Black in Robotics - Student and Postdoc Conference Travel Reimbursements

The BiR student and postdoc conference travel awards provide travel expense reimbursements to eligible students or postdocs enrolled in schools in the United States for up to $2000 per applicant.

Link to Applications for Awards for Conferences attended/attending:

https://forms.gle/M7kHjRPQSuo1pDAA6

Application Deadlines:

Applications are reviewed quarterly:

  • 2nd week of January

  • 2nd week of April

  • 2nd week of July

  • 2nd week of October

Eligibility

  • Must be actively enrolled in a higher education academic institution within the United States, and have a valid academic institution email address (both undergraduate and graduate (masters, doctorate) students, and postdocs are eligible)

  • Must be a current member of Black in Robotics (https://blackinrobotics.org/join-us) and an enrolled participant in the BiR resume book (https://resumebook.blackinrobotics.org/)

  • Must have an accepted publication at a robotics-related conference, and provide evidence of publication (poster, workshop paper, or conference paper)

  • Reimbursement would occur after the conference, and the awardee must retain all receipts for reimbursements that are itemized with proof of payment (card number should be redacted, but charge shown). (If applicable, the paying advisor or administrator's contact information must also be provided for validation) - Awards for finalists will reflect the valid, submitted receipts for reimbursement

Reimbursements support:

  1. Conference registration, paper submission fees and other student fees (e.g. conference dinner)

  2. Conference-related transportation reimbursement (ground, air travel)

  3. Hotel/Lodging reimbursement

  4. Food reimbursement (excluding alcoholic beverages)

Awardees will be asked to submit all documents for processing their awards either within a month after the award is granted or within a month after their conference (whichever comes later).

Any questions, please contact blackinrobotics@gmail.com

FAQ

  • If my publication has been accepted, but I have not attended the conference yet, can I still apply for this award? A: YES! we will reimburse you up to $2k after the conference conditioned on valid receipts.

  • If I have already attended the conference recently and have retained my receipts, can I still apply for this award? A: YES! These awards are distributed bi-annually, so as long as its been within the current year this is valid!

  • Will the reimbursement funds go to my PI or directly to me? A: Funds will be sent directly to the awardee, who may choose how best to use them.

Past Awardees

Nnamdi Chinomso Chikere

Graduate Student at The University of Notre Dame

Award Date: October 2024

Conference: 2024 The International Symposium on Distributed Autonomous Robotic Systems (DARS)

Publication Title: “Swarm of Bioinspired Legged Robots for Collective Object Transport“

Publication Summary: Our research presents a bioinspired multi-robot system that emulates cooperative behaviors observed in nature, like ants collectively transporting food. Unlike previous studies focused on wheeled robots or simulations, we use legged robots for enhanced mobility across complex terrains. Each robot is equipped with mechanically coupled legs and a dynamic control system, enabling adaptive, energy-efficient movement and resilience to individual failures. Using a hybrid control approach, a designated leader provides initial coordination, with each robot making independent adjustments to maintain transport alignment. This structure allows for seamless leadership changes to adapt to new paths. In our experiments, teams of legged robots transported objects of varying weights, demonstrating the system’s scalability and robustness. Results show that adding robots increases load capacity and maneuverability. This study contributes to multi-robot transport strategies, offering a scalable, flexible system ideal for real-world applications. Future work will focus on autonomous pathfinding and advanced algorithms for better adaptability in unstructured environments.

