VoxGuru: A Multimodal AI for Transformative Conversational Learning in Real-Time Dynamic Environments

A very important challenge in many virtual applications is to plan feasible, smooth and congestion-free paths for virtual agents in dynamic and complex environments. The agents should move towards their destinations successfully while avoiding the collisions with other agents and static and dynamic obstacles. In this paper, we propose a novel approach for realistic path planning. We first create a navigation mesh for the walkable regions in a two-dimensional environment. Then an A* search on this graph determines a series of connected meshes for agents to go through from the start position to the goal position and furthermore, the walkable corridor whose radii equal to maximum clearance to the obstacles is built based on backbone path derived from the inflection point method and Catmull-Rom spline. Finally, a local collision avoidance algorithm is integrated to guarantee that agents navigating in the corridor do not collide with other agents and dynamic obstacles. Our experiments show that we can compute feasible, smooth and realistic paths for agents situated in dynamic environments in real time.

The method of the current acceleration range navigation satellite signal simulator detection theoretically analyzed, but in the actual test work, how to set the satellite navigation signal simulator motion scenes and satellite receivers, a smaller level of the RF test signal navigation As well as implementing automated testing, there is a lack of practical and feasible testing methods. This paper simulates the RF signals received by receivers in different dynamic environments in real time, builds a dynamic range test staging, forms a specific test plan, and carries out the validity, practicability and effectiveness of the test verification test method. This test method is simple and reliable. The dynamic range of the satellite navigation signal simulator in the simulation environment can be accurately detected by this method.

One key prerequisite for a machine to interact intelligently with people is its ability to recognize humans as interaction partners, and to understand their behaviors and the intentions and plans behind them. In this paper we are particularly interested in behaviors which are related to motion, e.g. intentionally moving towards a goal or obstructing somebody's path. More specifically, we address the problem of detecting and tracking people in natural dynamic environments in realtime, and extracting and classifying typical motion patterns. Robust detection and tracking of nonrigid objects in natural changing environments with a moving observer is a challenging problem. Although various sophisticated approaches have been presented, robustness with respect to changing light conditions, non-rigidness of the tracked objects, occlusion and motion of the observer is still a problem which needs for an effective solution. Recognizing and understanding the intention of motion would leverage applications in areas such as smart environments, human-machine interaction and video surveillance. We present an approach for tracking people by integrating range information and visual information, and using their complimentary strengths to overcome typical tracking problems. Individual motion trajectories are extracted from these fused sensor data and are condensed in compact statistical spatiotemporal models. These models serve as a basis for the extraction of typical motion patterns by unsupervised learning.

Collective adaptive systems (CAS) have been attracting increasing attention in the field of artificial intelligence (AI), in which collaboration of agents plays a key role. These systems aim to accomplish a certain goal though collaborating between a variety of agents with different tasks, which adapt to changes of environment to be of adaptability. To solve the issue of collaboration of agents in an uncertain and highly dynamic environment, our research team had proposed a Goal-Capability-Commitment (GCC) based mediation for multi-agent collaboration, which generates the collaboration planning driven by capability based on global context states in real-time dynamic environment. As a case study for the application of GCC model, this paper adopts GCC to model the RoboCup Rescue Simulation System (RCRSS). As the result of modelling, the GCC domain model is applied to RCRSS where an efficiently quantitative evaluation is provided.

Robots are frequently presented with vast arrays of diverse data. Unfortunately, perfect memory and recall provides a mixed blessing. While flawless recollection of episodic data allows increased reasoning, photographic memory can hinder a robot's ability to operate in real-time dynamic environments. Human-inspired forgetting methods may enable robotic systems to rid themselves of out-dated, irrelevant, and erroneous data. This paper presents the use of human-inspired forgetting to act as a filter, removing unnecessary, erroneous, and out-of-date information. The novel ActSimple forgetting algorithm has been developed specifically to provide effective forgetting capabilities to robotic systems. This paper presents the ActSimple algorithm and how it was optimized and tested in a WiFi signal strength estimation task. The results generated by real-world testing suggest that human-inspired forgetting is an effective means of improving the ability of mobile robots to move and operate within complex and dynamic environments.

