A5009377355- Robotic Path Planning Algorithms
- Robotics and Sensor-Based Localization
- Leadership, Behavior, and Decision-Making Studies
- Space Exploration and Technology
- Space Satellite Systems and Control
- Underwater Vehicles and Communication Systems
- Smart Agriculture and AI
- Planetary Science and Exploration
- AI-based Problem Solving and Planning
- Modular Robots and Swarm Intelligence
- Optimization and Search Problems
- Soil Mechanics and Vehicle Dynamics
- UAV Applications and Optimization
- Decision-Making and Behavioral Economics
- Bayesian Modeling and Causal Inference
- Distributed and Parallel Computing Systems
- Nanomaterials and Printing Technologies
- Advanced Materials and Mechanics
- Astro and Planetary Science
- Indoor and Outdoor Localization Technologies
- Software Reliability and Analysis Research
- Simulation Techniques and Applications
- Reinforcement Learning in Robotics
- Misinformation and Its Impacts
- Software Engineering Research
West Virginia University
2015-2024
Morgantown High School
2020-2024
A waypoint planning algorithm for an unmanned aerial vehicle (UAV) is presented that teamed with ground (UGV) the task of search and rescue in a subterranean environment. The UAV UGV are such localization conducted on via multisensor fusion fisheye camera, 3-D light detection ranging, ranging radio, laser altimeter. Likewise, trajectory UGV, which assumed to have map environment (e.g., from simultaneous mapping). goal satisfy mission's exploration criteria while reducing error by evaluating...
We present the system design, navigation algorithm formulation, and field-testing results for a cooperative unmanned ground vehicle (UGV) aerial (UAV) team designed operation in GNSS-denied subterranean environment. Central to presented support longer UAV mission duration, sensing computation performed on-board is assumed be limited order reduce payload mass, UGV assumes responsibility of mapping unknown environment tracking state UAV. To achieve this, instrumented with an omnidirectional...
The increasing use of autonomous robot systems in hazardous environments underscores the need for efficient search and rescue operations. Despite significant advancements, existing literature on object often falls short overcoming difficulty long planning horizons dealing with sensor limitations, such as noise. This study introduces a novel approach that formulates problem belief Markov decision processes options (BMDP-O) to make Monte Carlo tree (MCTS) viable tool these challenges large...
Plans for establishing a long-term human presence on the Moon will require substantial increases in robot autonomy and multirobot coordination to support lunar outpost. To achieve these objectives, algorithm design choices software developments need be tested validated expected scenarios such as autonomous situ resource utilization, localization challenging environments, coordination. However, real-world experiments are extremely limited extraterrestrial environment. Also, realistic...
This work presents the design of Stickbug, a six-armed, multi-agent, precision pollination robot that combines accuracy single-agent systems with swarm parallelization in greenhouses. Precision robots have often been proposed to offset effects decreasing population natural pollinators, but they frequently lack required and scalability. Stickbug achieves this by allowing each arm drive base act as an individual agent, significantly reducing planning complexity. uses compact holonomic Kiwi...
The increasing use of autonomous and semi-autonomous agents in society has made it crucial to validate their safety. However, the complex scenarios which they are used may make formal verification impossible. To address this challenge, simulation-based safety validation is employed test system. Recent approaches using reinforcement learning prone excessive exploitation known failures a lack coverage space failures. limitation, type Markov decision process called "knowledge MDP" been defined....
Team Mountaineers launched efforts on the NASA Space Robotics Challenge Phase-2 (SRC2). The challenge will be held lunar terrain with virtual robotic platforms to establish an in-situ resource utilization process. In this report, we provide overview of a simulation environment, mobile robot, and software architecture that was created by in order prepare for competition's qualification round before competition environment released.
Due to the complexity of many decision making problems, tree search algorithms often have inadequate information produce accurate transition models. Robust methods, designed make safe decisions when faced with these uncertainties, overlook impact expressions uncertainty on how is made. This work introduces Ambiguity Attitude Graph Search (AAGS), advocating for more precise representation ambiguities (uncertainty from a set plausible models) in making. Additionally, AAGS allows users adjust...
Plans for establishing a long-term human presence on the Moon will require substantial increases in robot autonomy and multi-robot coordination to support lunar outpost. To achieve these objectives, algorithm design choices software developments need be tested validated expected scenarios such as autonomous in-situ resource utilization (ISRU), localization challenging environments, coordination. However, real-world experiments are extremely limited extraterrestrial environment. Also,...
We present a waypoint planning algorithm for an unmanned aerial vehicle (UAV) that is teamed with ground (UGV) the task of search and rescue in subterranean environment. The UAV UGV are such localization conducted on via multi-sensor fusion fish-eye camera, 3D LIDAR, ranging radio, laser altimeter. Likewise, trajectory UGV, which assumed to have map environment (e.g., from Simultaneous Localization Mapping). goal satisfy mission's exploration criteria while reducing error by evaluating...