Path-finding Task Research Articles

Integrated Sensor Fusion and Multi-Modal Hierarchical Neural Network for Activity Recognition in Lower Limb Prosthetics

Activity recognition plays pivotal role in enhancing functionality for prosthetic devices, ensuring seamless integration with users' movements. However, the complexity arises from the diverse data sources, including acceleration, angular velocity, joint angles, orientation, electromyography (EMG), and marker data, necessitating a robust approach to overcome challenges in information integration. The primary challenge lies in the effective utilization of multiple sensor modalities, each with unique characteristics and potential noise sources. The proposed solution addresses this by employing advanced sensor fusion techniques, such as Kalman filtering, during data collection. Synchronization and resampling ensure temporal consistency, while noise reduction techniques, such as low-pass filters, mitigate signal distortions. To further refine the process, a hybrid optimization-based feature selection Adaptive Step Size in Marine Predators Algorithm (ASSMPA) is introduced, focusing on marker data features. ASSMPA synergizes Marine Predators Algorithm (MPA) and Pathfinder Algorithm (PFA) for optimal feature selection in marine predator pathfinding tasks. The Feature Fusion step integrates attention mechanisms to dynamically weigh the significance of different sensor modalities during the fusion process. This strategic fusion enhances the overall performance of the Multi-Modal Hierarchical Neural Network (MMHNN). The proposed model is implemented using Python.

Integrated Sensor Fusion and Multi-Modal Hierarchical Neural Network for Activity Recognition in Lower Limb Prosthetics

Activity recognition plays pivotal role in enhancing functionality for prosthetic devices, ensuring seamless integration with users' movements. However, the complexity arises from the diverse data sources, including acceleration, angular velocity, joint angles, orientation, electromyography (EMG), and marker data, necessitating a robust approach to overcome challenges in information integration. The primary challenge lies in the effective utilization of multiple sensor modalities, each with unique characteristics and potential noise sources. The proposed solution addresses this by employing advanced sensor fusion techniques, such as Kalman filtering, during data collection. Synchronization and resampling ensure temporal consistency, while noise reduction techniques, such as low-pass filters, mitigate signal distortions. To further refine the process, a hybrid optimization-based feature selection Adaptive Step Size in Marine Predators Algorithm (ASSMPA) is introduced, focusing on marker data features. ASSMPA synergizes Marine Predators Algorithm (MPA) and Pathfinder Algorithm (PFA) for optimal feature selection in marine predator pathfinding tasks. The Feature Fusion step integrates attention mechanisms to dynamically weigh the significance of different sensor modalities during the fusion process. This strategic fusion enhances the overall performance of the Multi-Modal Hierarchical Neural Network (MMHNN). The proposed model is implemented using Python

Analyzing and Improving the Use of the FastMap Embedding in Pathfinding Tasks

Analyzing and Improving the Use of the FastMap Embedding in Pathfinding Tasks

QUANTITATIVE SIGNATURES OF BRAIN COGNITION IN YOUNG CHILDREN USING TASK-BASED EEG SIGNALS

Cognition is the practice of processing knowledge through mental processes. Understanding cognitive functions of the brain in young children helps in identifying neurodevelopmental disorders at early stages. Most studies used to diagnose neurodevelopmental disorders are based on behavioral scales. But most children with neurodevelopmental disorders are non-verbal. Thus, the goal of this research is to perform a task-based analysis of cognitive skills in children using electroencephalographic (EEG) signals. Spectral and fractal features of the EEG signals were acquired from pre-primary school children ([Formula: see text]) during arithmetic and path-finding cognitive tasks. The acquired signals were decomposed into various sub-bands. Investigations on the time-domain Higuchi Fractal Dimension (HFD) analysis and frequency domain Power Spectrum Analysis features demonstrated the dominance of the Theta band over the other subbands. The frontal electrode exhibited more workload in the arithmetic task, indicating the involvement of frontal regions and the temporal areas (T8) which were actively involved throughout the path-finding task, showing the activity related to spatial perception and navigation. Thus, the statistical information obtained from the spectral and fractal analyses seems to provide quantitative evidence of the variations in cognitive skills of young children thereby enhancing inferences about neurodevelopmental disorders.

Multiterminal Pathfinding in Practical VLSI Systems with Deep Neural Networks

A multiterminal obstacle-avoiding pathfinding approach is proposed. The approach is inspired by deep image learning. The key idea is based on training a conditional generative adversarial network (cGAN) to interpret a pathfinding task as a graphical bitmap and consequently map a pathfinding task onto a pathfinding solution represented by another bitmap. To enable the proposed cGAN pathfinding, a methodology for generating synthetic dataset is also proposed. The cGAN model is implemented in Python/Keras, trained on synthetically generated data, evaluated on practical VLSI benchmarks, and compared with state-of-the-art. Due to effective parallelization on GPU hardware, the proposed approach yields a state-of-the-art-like wirelength and a better runtime and throughput for moderately complex pathfinding tasks. However, the runtime and throughput with the proposed approach remain constant with an increasing task complexity, promising orders of magnitude improvement over state-of-the-art in complex pathfinding tasks. The cGAN pathfinder can be exploited in numerous high throughput applications, such as, navigation, tracking, and routing in complex VLSI systems. The last is of particular interest to this work.