Depth maps produced by consumer-grade sensors suffer from inaccurate measurements and missing data from either system or scene-specific sources. Data-driven denoising algorithms can mitigate such problems; however, they require vast amounts of ground truth depth data. Recent research has tackled this limitation using self-supervised learning techniques, but it requires multiple RGB-D sensors. Moreover, most existing approaches focus on denoising single isolated depth maps or specific subjects of interest highlighting a need for methods that can effectively denoise depth maps in real-time dynamic environments. This paper extends state-of-the-art approaches for depth-denoising commodity depth devices, proposing SelfReDepth, a self-supervised deep learning technique for depth restoration, via denoising and hole-filling by inpainting of full-depth maps captured with RGB-D sensors. The algorithm targets depth data in video streams, utilizing multiple sequential depth frames coupled with color data to achieve high-quality depth videos with temporal coherence. Finally, SelfReDepth is designed to be compatible with various RGB-D sensors and usable in real-time scenarios as a pre-processing step before applying other depth-dependent algorithms. Our results demonstrate our approach’s real-time performance on real-world datasets shows that it outperforms state-of-the-art methods in denoising and restoration performance at over 30 fps on Commercial Depth Cameras, with potential benefits for augmented and mixed-reality applications.

In this paper we introduce a robust earliest deadline scheduling algorithm for dealing with hard aperiodic tasks under overloads in a dynamic real-time environment. The algorithm synergistically combines many features including dynamic guarantees, graceful degradation in overloads, deadline tolerance, resource reclaiming, and dynamic re-guarantees. A necessary and sufficient schedulability test is presented, and an efficient 0(n) guarantee algorithm is proposed. The new algorithm is evaluated via simulation and compared to several baseline algorithms. The experimental results show excellent performance of the new algorithm in normal and overload conditions.

Tracking of moving objects in video streams with considering different dynamic backgrounds is a challenging problem in a real time dynamic environment. The proposed approach uses an observation model based on optical flow information used to know the displacement of the objects present in the scene. After finding the moving regions in the initial frame, we are applying active contour model (ACM) to track the moving objects in the further frames dynamically. These models have been used as a natural means of incorporating flow information into the tracking. The formulation of the active contour model by incorporating an additional force driven optical flow field improves the tracking speed. This algorithm efficiently works to track for low contrast videos like aerial videos.

A new method is presented for visualizing data as they are generated from real-time applications. These techniques allow viewers to perform simple data analysis tasks such as detection of data groups and boundaries, target detection, and estimation. The goal is to do this rapidly and accurately on a dynamic sequence of data frames. Our techniques take advantage of an ability of the human visual system called preattentive processing. Preattentive processing refers to an initial organization of the visual system based on operations believed to be rapid, automatic, and spatially parallel. Examples of visual features that can be detected in this way include hue, orientation, intensity, size, curvature, and line length. We believe that studies from preattentive processing should be used to assist in the design of visualization tools, especially those for which high speed target, boundary, and region detection are important. Previous work has shown that results from research in preattentive processing can be used to build visualization tools that allow rapid and accurate analysis of individual, static data frames. We extend these techniques to a dynamic real-time environment. This allows users to perform similar tasks on dynamic sequences of frames, exactly like those generated by real-time systems such as visual interactive simulation. We studied two known preattentive features, hue and curvature. The primary question investigated was whether rapid and accurate target and boundary detection in dynamic sequences is possible using these features. Behavioral experiments were run that simulated displays from our preattentive visualization tools. Analysis of the results of the experiments showed that rapid and accurate target and boundary detection is possible with both hue and curvature. A second question, whether interactions occur between the two features in a real-time environment, was answered positively.

Advanced Driver Assistance Systems (ADAS) have emerged as a critical technology in enhancing vehicle safety, providing convenience to drivers, and facilitating the transition toward fully autonomous vehicles. The core of these systems relies heavily on computer vision (CV) technologies, which enable vehicles to interpret and understand their surrounding environment in real time. The integration of computer vision in ADAS allows vehicles to recognize and process various objects such as pedestrians, vehicles, traffic signs, and lane markings, significantly improving both safety and the driving experience. In this paper, we explore the pivotal role of computer vision in the development and implementation of ADAS in autonomous vehicles. We begin by reviewing the evolution of ADAS, detailing the different sub-systems such as lane departure warning, automatic emergency braking, adaptive cruise control, and parking assistance, all of which depend on sophisticated image processing techniques. Furthermore, the paper examines the intersection of computer vision with other emerging technologies such as machine learning, deep learning, and sensor fusion. We discuss how these innovations enable ADAS to function more effectively in complex, dynamic environments. The methodology section focuses on cutting-edge algorithms used for object detection, semantic segmentation, and real-time image processing, which are integral to the functionality of modern ADAS. Additionally, we evaluate the challenges that computer vision systems face in real-world applications, including issues with sensor calibration, environmental conditions, computational limitations, and the integration of data from multiple sensors (e.g., cameras, LiDAR, radar). The paper also presents an analysis of the results obtained from various real-world implementations of ADAS technologies, highlighting improvements in driver safety and the reduction of traffic-related accidents. We explore the potential of computer vision in enabling fully autonomous driving by addressing the current gaps in technology and the advancements needed to close these gaps. Finally, the paper concludes with a discussion on the future of ADAS and the role of computer vision in realizing fully autonomous, reliable, and efficient transportation systems. We argue that continued research and development in computer vision, combined with innovations in deep learning and sensor technologies, are critical to advancing the capabilities and reliability of autonomous vehicles in the near future.

