26 July 2024 in Ocean Engineering
25 September 2024 in IEEE Robotics and Automation Letters
Effective data collection in collaborative information-gathering systems relies heavily on maintaining uninterrupted connectivity. Yet, real-world communication disruptions often pose challenges to information-gathering processes. To address this issue, we introduce a novel method —a limited communication decentralized information gathering system for multiple robots to explore environmental phenomena characterized as unknown spatial fields. Our method leverages quadtree structures to ensure comprehensive workspace coverage and efficient exploration. Unlike traditional systems that depend on global and synchronous communication, our method enables robots to share local experiences within a limited transmission range and coordinate their tasks through pairwise and asynchronous communication. Information estimation is facilitated by a Gaussian Process with an Attentive Kernel, allowing adaptive capturing of crucial behavior and data patterns. Our proposed system is validated through simulated scalar field studies in non-stationary environments where multiple robots explore spatial fields. Theoretical guarantees ensure the convergence of distributed area coverage and the regret bounds of distributed online scalar field mapping. We also validate our method empirically in a water quality monitoring scenario featuring three Autonomous Surface Vehicles, tasked with constructing a spatial field.
19 January 2026 in IEEE Robotics and Automation Letters
Autonomous robots performing navigation tasks in complex environments often face significant challenges due to uncertainty in state estimation. In settings where the robot faces significant resource constraints and accessing high-precision localization comes at a cost, the planner may have to rely primarily on less precise state estimates. Our key observation is that different tasks, and different portions of tasks require varying levels of precision in different regions: a robot navigating a crowded space might need precise localization near obstacles but can operate effectively with less precise state estimates in open areas. In this paper, we present a planning method for integrating task-specific uncertainty requirements directly into navigation policies. We introduce Task-Specific Uncertainty Maps (TSUMs), which abstract the acceptable levels of state estimation uncertainty across different regions. TSUMs align task requirements and environmental features using a shared representation space, generated via a domain-adapted encoder. Using TSUMs, we propose $\mathbf{G}$eneralized $\mathbf{U}$ncertainty $\mathbf{I}$ntegration for $\mathbf{D}$ecision-Making and $\mathbf{E}$xecution (GUIDE), a policy-conditioning framework that incorporates these uncertainty requirements into the robot’s decision-making process, enabling the robot to reason about the context-dependent value of certainty and adapt its behavior accordingly. We show how integrating GUIDE into reinforcement learning frameworks allows the agent to learn navigation policies that effectively balance task completion and uncertainty management without the need for explicit reward engineering. We evaluate GUIDE on a variety of real-world robotic navigation tasks and find that it demonstrates significant improvement in task completion rates compared to baseline methods that do not explicitly consider task-specific uncertainty.
30 May 2021 in Ingeniería
Contexto: Los problemas de minimización en el sentido de los mínimos cuadrados han sido constantemente usados en la restauración de imágenes borrosas. Estos se caracterizan por ser sensibles a valores atípicos afectando significativamente la calidad de la imagen restaurada. Teniendo en cuenta que la norma L1 es menos sensible a datos atípicos, el problema de restauración de imágenes borrosas se plantea como un problema de programación lineal. Método: Un método de punto interior se utiliza para la solución del problema de programación lineal. Se presenta la adaptación de técnicas de regularización al problema de programación lineal de la imagen buscada y su derivada. Se realiza un estudio comparativo con otras técnicas de restauración bajo diferentes tipos de difuminado de imágenes. Resultados: Se probó que el método propuesto conduce a mejoras notables en las imágenes recuperadas. Los experimentos numéricos muestran que el método de programación lineal funciona mucho mejor que los propuestos en la literatura, en términos de valores de PSNR, SSIM y en la calidad visual de las imágenes reconstruidas. Conclusiones: El problema de programación lineal regularizado puede utilizarse eficazmente como modelo matemático del problema de restauración de imágenes borrosas. Para trabajos futuros se plantea el estudio de la selección automática de parámetros de regularización y solución de restauración sin conocimiento previo del núcleo de difuminado.