Real-Time Adaptive A* with Depression Avoidance

Real-time search is a well known approach to solving search problems under tight time constraints. Recently, it has been shown that LSS-LRTA∗ , a well-known real-time search algorithm, can be improved when search is actively guided away of depressions. In this paper we investigate whether or not RTAA∗ can be improved in the same manner. We propose aRTAA∗ and daRTAA∗ , two algorithms based on RTAA∗ that avoid heuristic depressions. Both algorithms outperform RTAA∗ on standard path-finding tasks, obtaining better-quality solutions when the same time deadline is imposed on the duration of the planning episode. We prove, in addition, that both algorithms have good theoretical properties.

Effects of Self-Knowledge: Once Bitten Twice Shy

Procedurally generating rich, naturally behaving AI-controlled video game characters is an important open problem. In this paper we focus on a particular aspect of non-playable character (NPC) behavior, long favored by science-fiction writers. Specifically, we study the effects of self-knowledge on NPC behavior. To do so we adopt the well-known framework of agent-centered real-time heuristic search applied to the standard pathfinding task on video-game maps. Such search agents normally use a heuristic function to guide them around a map to the goal state. Heuristic functions are inaccurate underestimates of the remaining distance to goal. What if the agent somehow knew how long it (the agent) would actually take to reach the goal from each state? How would using such self-knowledge in place of a heuristic function affect the agent's behavior? We show that similarly to real life, knowing of one's irrational behavior in a situation can deter the agent from getting into that situation again even if it is, in fact, a part of an optimal solution. We demonstrate the "fear" with a simple example and empirically show that the issue is common in video-game pathfinding. We then analyze the issue theoretically and suggest that "fear" induced by self-knowledge is not a bug but a feature and may potentially be used to develop more naturally behaving NPCs.

Learning basic concept of computer programming with path-finding task in ar and its properties

This paper designs and develops a computer programming learning system for total beginners and those who have no programming experience. The traditional computer programming learning systems require prior knowledge about variables, their types, operators for arithmetic calculations and relational calculations etc., for adopting a wide range of representation of program codes, leading to the burden to them. The proposed system focuses on learning the three basic flows of control: sequential, conditional and iterative controls, for not requiring the prior knowledge, and exploits a path-finding task for confining representation of program codes to a specific task, which is a navigation task where students are asked to organize a sequence of orders for an avatar to move from a given start to a given end on a Manhattan grid map. The previous work employs the path-finding task to foster understanding of the sequence of orders by encouraging students to perform self-tracing process while our proposed system employs it to include that property of understanding for the three basic flows of control which are not covered in the previous work. To add high interactivity and tangibility for student motivation and engagement to learning, the proposed system also employs AR capability. An experiment on feasibility of our system for education is conducted and the results show that our system has the potential for improving students’ understanding of how to make program codes by decrease of the ratio of program codes’ length made by beginners to experts, which is from 2.186 to 1.267, regardless of AR capability such that the ratio decreased from 2.481 to 1.346 without AR capability and it was from 1.974 to 1.206 with it. The results also show that our system significantly leverages their motivation of learning by increase of beginners’ score from 5.00 without AR capability to 6.67 with it for interest and it is from 5.67 to 7.00 for amusement, and even if sacrificing a wide range of representation of program codes that the traditional systems take, a certain stress is significantly given on spending time thinking and building up a program code in proportion to its difficulty and complexity.

Knowledge of familiar environments: Assessing modalities and individual visuo-spatial factors

Familiarity enables us to form elaborate mental representations of environments, which are usually assessed with tasks that involve managing spatial information (such as pointing and locating landmarks). The present study also examines the role of familiarity using a “field” task that involved finding the shortest way to a destination, and the contribution of individual visuo-spatial factors (a set of abilities, preferences and strategies). Undergraduates more or less familiar with their university campus (45 in each group) performed pointing and landmark-locating (spatial information managing) tasks, and a shortest path finding task, and were administered several visuo-spatial measures. The results showed that familiarity had no effect on spatial information managing performance, but did influence shortest path finding. Individual visuo-spatial factors variously supported pointing accuracy, and shortest path finding performance. These results broaden our knowledge of how individual factors (familiarity and visuo-spatial abilities, preferences and strategies) jointly support the knowledge of an environment.

