About

Ph.D. student in the Computer Science program at Rice University, working under the direction of Dr. Lydia Kavraki. I received my Bachelors of Science in Computer Science from Rice in Spring 2016. My research interest is in algorithmic robotics, focused on solving the difficulties in motion planning that arise in robotic manipulation.

"zak" rice.edu / Duncan Hall 3052

Github / Google Scholar / ResearchGate


Research & Experience

Kavraki Lab @ Rice University

I am a currently Ph.D. student at the Kavraki Robotics Lab at Rice University, working on the problems that arise in robotic motion planning with geometric constraints.


Dexterous Robotics Lab @ NASA JSC
We are in collaboration with NASA Johnson Space Center's Dexterous Robotics Lab, where I have developed constrained motion planning on NASA’s humanoid robot Robonaut 2.

MRSL @ Rice University
I used to work in the Multi-Robot Systems Lab (MRSL) at Rice University, working on multi-robot manipulation.

Publications

[1]

W. Baker, Z. Kingston, M. Moll, J. Badger, and L. Kavraki. Robonaut 2 and You: Specifying and Executing Complex Operations

Abstract / BibTeX / Paper / Video

Crew time is a precious resource due to the expense of trained human operators in space. Efficient caretaker robots could lessen the manual labor load required by frequent vehicular and life support maintenance tasks, freeing astronaut time for scientific mission objectives. Humanoid robots can fluidly exist alongside human counterparts due to their form, but they are complex and high-dimensional platforms.

This paper describes a system that human operators can use to maneuver Robonaut 2 (R2), a dexterous humanoid robot developed by NASA to research co-robotic applications. The system includes a specification of constraints used to describe operations, and the supporting planning framework that solves constrained problems on R2 at interactive speeds. The paper is developed in reference to an illustrative, typical example of an operation R2 performs to highlight the challenges inherent to the problems R2 must face. Finally, the interface and planner is validated through a case-study using the guiding example on the physical robot in a simulated microgravity environment. This work reveals the complexity of employing humanoid caretaker robots and suggest solutions that are broadly applicable.

Close

@inproceedings{Baker2017,
  author = {Baker, W. and Kingston, Z. and Moll, M. and Badger, J. and Kavraki, L.},
  title = {Robonaut 2 and You: Specifying and Executing Complex Operations},
  booktitle = {IEEE Workshop on Advanced Robotics and its Social Impacts},
  year = {2017},
}

Close

[2]

N. Dantam, Z. Kingston, S. Chaudhuri, and L. Kavraki. Incremental Task and Motion Planning: A Constraint-Based Approach

Abstract / BibTeX / Paper / Publisher / Video

We present a new algorithm for task and motion planning (TMP) and discuss the requirements and abstractions necessary to obtain robust solutions for TMP in general. Our Iteratively Deepened Task and Motion Planning (IDTMP) method is probabilistically-complete and offers improved performance and generality compared to a similar, state-of-the-art, probabilistically-complete planner. The key idea of IDTMP is to leverage incremental constraint solving to efficiently add and remove constraints on motion feasibility at the task level. We validate IDTMP on a physical manipulator and evaluate scalability on scenarios with many objects and long plans, showing order-of-magnitude gains compared to the benchmark planner and a four-times self-comparison speedup from our extensions. Finally, in addition to describing a new method for TMP and its implementation on a physical robot, we also put forward requirements and abstractions for the development of similar planners in the future.

Close

@inproceedings{Dantam2016,
  author = {Dantam, N. and Kingston, Z. and Chaudhuri, S. and Kavraki, L.},
  title = {Incremental Task and Motion Planning: A Constraint-Based Approach},
  booktitle = {Robotics: Science and Systems},
  year = {2016},
}

Close

[3]

Z. Kingston, N. Dantam, and L. Kavraki. Kinematically Constrained Workspace Control via Linear Optimization.

Abstract / BibTeX / Paper / Poster / Publisher / Video

We present a method for Cartesian workspace control of a robot manipulator that enforces joint-level acceleration, velocity, and position constraints using linear optimization. This method is robust to kinematic singularities. On redundant manipulators, we avoid poor configurations near joint limits by including a maximum permissible velocity term to center each joint within its limits. Compared to the baseline Jacobian damped least-squares method of workspace control, this new approach honors kinematic limits, ensuring physically realizable control inputs and providing smoother motion of the robot. We demonstrate our method on simulated redundant and non-redundant manipulators and implement it on the physical 7-degree-of-freedom Baxter manipulator. We provide our control software under a permissive license.

Close

@inproceedings{Kingston2015,
  author = {Kingston, Z. and Dantam, N. and Kavraki, L.},
  booktitle = {International Conference on Humanoid Robots},
  title = {Kinematically Constrained Workspace Control via Linear Optimization},
  year = {2015},
}

Close

[4]

G. Habibi, Z. Kingston, Z. Wang, M. Schwager, and J. McLurkin. Pipelined Consensus for Global State Estimation in Multi-Agent Systems.

