Telerobotics involves the operation of robots from a distance, often using advanced communication technologies combining wireless and wired technologies and a variety of protocols. This application domain is crucial because it allows humans to interact with and control robotic systems safely and from a distance, often performing activities in hazardous or inaccessible environments. Thus, by enabling remote operations, telerobotics not only enhances safety but also expands the possibilities for medical and industrial applications. In some use cases, telerobotics bridges the gap between human skill and robotic precision, making the completion of complex tasks requiring high accuracy possible without being physically present. With the growing availability of high-speed networks around the world, especially with the advent of 5G cellular technologies, applications of telerobotics can now span a gamut of scenarios ranging from remote control in the same room to robotic control across the globe. However, there are a variety of factors that can impact the control precision of the robotic platform and user experience of the teleoperator. One such critical factor is latency, especially across large geographical areas or complex network topologies. Consequently, military telerobotics and remote operations, for example, rely on dedicated communications infrastructure for such tasks. However, this creates a barrier to entry for many other applications and domains, as the cost of dedicated infrastructure would be prohibitive. In this paper, we examine the network latency of robotic control over shared network resources in a variety of network settings, such as a local network, access-controlled networks through Wi-Fi and cellular, and a remote transatlantic connection between Finland and the United States. The aim of this study is to quantify and evaluate the constituent latency components that comprise the control feedback loop of this telerobotics experience—of a camera feed for an operator to observe the telerobotic platform’s environment in one direction and the control communications from the operator to the robot in the reverse direction. The results show stable average round-trip latency of 6.6 ms for local network connection, 58.4 ms when connecting over Wi-Fi, 115.4 ms when connecting through cellular, and 240.7 ms when connecting from Finland to the United States over a VPN access-controlled network. These findings provide a better understanding of the capabilities and performance limitations of conducting telerobotics activities over commodity networks, and lay the foundation of our future work to use these insights for optimizing the overall user experience and the responsiveness of this control loop.

With artificial intelligence (AI) rapidly increasing in popularity and presence in everyday life, new applications utilizing AI are being explored across virtually all domains, from banking and healthcare to cybersecurity to generative AI for images, voice, and video content creation. With that trend comes an inherent need for increased AI capabilities. One cornerstone of AI applications is the ability of generative AI to consume documents and utilize their content to answer questions, generate new content, correlate it with other data sources, and more. No longer constrained to text alone, we now leverage multimodal AI models to help us understand visual elements within documents, such as images, tables, figures, and charts. Within this realm, capabilities have expanded exponentially from traditional Optical Character Recognition (OCR) approaches towards increasingly utilizing complex AI models for visual content analysis and understanding. Modern approaches, especially those leveraging AI, are now focusing on interpreting more complex diagrams such as flowcharts, block diagrams, Unified Modeling Language (UML) diagrams, electrical schematics, and timing diagrams. These diagram types combine text, symbols, and structured layout, making them challenging to parse and comprehend using conventional techniques. This paper presents a historical analysis and comprehensive survey of scientific literature exploring this domain of visual understanding of complex technical illustrations and diagrams. We explore the use of deep learning models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and transformer-based architectures. These models, along with OCR, enable the extraction of both textual and structural information from visually complex sources. Despite these advancements, numerous challenges remain, however. These range from hallucinations, where the content extraction system produces outputs not grounded in the source image, which leads to misinterpretations, to a lack of contextual understanding of diagrammatic elements, such as arrows, grouping, and spatial hierarchy. This survey focuses on five key diagram types: flowcharts, block diagrams, UML diagrams, electrical schematics, and timing diagrams. It evaluates the effectiveness, limitations, and practical solutions—both traditional and AI-driven—that aim to enable the extraction of accurate and meaningful information from complex diagrams in a way that is trustworthy and suitable for real-world, high-accuracy AI applications. This survey reveals that virtually all approaches struggle with accurately extracting technical diagram information. It also illustrates a path forward. Pursuing research to further improve their accuracy is crucial for supporting and enabling various applications, including complex document question answering and Retrieval Augmented Generation (RAG), document-driven AI agents, accessibility applications, and automation.

As wireless communications become increasingly synonymous with everyday life, the demand for higher data rates, reliability, and efficiency continues to grow. This is further accelerated by the rapid rise in the Internet of Things (IoT) and industrial automation. However, traditional algorithm-based signal processing is limited by algorithmic complexity and its limited ability to adapt to and cope with increasingly adverse and congested channel conditions, thereby reducing the effectiveness of traditional digital signal processing techniques in real-world environments. To address these challenges, approaches using Deep Learning (DL) have rapidly gained attention as a promising alternative to traditional DSP techniques. DL techniques excel in adaptability and have demonstrated on-par or even superior performance compared to traditional approaches for various RF environments, particularly in challenging conditions such as low-SNR, high-mobility, and non-ideal channel scenarios. In this survey, we examine the various stages that comprise popular wireless transmission techniques, specifically Orthogonal Frequency Division Multiplexing (OFDM), which underpins numerous technologies, including Wi-Fi, 4G LTE, 5G, and DVB. We review recent research activities to implement the various stages of the OFDM receiver chain using DL methods, including synchronization, Cyclic Prefix (CP) removal, Fast Fourier Transform (FFT), channel estimation and equalization, demodulation, and decoding. We also review approaches that take a holistic view, aiming to use a unified DL approach across the entire signal processing chain. For each stage, we review existing Deep Learning-based methods and provide insights into how they aim to meet or exceed the performance of traditional approaches. This survey provides a comprehensive overview of the current development of deep learning-based OFDM systems, highlighting the potential benefits and challenges that remain in fully replacing conventional signal processing methods with modern deep learning approaches.