Biography: Nnamdi Chikere is an electrical engineering PhD student and an Edison Innovation Fellow at the University of Notre Dame, supervised by Dr. Yasemin Ozkan-Aydin at the Minimalist Naturally-Inspired Robotics Laboratory. His research focuses on bioinspired robotics, creating adaptive systems inspired by natural movement to tackle complex environments. Nnamdi’s projects include a multi-robot system for collective object transport, a sea turtle-inspired robot designed for robust mobility across granular and complex terrains, and flagellated robots modeled after biological organisms like zoospores and algae designed for low Reynolds number environments. His current work investigates how morphology and propulsion mechanics enhance mobility, with applications in environmental monitoring and search and rescue. With a Master’s degree in Electrical Engineering from the University of Notre Dame and a bachelor’s degree in Electrical and Electronic Engineering from Michael Okpara University of Agriculture in Nigeria, Nnamdi is always in pursuit of advancing knowledge and expertise, having developed a comprehensive understanding of engineering principles and a keen technical skill set. In addition to his research, he is deeply committed to mentorship and teaching, aiming to inspire the next generation of engineers and researchers. Nnamdi is open to both academic and industrial roles where he can leverage his expertise to bridge scientific innovation with impactful real-world applications. Outside work, he enjoys music, exploring nature, and playing sports.

Oluwasegun Timothy Akinniyi

Graduate Student at The University of Alabama

Award Date: July 2024

Conference: 2024 IEEE/ASME International Conference on Advanced Intelligent Mechatronics

Publication Title: “Development and Control of a Cable-Driven Robotic Platform for Studying Human Balance and Gait“

Publication Summary: The aging population faces increasing challenges related to mobility, weakness, and fall risk due to neuromuscular and skeletal degeneration. Addressing these challenges, this study focuses on the development and control of a cable-driven robotic platform aimed at studying human balance and gait dynamics. Traditional assistive devices for fall risk mitigation and rehabilitation interventions often have a bulky and complex design. To overcome these limitations, a compact and versatile cable-driven robotic platform capable of delivering precise and safe perturbations to the user's waist region was developed. Central to the platform's design is the integration of a load cell between the cable and a wearable waist belt, enabling real-time measurement of pulling forces. This innovation allows for accurate force tracking during perturbation scenarios, which is essential for assessing balance control mechanisms. To ensure effective force trajectory tracking, a closed-loop adaptive full-state feedback control approach was proposed. This control strategy offers superior performance compared to traditional proportional-integral-derivative (PID) controllers, as demonstrated in the experimental evaluations. This platform will support balance perturbation studies in static and dynamic walking tasks, enhancing human-in-the-loop optimization control research.

Biography: Oluwasegun was born and raised in Lagos, Nigeria. Oluwasegun holds an associate degree in Computer Engineering and both B.Sc. and M.Sc. degrees in Electronic and Electrical Engineering from Obafemi Awolowo University, Nigeria. Currently, Oluwasegun is a Mechanical Engineering PhD student and Graduate Council Fellow at the University of Alabama. My research focuses on Rehabilitation Robotics, bio-instrumentation, and embedded systems. Oluwasegun’s primary interest lies in translating engineering concepts from the workbench to the bedside.

Raechel Dionne Walker

Graduate Student at Massachusetts Institute of Technology

Award Date: March 2024

Conference: The Black Issues in Computing Education (BICE) Symposium

Publication Title: “Unveiling Voices: Boston Students' Data Activism Journey with Community Catalysts“

Publication Summary: A noticeable gap exists in the availability of computing curricula tailored to empower African American students to apply their computing skills for the betterment of their communities. This research applies "liberatory computing'' as a way to empower African American students in addressing embedded racism through computing. An exemplar of this liberatory computing approach is our curriculum on data activism, which uses data science to confront and mitigate systemic oppression. The study engaged 24 high school students of African American descent, who partnered with community organizations in the Greater Boston area for a range of data activism initiatives. These projects encompassed data analysis, geospatial analysis, qualitative analysis, surveys, interviews, artistic expression, and the incorporation of community perspectives. The organizers intend to use the students' projects for advocacy purposes, such as advocating for policies addressing flooding in African American and low-income Boston communities using data visualizations. The student surveys revealed heightened awareness of data science's role in combating racism and enhanced proficiency in promoting racial justice. Interviews with the students revealed that mitigating systemic oppression through their data activism projects with community organizers was a pivotal aspect that motivated them to persist in integrating data activism into their future pursuits. The implications of this research demonstrate how African American students can be empowered to utilize data science in order to catalyze societal transformation. This is achieved by fostering opportunities for them to apply their data science skills to tangible real-life issues through collaboration with community organizations addressing systemic challenges.