Abstract / BibTeX / Paper / Publisher

This paper presents pipelined consensus, an extension of pair-wise gossip-based consensus, for multi-agent systems using mesh networks. Each agent starts a new consensus in each round of gossiping, and stores the intermediate results for the previous k consensus in a pipeline message. After k rounds of gossiping, the results of the first consensus are ready. The pipeline keeps each consensus independent, so any errors only persist for k rounds. This makes pipelined consensus robust to many real-world problems that other algorithms cannot handle, including message loss, changes in network topology, sensor variance, and changes in agent population. The algorithm is fully distributed and self-stabilizing, and uses a communication message of fixed size. We demonstrate the efficiency of pipelined consensus in two scenarios: computing mean sensor values in a distributed sensor network, and computing a centroid estimate in a multi-robot system. We provide extensive simulation results, and real-world experiments with up to 24 agents. The algorithm produces accurate results, and handles all of the disturbances mentioned above.

Close

@inproceedings{Habibi2015a,
  author = {Habibi, G. and Kingston, Z. and Wang, Z. and Schwager, M. and McLurkin, J.},
  booktitle = {International Conference on Autonomous Agents and Multiagent Systems},
  title = {Pipelined Consensus for Global State Estimation in Multi-Agent Systems},
  year = {2015},
}

Close

[5]

G. Habibi, Z. Kingston, W. Xie, M. Jellins, and J. McLurkin. Distributed Centroid Estimation and Motion Controllers for Collective Transport by Multi-Robot Systems.

Abstract / BibTeX / Paper / Publisher / Video

This paper presents pipelined consensus, an extension of pair-wise gossip-based consensus, for multi-agent systems using mesh networks. Each agent starts a new consensus in each round of gossiping, and stores the intermediate results for the previous k consensus in a pipeline message. After k rounds of gossiping, the results of the first consensus are ready. The pipeline keeps each consensus independent, so any errors only persist for k rounds. This makes pipelined consensus robust to many real-world problems that other algorithms cannot handle, including message loss, changes in network topology, sensor variance, and changes in agent population. The algorithm is fully distributed and self-stabilizing, and uses a communication message of fixed size. We demonstrate the efficiency of pipelined consensus in two scenarios: computing mean sensor values in a distributed sensor network, and computing a centroid estimate in a multi-robot system. We provide extensive simulation results, and real-world experiments with up to 24 agents. The algorithm produces accurate results, and handles all of the disturbances mentioned above.

Close

@inproceedings{Habibi2015b,
  author = {Habibi, G. and Kingston, Z. and Xie, W. and Jellins, M. and McLurkin, J.},
  booktitle={IEEE International Conference on Robotics and Automation},
  title={Distributed Centroid Estimation and Motion Controllers for Collective Transport by Multi-Robot Ssystems},
  year={2015},
}

Close


Teaching & Outreach

COMP 450/550

I was a TA for COMP 450/550, Algorithmic Robotics, in the Fall 2016 semester. COMP 450 is an introductory robotics course focused on motion planning and AI algorithms, ranging from simple cell decomposition methods to sampling-based planning.

MANA de Tejas Gulf Coast

I gave an presentation on the basics of robotics with Dr. Mark Moll to a group from MANA, a national Latina organization. Read about it in the Rice at Large publication.

COMP 140

I was an in-class TA for COMP 140, Introduction to Computational Thinking, in the Fall 2015 semester. COMP 140 is unique as it is a flipped classroom, where lectures are given through videos outside of class, and class-time is spent with hands-on exercises.

COMP 321

I was an in-lab TA for COMP 321, Introduction to Computer Systems, in the Spring 2015 semester. COMP 321 in an introductory systems course, using the C programming language to impart deeper knowledge of how modern computer systems operate.

Chicago MSI

I worked in a consultant position with Dr. James McLurkin, for the Chicago Museum of Science and Industry (MSI). The MSI was creating the Robot Revolution Exhibit, and the r-one robot was featured! Participants in the exhibit could use a control station on the side of an arena hosting multiple robots to command the r-ones to move in distributed swarm behaviors, such as clustering, follow-the-leader, and flocking.

ENGI 128

I was a TA for ENGI 128, Introduction to Engineering Systems, in the Fall 2014 Semester. This course is freshman-only, fun-filled introduction to concepts in mechanical engineering, electrical engineering, and computer science. The course used the r-one robot, an inexpensive robot developed by the MRSL.

Summer Swarm Camp

I was a TA for the Summer Swarm Robot Camp hosted by the MRSL. The camp was designed for middle school and high school students in the community interested in robotics and computer science to get a hands-on experience working with a robot and programming its behavior. The camp used the r-one robot, and the Python programming language.


Awards

NSTRF

I accepted the NASA Space Technology Research Fellowship. Read about it in the Rice Engineering News.

NSF GRFP

I was awarded the National Science Foundation's Graduate Research Fellowship. Read about it in the Rice Computer Science News. There was also an interview.

CS GRF

I was awarded the Graduate Research Fellowship for Rice Undergraduates by the Rice Computer Science Department.

Distinction in Research

I was awarded the Distinction in Research and Creative Works.


Miscellaenous

Coroga

An experiment with three.js to procedurally generate aesthetically pleasing rock gardens. Check it out! Code is on Github.