КЛАСИЧНІ МЕТОДИ ПЛАНУВАННЯ ШЛЯХУ ДЛЯ МОБІЛЬНИХ РОБОТІВ

Мобільні автономні роботи (МАР) використовуються для виконання великої кількості різноманітних завдань у різних галузях, таких як видобуток корисних копалин, пошук та порятунок, військових застосувань тощо. Окремо виділяється категорія МАР, які використовуються у закритих приміщеннях. Це пов’язано з додатковими технічними та програмними обмеженнями які накладаються на МАР та оператора. У цій статті розглядаються 35 класичних методів пошуку шляху для МАР та методів їх оптимізації. Класичні методи включають наступні категорії методів: методи клітинної декомпозиції; методи штучного потенційного поля; вибіркові методи; методи, що використовують мережу проміжних задач. У статті також розглядаються основні проблеми, що виникають під час виконання задачі пошуку шляхів. Методи аналізувалися за такими характеристиками: обмеження; режим планування; мнтрика, яка використовується для планування наступного кроку. Також у статті розглядаються основні проблеми з якими стикаються під час виконання задачі пошуку шляху.

Grid Path Planning with Deep Reinforcement Learning: Preliminary Results

Single-shot grid-based path finding is an important problem with the applications in robotics, video games etc. Typically in AI community heuristic search methods (based on A* and its variations) are used to solve it. In this work we present the results of preliminary studies on how neural networks can be utilized to path planning on square grids, e.g. how well they can cope with path finding tasks by themselves within the well-known reinforcement problem statement. Conducted experiments show that the agent using neural Q-learning algorithm robustly learns to achieve the goal on small maps and demonstrate promising results on the maps have ben never seen by him before.

Modeling emotion and inference as a value calculation system

There have been many studies on the modeling of a relation between emotion and decision making. Though the effect of emotion on inference in making a decision is evident, its computational mechanism, especially for intuitive inference, is not yet clear. Therefore, in this paper, we discuss the possibility of the computational modeling of an intuitive inference guided by emotion in which random-seeming neural excitation plays the role of a probability-based parallel search of values. First, we show a possible architecture of the intuitive inference in which the system of multiple values affects the process of action decision. Then, we focus on an effect of the value-control mechanism for intuitive inference in a path-finding task. In a computer simulation, we aimed to simulate a model of value management in which multiple value components of the brainstem are controlled for an action search. Though the brainstem seems simple, the model includes the essence of the resolution of conflicts between multiple values.

Recognition of a Virtual Maze Scene Using Simulated Prosthetic Vision.

A real-time psychological physics experimental platform was built to aid in discovering the best real-time image processing strategy for the limited number of electrodes, and in providing the most useful prosthetic implant visual information. A number of maze pathfinder tasks were performed at low resolution to simulate use by blind individuals in performing daily visual activities. In this study, simple (5 rows × 5 columns), medium (8 × 8), and complex (11 × 11) maze models were created in 3DMAX. The models were constructed by using Unity to build virtual scenes for real-time pixel processing, including binarization, color inversion, and matching to templates with three different resolutions (16 × 16, 24 × 24, 32 × 32). Subjects completed maze pathfinding tasks using 45° and 60° views of the labyrinth at the 32 × 32 resolution to determine the optimal viewing angle. The time required to find the maze entrance and complete the maze were analyzed along with the rate of maze completion (accuracy) at various resolutions. In the first experiment, the average time required to find the entrance and the average maze pathfinding duration were significantly longer at 60°. Therefore, the 45° view provided the best perspective. In the second experiment, the angle was fixed to 45°. As the maze difficulty increased, the average time needed to find the maze entrance decreased, but the average time required to complete the maze increased. When the difficulty of the maze was fixed, the time required to find the maze entrance and solve the maze decreased when the resolution increased. The accuracy with which the maze path was identified increased as well. The average maze pathfinding time at 24 × 24 was significantly less than at 16 × 16. A similar trend was observed when the average maze pathfinding times at 32 × 32 and 24 × 24 were compared. At 32 × 32, the average pathfinding accuracy was 100%. This indicates that 32 × 32 is an effective resolution for maze pathfinding.

Optimal path-finding through mental exploration based on neural energy field gradients

Rodent animal can accomplish self-locating and path-finding task by forming a cognitive map in the hippocampus representing the environment. In the classical model of the cognitive map, the system (artificial animal) needs large amounts of physical exploration to study spatial environment to solve path-finding problems, which costs too much time and energy. Although Hopfield’s mental exploration model makes up for the deficiency mentioned above, the path is still not efficient enough. Moreover, his model mainly focused on the artificial neural network, and clear physiological meanings has not been addressed. In this work, based on the concept of mental exploration, neural energy coding theory has been applied to the novel calculation model to solve the path-finding problem. Energy field is constructed on the basis of the firing power of place cell clusters, and the energy field gradient can be used in mental exploration to solve path-finding problems. The study shows that the new mental exploration model can efficiently find the optimal path, and present the learning process with biophysical meaning as well. We also analyzed the parameters of the model which affect the path efficiency. This new idea verifies the importance of place cell and synapse in spatial memory and proves that energy coding is effective to study cognitive activities. This may provide the theoretical basis for the neural dynamics mechanism of spatial memory.