Biography: Raechel Walker is currently a PhD Candidate in the Personal Robots Group within the Department of Media Arts and Sciences. Her research is primarily centered on AI education, with a specific focus on the concept of "liberatory computing" for minoritized communities. Her work on data activism has gained recognition and been featured in the MIT News, The Concord Bridge, the Day of AI, and the #CSK8 Podcast by Jared O’Leary.

Surafel Tesfaye Anshebo

Graduate Student at Virginia Tech

Award Date: March 2024

Conference: Xponential 2024

Publication Title: “Comparative Study of Vision-Based Methods for Real-Time Traffic Monitoring“

Publication Summary: This paper delves into a comprehensive examination of the performance disparities between traditional computer vision algorithms and deep learning algorithms when applied to the task of vehicle traffic monitoring. It focuses on detection and tracking vehicles, an essential component for real-time monitoring and management systems. Specifically, the study scrutinizes the efficacy of two traditional algorithms, Haar Cascade and SORT, alongside two deep learning algorithms, namely YOLOv5 and Deep SORT.

Biography: Surafel is a first-year master’s student pursuing a degree in Mechanical Engineering and advised by Professor Kochersberger. Surafel’s interests have always been in robotics and perception.

Obumneme Godson Osele

Graduate Student at Stanford University

Award Date: March 2024

Conference: IEEE International Conference on Robotics and Automation (ICRA) 2024

Publication Title: “Tip-Clutching Winch for High Tensile Force Application with Soft Growing Robots“

Publication Summary: The navigational abilities of tip-everting soft-growing robots, known as vine robots, are compromised when tip-mount devices are added to enable the carrying of payloads. We present a new method for securing a vine robot to objects or its environment that exploits the unique eversion-based growth mechanism and flexibility of vine robots, while keeping the tip of the vine robot free of encumbrance. Our implementation is a tip-clutching winch, into which vine robots can insert themselves and anchor to via powerful overlapping belt friction. The device enables passive, high-strength, and reversible fastening, and can easily release the vine robot. This approach enables the carrying of loads of at least 28 kg (limited by the tensile strength of the vine robot body material and winch actuator torque capacity), as well as novel material transport and locomotion capabilities.

Biography: Obumneme Godson Osele (he/him) is a Mechanical Engineering PhD candidate at Stanford University. His research interests include developing cost-efficient robots exploiting under-actuated, reconfigurable, and soft robotic designs outfitted with innovative sensors to aid human-robot collaboration. Additional research interests include translating cost-efficient robots into low-resource settings as well as expanding the accessibility of robotics technology and curricula. He is a Ford Foundation Predoctoral Fellow, EDGE Fellow, GEM Associate Fellow, SystemX Robotics DEI Fellow, and a Stanford RAISE Fellow. He also holds a BS in Biomedical Engineering and MS in Mechanical Engineering from Northwestern University.

Jordan Lekeufack Sopze

Graduate Student at UC Berkeley

Award Date: March 2024

Conference: 2024 IEEE International Conference on Robotics and Automation

Publication Title: “Conformal Decision Theory: Safe Autonomous Decisions Without Distributions“

Publication Summary: We introduce Conformal Decision Theory, a framework for producing safe autonomous decisions despite imperfect machine learning predictions. Examples of such decisions are ubiquitous, from robot planning algorithms that rely on pedestrian predictions, to calibrating autonomous manufacturing to be high throughput but low error, to the choice of trusting a nominal policy versus switching to a safe backup policy at run-time. The decisions produced by our algorithms are safe in the sense that they come with provable statistical guarantees of having low risk without any assumptions on the world model whatsoever; the observations need not be I.I.D. and can even be adversarial. The theory extends results from conformal prediction to calibrate decisions directly, without requiring the construction of prediction sets. Experiments demonstrate the utility of our approach in robot motion planning around humans, automated stock trading, and robot manufacturing.

