A5023976625- Robotic Path Planning Algorithms
- Underwater Vehicles and Communication Systems
- Robotics and Sensor-Based Localization
- Optimization and Search Problems
- Target Tracking and Data Fusion in Sensor Networks
- Maritime Navigation and Safety
- Distributed Control Multi-Agent Systems
- Robot Manipulation and Learning
- Reinforcement Learning in Robotics
- Machine Learning and Algorithms
- Modular Robots and Swarm Intelligence
- Soft Robotics and Applications
- Indoor and Outdoor Localization Technologies
- Underwater Acoustics Research
- Guidance and Control Systems
- Water Quality Monitoring Technologies
- Advanced Image and Video Retrieval Techniques
- Metaheuristic Optimization Algorithms Research
- Gaussian Processes and Bayesian Inference
- AI-based Problem Solving and Planning
- Autonomous Vehicle Technology and Safety
- Robotic Locomotion and Control
- Energy Efficient Wireless Sensor Networks
- Video Surveillance and Tracking Methods
- Artificial Intelligence in Games
Oregon State University
2016-2025
Rogers (United States)
2014-2024
University of Southern California
2011-2016
Southern California University for Professional Studies
2011-2016
University of Thessaly
2015
Centre for Research and Technology Hellas
2015
Massachusetts Institute of Technology
2012
Viterbo University
2012
Carnegie Mellon University
2006-2010
Aristotle University of Thessaloniki
2007
We propose three sampling-based motion planning algorithms for generating informative mobile robot trajectories. The goal is to find a trajectory that maximizes an information quality metric (e.g. variance reduction, gain, or mutual information) and also falls within pre-specified budget constraint fuel, energy, time). Prior have employed combinatorial optimization techniques solve these problems, but existing are typically restricted discrete domains often scale poorly in the size of...
We examine the problem of utilizing an autonomous underwater vehicle (AUV) to collect data from sensor network. The sensors in network are equipped with acoustic modems that provide noisy, range-limited communication. AUV must plan a path maximizes information collected while minimizing travel time or fuel expenditure. propose planning methods extend algorithms for variants Traveling Salesperson Problem (TSP). While executing path, can improve performance by communicating multiple nodes at...
Recent advances in Autonomous Underwater Vehicle (AUV) technology have facilitated the collection of oceanographic data at a fraction cost ship‐based sampling methods. Unlike deep ocean, operation AUVs coastal regions exposes them to risk collision with ships and land. Such concerns are particularly prominent for slow‐moving since ocean current magnitudes often strong enough alter planned path significantly. Prior work using predictive currents relies upon deterministic outcomes, which do...
This paper examines the problem of locating a mobile, non-adversarial target in an indoor environment using multiple robotic searchers. One way to formulate this is assume known and choose searcher paths most likely intersect with path taken by target. We refer as multi-robot efficient search planning (MESPP) problem. Such prob lems are NP-hard, optimal solutions typically scale exponentially number present approximation al gorithm that utilizes finite-horizon implicit coordination achieve...
We discuss the problem of inspecting an underwater structure, such as a submerged ship hull, with autonomous vehicle (AUV). Unlike large body prior work, we focus on planning views AUV to improve quality inspection, rather than maximizing accuracy given data stream. formulate inspection extension Bayesian active learning, and show connections recent theoretical guarantees in this area. rigorously analyze benefit adaptive re-planning for problems, prove that potential adaptivity can be...
We examine the scenario in which a mobile network of robots must search, survey, or cover an environment and communication is restricted by relative location. While many algorithms choose to maintain connected at all times while performing such tasks, we relax this requirement use periodic connectivity, where regain connectivity fixed interval. propose online algorithm that scales linearly number allows for arbitrary constraints. To complement proposed algorithm, provide theoretical...
We propose a multi-robot exploration algorithm that uses adaptive coordination to provide heterogeneous behavior. The key idea is maximize the efficiency of exploring and mapping an unknown environment when team faced with unreliable communication limited battery life (e.g., aerial rotorcraft). proposed utilizes four states: explore, meet, sacrifice, relay. explore state frontier-based algorithm, meet returns last known location share data, sacrifice sends robot out without consideration...
We consider the problem of multi-robot coordination subject to constraints on configuration. Specifically, we examine case in which a mobile network robots must search, survey, or cover an environment while remaining connected. While many algorithms utilize continual connectivity for such tasks, relax this requirement and introduce idea periodic connectivity, where regain at fixed interval. show that, some cases, reduces well-studied NP-hard informative path planning (MIPP) problem, propose...
