expectation of either role could undermine group performance due to misalignment of values between humans and robots. Specifically, a robot needs to serve as an effective listener to infer human users’ intents from instructions and feedback and as an expressive speaker to explain its decision processes to users. Here, we investigate how to foster effective bidirectional human-robot communications in the context of value alignment—collaborative robots and users form an aligned understanding of the importance of possible task goals. We propose an explainable artificial intelligence (XAI) system in which a group of robots predicts users’ values by taking in situ feedback into consideration while communicating their decision processes to users through explanations. To learn from human feedback, our XAI system integrates a cooperative communication model for inferring human values associated with multiple desirable goals. To be interpretable to humans, the system simulates human mental dynamics and predicts optimal explanations using graphical models. We conducted psychological experiments to examine the core components of the proposed computational framework. Our results show that real-time human-robot mutual understanding in complex cooperative tasks is achievable with a learning model based on bidirectional communication. We believe that this interaction framework can shed light on bidirectional value alignment in communicative XAI systems and, more broadly, in future human-machine teaming systems.

1 June 2015
Verified
Conference Paper
Closed access
DPDaniel Prince
Daniel Prince
MEMark Edmonds
Mark Edmonds
ASAndrew Sutter
Andrew Sutter
MCMatthew Cusumano
Matthew Cusumano
WLWenjie Lu
Wenjie Lu
Vijayan K AsariVijayan K Asari
Vijayan K Asari
The initial framework for an electroencephalography (EEG) thought recognition software suite is developed, built, and tested. This suite is designed to recognize human thoughts and pair them to actions for controlling a robotic arm. Raw EEG brain activity data is collected using an Emotiv EPOC headset. The EEG data is processed through linear discriminant analysis (LDA), where an intended action is identified. The EEG classification suite is being developed to increase the number of distinct actions that can be identified compared to the Emotiv recognition software. The EEG classifier was able to correctly distinguish between two separate physical movements. Future goals for this research include recognition of more gestures, and enabling of real time processing.

23 August 2018 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Closed access
MEMark Joseph Edmonds
Mark Joseph Edmonds
TATanvir Atahary
Tanvir Atahary
SDScott Douglass
Scott Douglass
TTTarek Taha
Tarek Taha
Declarative memory enables cognitive agents to effectively store and retrieve factual memory in real-time. Increasing the capacity of a real-time agent's declarative memory increases an agent's ability to interact intelligently with its environment but requires a scalable retrieval system. This work represents an extension of the Accelerated Declarative Memory (ADM) system, referred to as Hardware Accelerated Declarative Memory (HADM), to execute retrievals on a GPU. HADM also presents improvements over ADM's CPU execution and considers critical behavior for indefinitely running declarative memories. The negative effects of a constant maximum associative strength are considered, and mitigating solutions are proposed. HADM utilizes a GPU to process the entire semantic network in parallel during retrievals, yielding significantly faster declarative retrievals. The resulting GPU-accelerated retrievals show an average speedup of approximately 70 times over the previous Service Oriented Architecture Declarative Memory (soaDM) implementation and an average speedup of approximately 5 times over ADM. HADM is the first GPU-accelerated declarative memory system in existence.

25 November 2019 in arXiv
Verified
Preprint
Open access
PDF file
MEMark Edmonds
Mark Edmonds
XMXiaojian Ma
Xiaojian Ma
SQSiyuan Qi
Siyuan Qi
YZYixin Zhu
Yixin Zhu
HLHongjing Lu
Hongjing Lu
SZSong-Chun Zhu
Song-Chun Zhu
Learning transferable knowledge across similar but different settings is a fundamental component of generalized intelligence. In this paper, we approach the transfer learning challenge from a causal theory perspective. Our agent is endowed with two basic yet general theories for transfer learning: (i) a task shares a common abstract structure that is invariant across domains, and (ii) the behavior of specific features of the environment remain constant across domains. We adopt a Bayesian perspective of causal theory induction and use these theories to transfer knowledge between environments. Given these general theories, the goal is to train an agent by interactively exploring the problem space to (i) discover, form, and transfer useful abstract and structural knowledge, and (ii) induce useful knowledge from the instance-level attributes observed in the environment. A hierarchy of Bayesian structures is used to model abstract-level structural causal knowledge, and an instance-level associative learning scheme learns which specific objects can be used to induce state changes through interaction. This model-learning scheme is then integrated with a model-based planner to achieve a task in the OpenLock environment, a virtual ``escape room'' with a complex hierarchy that requires agents to reason about an abstract, generalized causal structure. We compare performances against a set of predominate model-free reinforcement learning(RL) algorithms. RL agents showed poor ability transferring learned knowledge across different trials. Whereas the proposed model revealed similar performance trends as human learners, and more importantly, demonstrated transfer behavior across trials and learning situations.