Biography: Born and raised in Cameroon, I pursued my undergraduate studies at École Polytechnique in France before joining UC Berkeley for a PhD in Statistics. My research focuses on the applications of conformal predictions to decision-making processes, with a particular interest in robot navigation.

Hafiz Oyediran

Graduate Student at the Univerisity of Nebraska-Lincoln

Award Date: January 2024

Conference: ASCE Construction Research Conference

Publication Title: “Information Modeling for 4D BIM-based Construction Robot Task Planning and Simulation“

Publication Summary: The integration of robotics technology with Building Information Modelling (BIM) to plan robot operations is a promising approach for automating construction tasks. While 4D BIM-related technologies are arguably the most advanced method of planning for construction projects, they lack adequate elemental information required by a robot to plan its operations within the spatiotemporal context of the construction site. This poses a challenge to planning robot operations for construction tasks considering their spatial coordination with human workers and site conditions. This study identifies the information required in 4D BIM for planning and simulating construction robot operations. A Robot Operating System based software program was developed to demonstrate the utilization of this information in the planning and simulation of construction robot operations. The program was evaluated in a simulated construction environment, employing a Husky mobile robot to install drywall boards using information from 4D BIM. The simulation demonstrates the importance of information modeling in the integration of 4D BIM with robotics technologies for the planning and execution of construction tasks.

Biography: Hafiz is currently a Ph.D. Candidate in the Department of Construction Engineering and Management at the Durham School of Architectural Engineering and Construction, College of Engineering at the University of Nebraska-Lincoln. Hafiz’s PhD research focuses on the integration of robotics technologies with building information modeling (BIM) for construction task planning and execution. Hafiz is currently working on studies that focus on the safe planning of robot operations in the execution of tasks considering the dynamic nature of construction sites. Hafiz’s research interest includes robotics applicability in construction, Building Information Modeling, and the use of virtual, augmented, and mixed reality for construction engineering and management. Before starting his Ph.D., Hafiz worked in numerous roles as an intern structural engineer, site supervisor, and project manager. Hafiz holds an MSc in Construction Management and a BSc in Building from the University of Lagos, Nigeria. Furthermore, Hafiz possesses a Higher Diploma and a National Diploma in Civil Engineering Technology from Lagos State Polytechnic, Lagos, Nigeria. Hafiz is also a director of an NGO that was co-founded with friends for the advocacy of BIM adoption in Africa called the "BIM Africa Initiative". The organization has grown to be one of the most pronounced in terms of BIM advocacy and adoption in Africa.

Elijah Johnson

Graduate Student at the Massachusetts Institute of Technology

Award Date: January 2024

Conference: Black Issues in Computing Education

Publication Title: “Unveiling Voices: Boston Students' Data Activism Journey with Community Catalysts“

Publication Summary: A noticeable gap exists in the availability of computing curricula tailored to empower African American students to apply their computing skills for the betterment of their communities. This research applies "liberatory computing'' as a way to empower African American students in addressing embedded racism through computing. An exemplar of this liberatory computing approach is our curriculum on data activism, which uses data science to confront and mitigate systemic oppression. The study engaged 24 high school students of African American descent, who partnered with community organizations in the Greater Boston area for a range of data activism initiatives. These projects encompassed data analysis, geospatial analysis, qualitative analysis, surveys, interviews, artistic expression, and the incorporation of community perspectives. The organizers intend to use the students' projects for advocacy purposes, such as advocating for policies addressing flooding in African American and low-income Boston communities using data visualizations. The student surveys revealed heightened awareness of data science's role in combating racism and enhanced proficiency in promoting racial justice. Interviews with the students revealed that mitigating systemic oppression through their data activism projects with community organizers was a pivotal aspect that motivated them to persist in integrating data activism into their future pursuits. The implications of this research demonstrate how African American students can be empowered to utilize data science in order to catalyze societal transformation. This is achieved by fostering opportunities for them to apply their data science skills to tangible real-life issues through collaboration with community organizations addressing systemic challenges.

