Hi, I'm Zulfiqar, a PhD Robotics student at Georgia Institute of Technology.
Introduction
I am a 2nd year Robotics PhD student in CORE Robotics Lab (led by Dr. Matthew Gombolay). My research interests include agile robotics, human-robot interaction and imitation learning. Specifically, I hope to create agile mobile robots that can intelligently collaborate with humans. I envision a future where agile robots closely partner with human beings while being completely safe.
Prior to starting my PhD, I worked as a Research Engineer at Keeptruckin, where I developed algorithms to detect dangerous driving behaviours such as close following, hard braking, and high-speed cornering. I previously received a M.S. in Mechanical Engineering with a concentration in Robotics and Controls from Georgia Institute of Technology in 2020, and a B.Sc. in Mechanical Engineering from NUST in 2017.
Publications
Athletic Mobile Manipulator System for Robotic Wheelchair Tennis
Zulfiqar Zaidi*, Daniel Martin*, Nathaniel Belles, Viacheslav Zakharov, Arjun Krishna, Kin Man Lee, Peter Wagstaff, Sumedh Naik, Matthew Sklar, Sugju Choi, Yoshiki Kakehi, Ruturaj Patil, Divya Mallemadugula, Florian Pesce, Peter Wilson, Wendell Hom, Matan Diamond, Bryan Zhao, Nina Moorman, Rohan Paleja, Letian Chen, Esmaeil Seraj, and Matthew Gombolay
(accepted at RA-L, 2023)
We present ESTHER, a robotic platform consisting of a high-speed Barrett WAM arm, motorized regulation sports wheelchair, and a decentralized vision system for autonomously playing tennis against a human opponent on a regulation tennis court. The goal of this paper is to (1) inspire more research in human-scale robot athletics and (2) establish the first baseline for a reproducible wheelchair tennis robot for regulation singles play.
Enhancing Safety in Learning from Demonstration Algorithms via Control Barrier Function Shielding
Yue Yang*, Letian Chen*, Zulfiqar Zaidi*, Sanne van Waveren, Arjun Krishna, and Matthew Gombolay
(accepted at HRI 2024, acceptance rate: 24.9%)
In this work, we propose a new framework, ShiElding with Control barrier fUnctions in inverse REinforcement learning (SECURE), which learns a customized Control Barrier Function (CBF) from end-users that prevents robots from taking unsafe actions while imposing little interference with the task completion. We evaluate SECURE in three sets of experiments. First, we empirically validate SECURE learns a high-quality CBF from demonstrations and outperforms conventional LfD methods on simulated robotic and autonomous driving tasks with improvements on safety by up to 100%. Second, we demonstrate that roboticists can leverage SECURE to outperform conventional LfD approaches on a real-world knife-cutting, meal-preparation task by 12.5% in task completion while driving the number of safety violations to zero. Finally, we demonstrate in a user study that non-roboticists can use SECURE to effectively teach the robot safe policies that avoid collisions with the person and prevent coffee from spilling.
Multi-Camera Asynchronous Ball Localization and Trajectory Prediction with Factor Graphs and Human Poses
Qingyu Xiao, Zulfiqar Zaidi, and Matthew Gombolay
(accepted at ICRA 2024, acceptance rate: 44.8%)
In this work, we focus on advancing agile robotics in highly dynamic and interactive environments, specifically targeting the realm of ball sports. These sports, exemplified by tennis, are characterized by high-speed ball movements and complex dynamics, including the Magnus effect, which significantly complicates trajectory prediction. We propose an innovative approach that combines a multi-camera system with factor graphs for real-time and asynchronous 3D tennis ball localization. Additionally, we estimate hidden states like velocity and spin for trajectory prediction. Furthermore, to enhance spin inference early in the ball’s flight, where limited observations are available, we integrate human pose data using a temporal convolutional network (TCN) to compute spin priors within the factor graph. This refinement provides more accurate spin priors at the beginning of the factor graph, leading to improved early-stage hidden state inference for prediction
The Effect of Robot Skill Level and Communication in Rapid, Proximate Human-Robot Collaboration
Kin Man Lee*, Arjun Krishna*, Zulfiqar Zaidi, Rohan Paleja, Letian Chen, Erin Hedlund-Botti, Mariah Schrum, and Matthew Gombolay
(accepted at HRI 2023, acceptance rate: 25.2%)
In this work, we aim to enable the deployment of safe and trustworthy agile robots that operate in proximity with humans. We do so by 1) Proposing a novel human-robot doubles table tennis scenario to serve as a testbed for studying agile, proximate human-robot collaboration and 2) Conducting a user-study to understand how attributes of the robot (e.g., robot competency or capacity to communicate) impact team dynamics, perceived safety, and perceived trust, and how these latent factors affect human-robot collaboration (HRC) performance.
Utilizing Human Feedback for Primitive Optimization in Wheelchair Tennis
Arjun Krishna, Zulfiqar Zaidi, Letian Chen, Rohan Paleja, Esmaeil Seraj, and Matthew Gombolay
(accepted at CoRL-W 2022 - Learning for Agile Robots)
We consider the problem of building a flexible and adaptive controller for a challenging agile mobile manipulation task of hitting ground strokes on a wheelchair tennis robot. We propose and evaluate an extension to work done on learning striking behaviors using a probabilistic movement primitive~(ProMP) framework by (1) demonstrating the safe execution of learned primitives on an agile mobile manipulator setup, and (2) proposing an online primitive refinement procedure that utilizes evaluative feedback from humans on the executed trajectories.
LANCON-LEARN: Learning with Language to Enable Generalization in Multi-Task Manipulation
Andrew Silva , Nina Moorman, William Silva, Zulfiqar Zaidi, Nakul Gopalan, and Matthew Gombolay
(accepted at ICRA 2022 and RA-L)
We introduce a novel attention-based approach to language-conditioned multi-task learning in manipulation domains to enable learning agents to reason about relationships between skills and task objectives through natural language and interaction.
M.S. Thesis
ROS Based Teleoperation and Docking of a Low Speed Urban Vehicle
Zulfiqar Zaidi (advised by Dr. Bert Bras, Sustainable Design and Manufacturing Lab)
(In partial fulfillment of the requirements for the degree Master of Science in the School of Mechanical Engineering, Georgia Tech)
This study seeks to build a teleoperated system using the ROS framework which employs the 4G LTE network for communication. For this purpose, a prototype system is built using a remote-controlled low speed urban vehicle that hosts a multimedia link between the vehicle and the control station. The operator drives the vehicle remotely primarily based on processed video feed and LIDAR data. The teleoperated system built is tested by asking an experienced driver to complete certain tasks while driving the vehicle remotely. Moreover, this study also introduces an autonomous docking procedure based on differential GPS and video feedback that allows the vehicle to autonomously dock itself into a charging station, providing a proof-of- concept solution for autonomous charging/fueling of self-driving cars.
