top of page

Nick Mohammad

  • LinkedIn

I am a 4th year PhD student in Computer Engineering at the University of Virginia. I work in the Autonomous Mobile Robots Lab (AMR) and Link Lab under Prof. Nicola Bezzo. I received both my B.S. in Computer Engineering and M.S. in Computer Science from the University of Virginia.

My research focuses on agile and robust motion planning of ground and aerial vehicles for use in exploration and inspections of unknown, cluttered environments.

20230709_145141.jpg

Research
A Robust and Fast Occlusion-based Frontier Method for Autonomous Navigation in Unknown Cluttered Environments [IROS '22]

Nicholas Mohammad, Nicola Bezzo

Navigation through unknown, cluttered environments is a fundamental and challenging task for autonomous vehicles as they must deal with a myriad of obstacle configurations typically unknown a priori. Challenges arise because obstacles of unknown shapes and dimensions can create occlusions limiting sensor field of view and leading to uncertainty in motion planning.In this paper we propose to leverage such occlusions to quickly explore and cover unknown cluttered environments. Specifically, this work presents a novel occlusion-aware frontier-based approach that estimates gaps in point cloud data and shadows in the field of view to generate waypoints to navigate. Our scheme also proposes a breadcrumbing technique to save states of interest during exploration that can be exploited in future missions. For the latter aspect we focus primarily on the generation of the minimum number of breadcrumbs that will increase coverage and visibility of an explored environment.

This work was accepted to IROS '22 which took place in Kyoto, Japan on October 23-27, 2022. To see our simulation and experiment results, visit our webpage for this paper.

nick_intro2.png

A GP-based Robust Motion Planning Framework for Agile Autonomous Robot Navigation and Recovery in Unknown Environments [ICRA '24]
Nicholas Mohammad, Jacob Higgins, Nicola Bezzo

For autonomous mobile robots, uncertainties in the environment and system model can lead to failure in the motion planning pipeline, resulting in potential collisions. In order to achieve a high level of robust autonomy, these robots should be able to proactively predict and recover from such failures. To this end, we propose a Gaussian Process (GP) based model for proactively detecting the risk of future motion planning failure. When this risk exceeds a certain threshold, a recovery behavior is triggered that leverages the same GP model to find a safe state from which the robot may continue towards the goal. The proposed approach is trained in simulation only and can generalize to real world environments on different robotic platforms. Simulations and physical experiments demonstrate that our framework is capable of both predicting planner failures and recovering the robot to states where planner success is likely, all while producing agile motion.

This work has recently been accepted to ICRA '24 which will take place in Yokohama, Tokyo, Japan on May 13-17, 2024. To see our simulation and experiment results, visit our webpage for this paper.

spot_exp01_snapshots06.png
spot_experiment_rviz.png

Model Predictive Path Integral Method for Fast, Proactive, and Uncertainty-Aware UAV Planning in Cluttered Environments [IROS '23]
Jacob Higgins, Nicholas Mohammad, Nicola Bezzo

Current motion planning approaches for autonomous mobile robots often assume that the low level controller of the system is able to track the planned motion with very high accuracy. In practice, however, tracking error can be affected by many factors, and could lead to potential collisions when the robot must traverse a cluttered environment. To address this problem, this paper proposes a novel receding-horizon motion planning approach based on Model Predictive Path Integral (MPPI) control theory -- a flexible sampling-based control technique that requires minimal assumptions on vehicle dynamics and cost functions. This flexibility is leveraged to propose a motion planning framework that also considers a data-informed risk function. Using the MPPI algorithm as a motion planner also reduces the number of samples required by the algorithm, relaxing the hardware requirements for implementation. The proposed approach is validated through trajectory generation for a quadrotor unmanned aerial vehicle (UAV), where fast motion increases trajectory tracking error and can lead to collisions with nearby obstacles. Simulations and hardware experiments demonstrate that the MPPI motion planner proactively adapts to the obstacles that the UAV must negotiate, slowing down when near obstacles and moving quickly when away from obstacles, resulting in a complete reduction of collisions while still producing lively motion.

This work was accepted to IROS '23 which took place in Detroit, Chicago, USA on October 1-5, 2023. To see the simulation and experiment results, visit the webpage for this paper.

intro_fig2.png

Competitions
ICRA 2022 Benchmark for Autonomous Robot Navigation (BARN) Challenge

At the International Conference on Robotics and Automation (ICRA) 2022, Rahul Peddi, Lauren Bramblett, and I competed in the BARN Challenge, which tasked competitors to develop a robust navigation strategy to navigate quickly and safely through cluttered unknown environments. The first stage of the competition took place in the simulated BARN dataset with a Clearpath Jackal as the mobile robot. Using a mapless, gap-based navigation scheme, we were able to place in the top three teams and secured a spot at the in person competition being held at ICRA 2022. There, we went up against UT Austin and Temple on real world obstacle courses and placed 2nd. For additional information about the competition and all of the competitors, see the competition website here. After the competition was complete, Clearpath Robotic's wrote an article for their website about the BARN Challenge, which can be found here.

barn_competitors.jpg

ICRA 2023 Benchmark for Autonomous Robot Navigation (BARN) Challenge

At the International Conference on Robotics and Automation (ICRA) 2023, Lauren Bramblett and I competed in the BARN Challenge for the second consecutive year. This time, we developed a costmap-based, safe corridor motion planner. We used a MIQP to generate safe trajectories in a receding horizon fashion, and an in-house Model Predictive Controller (MPC) that I developed to track the trajectories (check it out here!). We were able to place in the top teams and secured a spot at the in person competition in London. There, we went up against UT Austin, KU Leuven, University of Almeria, and Inventec on real world obstacle courses and placed 4th, one successful course completion away from the top 3. For additional information about the competition and all of the competitors, see the competition website here.

barn_at_icra_2023.jpg

Education

2016-2020

University of Virginia

2020-2022

University of Virginia

B.S. in Computer Engineering

  • Capstone: "Word Puzzle Solving Robot"

M.S. in Computer Science

  • Thesis: "Occlusion-Aware Motion Planning of Autonomous Robots in Cluttered and Unknown Environments"

bottom of page