Biography: Elijah Johnson is a second-year undergraduate student at the Massachusetts Institute of Technology (MIT), pursuing a dual degree in Artificial Intelligence and Decision Making and Mathematics. His academic journey is complemented by active research in the Personal Robots Group at the MIT Media Lab, under the mentorship of Raechel Walker.

Abriana Stewart-Height

Graduate Student at the University of Pennsylvania

Award Date: October 2023

Conference: International Symposium on Experimental Robotics

Publication Title: “Limb-Loss Recovery Gaits and Their Energetic Cost“

Publication Summary: This work addresses the challenge of fault recovery from limb-loss by employing novel dynamical gaits. We demonstrate empirically a stable tripedal dynamic gait on the Ghost Robotics Minitaur platform. This pronking gait achieves comparable speeds to those on the intact quadrupedal machine. In consequence, despite substantially higher energetic expenditure per stride, it's CoT is reduced by ~10% - 15% relative to that of its slower quasi-static tripedal walking alternative.

Biography: Abriana Stewart-Height is a PhD student in the Department of Electrical & Systems Engineering and a member of the General Robotics, Automation, Sensing and Perception lab at the University of Pennsylvania. Prior to Penn, she received a Bachelor of Science in Electrical Engineering at the University of Maryland. Her current research focuses on limb failure in legged robots and how they can adapt to limb damage while working in complex outdoor environments. Outside of research, she enjoys playing basketball, roller skating, and learning foreign languages.

De'Aira Gladys Bryant

Graduate Student at Georgia Institute of Technology

Award Date: October 2023

Conference: IEEE International Conference on Robot and Human Communication (RO-MAN) 2023

Publication Title: “Teaching a Robot Where to Park: A Scalable Crowdsourcing Approach“

Publication Summary: For social robots to successfully integrate into daily life in home environments, they will need reliable models of the way people perceive and use space in the home. This paper explores the problem of obtaining annotated training data at scale for subjective judgments about spatial locations. Focusing on the use case of identifying good and bad parking spots for a social robot operating in a home environment, two experiments are presented. The first study shows that the presentation of context-rich 3D images to human annotators yields notably different outcomes from those obtained when using 2D robot navigation maps. We attribute the source of these differences to a set of features visible only in the 3D views and introduce a technique for labeling these features on the 2D maps. The second study reveals that using labeled 2D maps produces annotation data very similar to that obtained using 3D images. Since a labeled 2D map can be generated at a fraction of the cost of a full set of 3D views, we recommend this method as a scalable approach to collecting subjective spatial data annotations in everyday environments.

Biography: De’Aira Bryant is a computer science doctoral candidate in the College of Computing at the Georgia Institute of Technology. Her work in the Human Automation Systems (HumAnS) lab spans the fields of human-robot interaction, affective computing, and AI ethics. In particular, she explores and highlights how bias-aware robots enhance the possibilities for interactive communication with humans. De’Aira is a National Science Foundation GRFP, GEM, SLOAN, and Amazon fellow where she has most recently interned as a research scientist in Consumer Robotics working on Astro. Most proudly, De’Aira is a passionate advocate for equitable access to computing education and enjoys creating online media content to inspire the next generation of computer scientists and roboticists.

Jasmin Elena Palmer

Ph.D. Student in Mechanical Engineering, Stanford University. Member of the CHARM Lab

Award Date: December 2022

Conference: The 2022 IEEE/RSJ International Conference on Intelligent Robots And Systems (IROS 2022)

Publication Title: “Haptic Feedback Relocation from the Fingertips to the Wrist for Two-Finger Manipulation in Virtual Reality“