We propose an incremental sampling-based motion planning algorithm that generates maximally informative trajectories for guiding mobile robots to observe their environment.The goal is find a trajectory maximizes information metric (e.g., variance reduction, gain, or mutual information) and also falls within pre-specified budget constraint fuel, energy, time).Prior algorithms have employed combinatorial optimization techniques solve these problems, but existing are typically restricted...
Underwater robots beneath ocean waves can benefit from feedforward control to reduce position error. This letter proposes a method using model predictive (MPC) predict and counteract future disturbances an wave field. The MPC state estimator employs linear theory (LWT) solver approximate the component fluid dynamics under Wave data deployed buoys are used construct simulated is optimize set of actions by gradient descent along prediction horizon. optimized input minimizes global cost...
The self-organizing map (SOM) is an unsupervised learning technique providing a transformation of high-dimensional input space into lower dimensional output space. In this paper, we utilize the SOM for traveling salesman problem (TSP) to develop solution autonomous data collection. Autonomous collection requires gathering from predeployed sensors by moving within limited communication radius. We propose new growing that adapts number neurons during learning, which also allows our approach...
Subterranean robot exploration is difficult, with many mobility, communications, and navigation challenges that require an approach a diverse set of systems, reliable autonomy. While prior work has demonstrated partial successes in addressing the problem, here we convey comprehensive to address problem subterranean wide range tunnel, urban, cave environments. Our driven by themes resiliency modularity, show examples how these influence design different modules. In particular, detail our...
We discuss the problem of inspecting an underwater structure, such as a submerged ship hull, with autonomous vehicle (AUV). In scenarios, goal is to construct accurate 3D model structure and detect any anomalies (e.g., foreign objects or deformations). propose method for constructing meshes from sonar-derived point clouds that provides watertight surfaces, we introduce uncertainty modeling through non-parametric Bayesian regression. Uncertainty novel cost functions planning path AUV minimize...
This paper presents novel data fusion methods that enable teams of vehicles to perform target search tasks without guaranteed communication. Techniques are introduced for merging estimates a target's position from regain contact after long periods time, and fully distributed team-planning algorithm is proposed, which utilizes limited shared information as it becomes available. The proposed techniques shown avoid overcounting information, ensures combining different will not decrease the...
Operating autonomous underwater vehicles (AUVs) near shore is challenging—heavy shipping traffic and other hazards threaten AUV safety at the surface, strong ocean currents impede navigation when underwater. Predictive models of have been shown to improve accuracy, but these forecasts are typically noisy, making it challenging use them effectively. Prior work has explored probabilistic planners, such as Markov decision processes (MDPs), for planning in scenarios, prior methods lacked a...
Abstract Mobile autonomous platforms are revolutionizing our understanding of ocean systems by providing a solution for the four‐dimensional observation problem faced in ocean. The sensors commonly used platforms, however, leave large gap observations food chain between primary producers and predators. Echosounders have potential to fill this gap. Here, we present details new, commercially available quantitative scientific echosounder specifically designed meet challenges deployment...
Abstract Ocean monitoring is an expensive and time consuming endeavor, but it can be made more efficient through the use of teams autonomous robots. In this paper, we present a system for identification tracking ocean fronts by coordinating sampling efforts heterogeneous team surface vehicles (ASVs) underwater (AUVs). The primary contributions study are (1) our algorithm performing coordination using general autonomy principles: Sequential Allocation Monte Carlo Tree Search (SA‐MCTS) which...
In early motor interventions from clinical rehabilitation to physical activity encouragement, one major challenge is maintaining child engagement and motivation. Robots show unique promise for addressing this challenge, but providing robots with new types of autonomous functionality vital promoting robot integration usefulness in the clinic home spaces. To provide needed autonomy capabilities GoBot, our assistive child-robot motion interventions, we propose a behavior tree framework. Within...
This paper presents coordination and data fusion methods for teams of vehicles performing target search tasks without guaranteed communication. A fully distributed team planning algorithm is proposed that utilizes limited shared information as it becomes available, techniques are introduced merging estimates the target's position from regain contact after long periods time. The shown to avoid overcounting information, which ensures combining different will not decrease performance search....
We examine the problem of planning paths for an autonomous underwater vehicle (AUV) to collect data from sensor network. The sensors in network are equipped with acoustic modems that provide noisy, range-limited communication. AUV must plan a path maximizes information collected while minimizing travel time or fuel expenditure. This is closely related classical Traveling Salesperson Problem (TSP), but differs particular has probability being depending on quality propose methods solving this...