As wireless communications become increasingly synonymous with everyday life, the demand for higher data rates, reliability, and efficiency continues to grow. This is further accelerated by the rapid rise in the Internet of Things (IoT) and industrial automation. However, traditional algorithm-based signal processing is limited due to algorithm complexity and the limited ability to adapt to, and cope with, increasingly adverse and congested channel conditions, which reduce the effectiveness of traditional digital signal processing techniques in real-world environments. To address these challenges, approaches using Deep Learning (DL) have rapidly gained attention as a promising alternative to traditional DSP techniques. DL techniques excel in adaptability and have been shown to outperform traditional approaches in various RF environments. In this survey, we examine and analyze the various stages that comprise popular wireless transmission techniques, specifically Orthogonal Frequency Division Multiplexing (OFDM), which forms the foundation for numerous technologies, including Wi-Fi, 4G LTE, 5G, and DVB. We review recent research activities to implement the various stages of the OFDM receiver chain using DL methods, including synchronization, Cyclic Prefix (CP) removal, Fast Fourier Transform (FFT), channel estimation and equalization, demodulation, and decoding. We also review approaches that focus on a holistic view that aims to utilize a unified DL approach for the entire signal processing chain. For each stage, we review existing Deep Learning-based methods and provide insights into how they aim to meet or exceed the performance of traditional approaches. This survey seeks to provide a comprehensive overview of the current development of deep learning-based OFDM systems, highlighting the potential benefits and challenges that remain in fully replacing conventional signal processing methods with modern deep learning approaches.

Telerobotics involves the operation of robots from a distance, often using advanced communication technologies combining wireless and wired technologies and a variety of protocols. This application domain is crucial because it allows humans to interact with and control robotic systems safely and from a distance, often performing activities in hazardous or inaccessible environments. Thus, by enabling remote operations, telerobotics not only enhances safety but also expands the possibilities for medical and industrial applications. In some use cases, telerobotics bridges the gap between human skill and robotic precision, making the completion of complex tasks requiring high accuracy possible without being physically present. With the growing availability of high-speed networks around the world, especially with the advent of 5G cellular technologies, applications of telerobotics can now span the gamut of scenarios ranging from remote control in the same room to robotic control across the globe. However, there are a variety of factors that can impact the control precision of the robotic platform and user experience by the teleoperator. One such critical factor is latency, especially across large geographical areas or complex network topologies. Consequently, military telerobotics and remote operations, for example, rely on dedicated communications infrastructure for such tasks. However, this creates a barrier to entry for many other applications and domains, as the cost of dedicated infrastructure would be prohibitive. In this paper, we examine the network latency of robotic control over shared network resources in a variety of network settings, such as a local network, access-controlled networks through Wi-Fi and cellular, and also a remote transatlantic connection between Finland and the United States. The aim of this study is to quantify and evaluate the constituent latency components that comprise the control feedback loop of this telerobotics experience - between a camera feed to observe the telerobotic platform's environment by the operator in one direction and the control communications from the operator to the robot in the reverse direction and to subsequently use these insights to optimize the end-to-end latency for optimizing the user experience. The results show stable average round trip latency of 6.6 ms for local network connection, 58.4 ms connecting over Wi-Fi, 115.4 ms connecting through cellular, and 240.7 ms connecting from Finland to the United States over a VPN access-controlled network. These findings pave the way toward a better understanding of the capabilities and performance limitations of telerobotics activities over commodity networks.

With Artificial Intelligence (AI) rapidly increasing in popularity and presence in everyday life, new applications utilizing AI are being explored throughout virtually all domains, from banking and healthcare to cybersecurity to generative AI for images, voice, and video content creation. With that trend comes an inherent need for increased AI capabilities. One cornerstone of AI applications is the ability of Generative AI to consume documents and utilize their content to answer questions, generate new content, correlate it with other data sources, and more. No longer constrained to text alone, we now leverage multimodal AI models to help us understand visual elements within documents, such as images, tables, figures, and charts. Within this realm, capabilities have expanded exponentially from traditional Optical Character Recognition (OCR) approaches towards increasingly utilizing complex AI models for visual content analysis and understanding. Modern approaches, especially those leveraging AI, are now focusing on interpreting more complex diagrams such as flowcharts, block diagrams, electrical schematics, and timing diagrams. These diagrams combine text, symbols, and structured layout, making them challenging to parse and comprehend using conventional techniques. This paper presents a historical analysis and comprehensive survey of scientific literature exploring this domain of visual understanding of complex technical illustrations and diagrams. We explore the use of deep learning models, including Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Transformer-based architectures. These models, along with OCR, enable the extraction of both textual and structural information from visually complex sources. Despite these advancements, numerous challenges remain, however. These range from hallucinations, where OCR systems produce outputs not grounded in the source image, leading to misinterpretations, to a lack of contextual understanding of diagrammatic elements, such as arrows, grouping, and spatial hierarchy. This survey focuses on four key diagram types: flowcharts, block diagrams, electrical schematics, and timing diagrams. It evaluates the effectiveness, limitations, and practical solutions — both traditional and AI-driven — that aim to enable the extraction of accurate and meaningful information from complex diagrams in a way that is trustworthy and suitable for real-world, high-accuracy AI applications. This survey reveals that virtually all approaches struggle with accurately extracting technical diagram information, and it illustrates a path forward. Pursuing research to improve their accuracy further is crucial for various applications, including complex document question answering and Retrieval Augmented Generation, document-driven AI agents, accessibility applications, and automation.