Publication Summary: Relocation of haptic feedback from the fingertips to the wrist has been considered as a way to enable haptic interaction with mixed-reality virtual environments while leaving the fingers free for other tasks. We present a pair of wrist-worn tactile haptic devices and a virtual environment to study how various mappings between fingers and tactors affect task performance. The haptic feedback rendered to the wrist reflects the interaction forces occurring between a virtual object and virtual avatars controlled by the index finger and thumb. We performed a user study comparing four different finger-to-tactor haptic feedback mappings and one no-feedback condition as a control. We evaluated users’ ability to perform a simple pick-and-place task via the metrics of task completion time, path length of the fingers and virtual cube, and magnitudes of normal and shear forces at the fingertips. We found that multiple mappings were effective, and there was a greater impact when visual cues were limited. We discuss the limitations of our approach and describe next steps toward multi-degree-of-freedom haptic rendering for wrist-worn devices to improve task performance in virtual environments.

Biography: Jasmin earned a Bachelor of Science in Mechanical Engineering with a concentration in Controls, Instrumentation, and Robotics at the Massachusetts Institute of Technology (MIT) and a Master of Science in Mechanical Engineering at Stanford University. Jasmin is currently pursuing her Ph.D. in Mechanical Engineering at Stanford University and conducting research with faculty supervisor Professor Allison Okamura in the Collaborative Haptics in Robotics in Medicine (CHARM) Lab. Jasmin’s Ph.D. research centers around human-computer interaction and haptics, the science of and relating to the sense of touch. Developing technology that provides beneficial haptic feedback to human operators requires a multi-pronged and interdisciplinary approach. Her work leverages concepts from psychology and neuroscience to understand human perception, experimental design, and statistical analysis, and also applies her engineering background in dynamic modeling of physical systems and mechatronic system development in order to develop novel designs for wearable devices. The goal of her thesis is to develop an adaptable simulation framework that provides realistic haptic feedback for humans to perform various dexterous manipulation tasks in dynamic virtual reality (VR) and mixed reality (MR) environments using wrist-worn tactile devices. Jasmin wants to become an inspiration for other women of color to pursue careers in STEM fields. Jasmin also enjoys composing music, playing the flute, and studying foreign languages.

Andre Cleaver

PhD Student at Tufts University

Award Date: March 2023

Conference: ACM/IEEE 2023 International Conference on Human-Robot Interaction

Publication Title: “Helping Humans Become Better Teachers for Robots with Augmented Reality“

Publication Summary: We demonstrate TRAinAR, an augmented reality (AR)-based tool that is designed to improve sim2real reinforcement learning for robots. TRAinAR aims to enable users to train a robot by quickly prototyping complex environments in a virtual training environment with constraints to match the real-world. TRAinAR also allows a user to visualize the robot's training data in context of the environment which can provide insights into ways to improve the robot's training process. In this paper, we propose a human-participant study to evaluate TRAinAR as a valuable training tool. The proposed user study will help humans better identify ways to teach and improve a robot's learning process. In a technical demonstration, our application enabled a robotic arm manipulator to learn how to navigate its end-effector toward a goal object while implicitly learning to avoid obstacles.

Biography: Andre Cleaver is in the field of human-robot interaction, currently pursuing his Ph.D. in Mechanical Engineering at Tufts University. Originally from San Antonio, he received his Bachelor of Science in Biomedical Engineering from the University of Texas San Antonio in 2016 before moving to Medford, Massachusetts, to obtain his Master's in Mechanical Engineering from Tufts in 2018. His Ph.D. graduate studies at Tufts, under the guidance of Jivko Sinapov, focus on exploring how augmented reality (AR) can improve human-robot interactions. Specifically, Andre is investigating how AR can help robots convey their perception of the world to humans in a more instinctual way. He aims to present information visually, which can help people connect what they see with what the robot perceives. Currently, Andre is writing his Ph.D. dissertation on human-robot interaction, with a particular emphasis on teaching humans to provide information to robots using reinforcement learning. His goal is to provide adaptive visualization tools such as TRAinAR to help users identify functions the robot excels in and teach the robot new skills utilizing reinforcement learning in an AR environment. Recently, he won the Best Video award at the 2023 International Conference of Human Robot Interaction in Stockholm, Sweden, where he demonstrated the use of TRAinAR to confine a robot to a specific region by confinements set in an AR environment. Looking ahead, Andre is determined to apply his Ph.D. research to enable anyone, regardless of their expertise, to interact with robots in a safe and intuitive manner.