In this paper , a Novel Cellular Neural Network (CNN) entitled the shortest path CNN (SP-CNN) is proposed. It has a good performance in path planning for mobile robots because of its network structure and neural dynamics. The proposed method not only can generate the best solution in static environments in real time but also generate the optional solution in dynamic environments or in unknown environments according to its currently acquired navigation map. Extensive simulations about the above mentioned aspects demonstrate the effectiveness of the proposed approach.

Point label placement problem is the problem of labeling points in graphical display systems such as mapbased ones in order to minimize conflicts of labels and thus to maximize legibility. Algorithmic complexity of the general problem is proven to be NP-hard. Addressing this problem is becoming more important in dynamic and real-time environments, where both display properties or point elements are subject to change, since those systems have potential use widely and in large scale. In this study, heuristic optimization methods are proposed to facilitate fast and goodquality labeling in such dynamic environments. The methods are two-phased and comprised of several combinations of greedy construction and local search methods. Performances of the methods are examined in terms of solution quality and run time. The eliminative, two-criteria method outperform other methods in this study and the methods proposed in the literature.

Point label placement problem is the problem of labeling points in graphical display systems such as mapbased ones in order to minimize conflicts of labels and thus to maximize legibility. Algorithmic complexity of the general problem is proven to be NP-hard. Addressing this problem is becoming more important in dynamic and real-time environments, where both display properties or point elements are subject to change, since those systems have potential use widely and in large scale. In this study, heuristic optimization methods are proposed to facilitate fast and goodquality labeling in such dynamic environments. The methods are two-phased and comprised of several combinations of greedy construction and local search methods. Performances of the methods are examined in terms of solution quality and run time. The eliminative, two-criteria method outperform other methods in this study and the methods proposed in the literature.

Purpose With the increasing demand for surveillance and smart transportation, drone technology has become the center of attraction for robotics researchers. This study aims to introduce a new path planning approach to drone navigation based on topology in an uncertain environment. The main objective of this study is to use the Ricci flow evolution equation of metric and curvature tensor over angular Riemannian metric, and manifold for achieving navigational goals such as path length optimization at the minimum required time, collision-free obstacle avoidance in static and dynamic environments and reaching to the static and dynamic goals. The proposed navigational controller performs linearly and nonlinearly both with reduced error-based objective function by Riemannian metric and scalar curvature, respectively. Design/methodology/approach Topology and manifolds application-based methodology establishes the resultant drone. The trajectory planning and its optimization are controlled by the system of evolution equation over Ricci flow entropy. The navigation follows the Riemannian metric-based optimal path with an angular trajectory in the range from 0° to 360°. The obstacle avoidance in static and dynamic environments is controlled by the metric tensor and curvature tensor, respectively. The in-house drone is developed and coded using C++. For comparison of the real-time results and simulation results in static and dynamic environments, the simulation study has been conducted using MATLAB software. The proposed controller follows the topological programming constituted with manifold-based objective function and Riemannian metric, and scalar curvature-based constraints for linear and nonlinear navigation, respectively. Findings This proposed study demonstrates the possibility to develop the new topology-based efficient path planning approach for navigation of drone and provides a unique way to develop an innovative system having characteristics of static and dynamic obstacle avoidance and moving goal chasing in an uncertain environment. From the results obtained in the simulation and real-time environments, satisfactory agreements have been seen in terms of navigational parameters with the minimum error that justifies the significant working of the proposed controller. Additionally, the comparison of the proposed navigational controller with the other artificial intelligent controllers reveals performance improvement. Originality/value In this study, a new topological controller has been proposed for drone navigation. The topological drone navigation comprises the effective speed control and collision-free decisions corresponding to the Ricci flow equation and Ricci curvature over the Riemannian metric, respectively.

Conventional mission-critical systems cannot prevent mission failure in dynamic battlefield environments in which the execution situations or missions change abruptly. To solve this problem, self-adaptive systems have been proposed in the literature. However, the previous studies do not offer specifics on how to identify changes in a system situation or to transform situation information into the actions the systems must take in dynamic environments. This paper proposes a situation-awareness based self-adaptive system architecture (SASA) to support more efficient adaptation and, hence, achieve more accurate and successful missions, even in dynamic execution environments. A case study for air defense systems (ADS) using tests in a HLA/TRI-based real-time distributed simulation environment was implemented.