Naome Etori

PhD student at the University of Minnesota -Twin Cities

Award Date: March 2023

Conference: AAAI-23 conference in Washington, DC.

Publication Title: “What We Know So Far: Artificial Intelligence in African Healthcare“

Publication Summary: Healthcare in Africa is a complex issue influenced by many factors including poverty, lack of infrastructure, and inadequate funding. However, Artificial intelligence (AI) applied to healthcare, has the potential to transform healthcare in Africa by improving the accuracy and efficiency of diagnosis, enabling earlier detection of diseases, and supporting the delivery of personalized medicine. This paper reviews the current state of how AI Algorithms can be used to improve diagnostics, treatment, and diseases monitoring, as well as how AI can be used to improve access to healthcare in Africa as a low-resource setting and discusses some of the critical challenges and opportunities for its adoption. As such, there is a need for a well-coordinated effort by the governments, private sector, healthcare providers, and international organizations to create sustainable AI solutions that meet the unique needs of the African healthcare system.

Biography: Naome Etori is a second-year PhD student at the University of Minnesota – Twin Cities working in Professor Maria Gini's lab for artificial intelligence and robotics. Her research interests are in artificial intelligence (AI), natural language processing (NLP), and their intersection with business and healthcare applications to low resource settings, as well as decision-making that is inclusive of all people and promotes development toward a society where everyone can thrive. Also, she is intrigued by issues related to ethics in computational social science and human-machine interaction. In her leisure time, she mentors a number of students, particularly those from marginalized communities, and links them to resources and scholarship possibilities, many of which are focused on computing and other STEM subjects. Additionally, she is personally dedicated to inspiring women and people of color to pursue careers in STEM professions like computing.

Jasmine Berry

Postdoctoral Fellow - University of Michigan

Award Date: August 2023

Conference: IEEE RO-MAN 2023

Publication Title: “A Case of Identity: Enacting Robot Identity with Belief Propagation for Decentralized Multi-Agent Task Allocation“

Publication Summary: Advancements in autonomous agents have led to an increasingly ubiquitous presence of robots in human environments where social and physical interaction is expected. Such environments are often composed of heterogeneous agents with disparate action capabilities, intentions, and motivations. Intra- and inter-agent dissimilarity often prevents enacting effective behavioral skills (e.g., collaboration, communication, coordination) towards dynamic task allocation objectives. We propose a Bayesian probabilistic inference approach, Multi-Robot Belief Propagation with Identity constraints (MRPB-I), for 1) decentralized task allocation in multi-agent systems and 2) modeling task affinity using personal identities. MRPB-I leverages competing costs of individual and group capabilities that result in less error-prone convergence to steady state, scalability without loss of accuracy, and sensitivity to environmental dynamics. An implementation of MRBP-I as a distributed algorithm that weighs factors of both individual and cooperative perception in an energy-minimizing task allocation scheme is presented.

Biography: Dr. Jasmine Berry, Neuro-AI researcher, actively works to model the science of human cognition for advanced computational machines and robotics using artificial intelligence. She received her B.S. degree in Computer Science from Norfolk State University. Then she pursued Master's and Ph.D. degrees in Computer Science from the University of Southern California, with a dissertation topic on “Sensorimotor Body Representations for Neuro-Robotic Systems.” Her research was sponsored by the GEM Consortium Graduate Fellowship and Viterbi Doctoral Fellowship. Presently, Dr. Berry is a Computing Innovations (CI) Fellow at the University of Michigan’s Laboratory of Progress where she is developing cognitive models for robotic agents to learn self-awareness via social interactions. She is also engaged in local volunteer efforts to bridge the educational resource gap by empowering K-12 students to master STEM and motivate them to succeed academically and professionally.