Weighted heuristic anytime search: new schemes for optimization over graphical models

Weighted heuristic search (best-first or depth-first) refers to search with a heuristic function multiplied by a constant w [31]. The paper shows, for the first time, that for optimization queries in graphical models the weighted heuristic best-first and weighted heuristic depth-first branch and bound search schemes are competitive energy-minimization anytime optimization algorithms. Weighted heuristic best-first schemes were investigated for path-finding tasks. However, their potential for graphical models was ignored, possibly because of their memory costs and because the alternative depth-first branch and bound seemed very appropriate for bounded depth. The weighted heuristic depth-first search has not been studied for graphical models. We report on a significant empirical evaluation, demonstrating the potential of both weighted heuristic best-first search and weighted heuristic depth-first branch and bound algorithms as approximation anytime schemes (that have sub-optimality bounds) and compare against one of the best depth-first branch and bound solvers to date.

Incremental Construction of Generalized Voronoi Diagrams on Pointerless Quadtrees

In robotics, Generalized Voronoi Diagrams (GVDs) are widely used by mobile robots to represent the spatial topologies of their surrounding area. In this paper we consider the problem of constructing GVDs on discrete environments. Several algorithms that solve this problem exist in the literature, notably the Brushfire algorithm and its improved versions which possess local repair mechanism. However, when the area to be processed is very large or is of high resolution, the size of the metric matrices used by these algorithms to compute GVDs can be prohibitive. To address this issue, we propose an improvement on the current algorithms, using pointerless quadtrees in place of metric matrices to compute and maintain GVDs. Beyond the construction and reconstruction of a GVD, our algorithm further provides a method to approximate roadmaps in multiple granularities from the quadtree based GVD. Simulation tests in representative scenarios demonstrate that, compared with the current algorithms, our algorithm generally makes an order of magnitude improvement regarding memory cost when the area is larger than210×210. We also demonstrate the usefulness of the approximated roadmaps for coarse-to-fine pathfinding tasks.

A Temporal-Difference Learning Method Using Gaussian State Representation for Continuous State Space Problems

In this paper, we tackle the problem of reinforcement learning (RL) in a continuous state space. An appropriate discretization of the space can make many learning tasks tractable. A method using Gaussian state representation and the Rational Policy Making algorithm (RPM) has been proposed for this problem. This method discretizes the space by constructing a chain of states which represents a path to the goal of the agent exploiting past experiences of reaching it. This method exploits successful experiences strongly. Therefore, it can find a rational solution quickly in an environment with few noises. In a noisy environment, it makes many unnecessary and distractive states and does the task poorly. For learning in such an environment, we have introduced the concept of the value of a state to the above method and developed a new method. This method uses a temporal-difference (TD) learning algorithm for learning the values of states. The value of a state is used to determine the size of the state. Thus, our developed method can trim and eliminate unnecessary and distractive states quickly and learn the task well even in a noisy environment. We show the effectiveness of our method by computer simulations of a path finding task and a cart-pole swing-up task.

Real-Time Adaptive A∗ with Depression Avoidance

RTAA* is probably the best-performing real-time heuristic search algorithm at path-finding tasks in which the environ- ment is not known in advance or in which the environment is known and there is no time for pre-processing. As most real- time search algorithms do, RTAA∗ performs poorly in presence of heuristic depressions, which are bounded areas of the search space in which the heuristic is too low with respect to their border. Recently, it has been shown that LSS-LRTA∗, a well-known real-time search algorithm, can be improved when search is actively guided away of depressions. In this paper we investigate whether or not RTAA∗ can be improved in the same manner. We propose aRTAA∗ and daRTAA∗, two algorithms based on RTAA∗ that avoid heuristic depressions. Both algorithms outperform RTAA∗ on standard path-finding tasks, obtaining better-quality solutions when the same time deadline is imposed on the duration of the planning episode. We prove, in addition, that both algorithms have good theoretical properties

Effects of e-map format and sub-windows on driving performance and glance behavior when using an in-vehicle navigation system

An on-road driving experiment was conducted to investigate the effects of e-map format and sub-windows on driving performance and glance behavior of navigation system users. Twenty-eight participants navigated an urban route using the navigation display with 2D or 3D e-maps and either with or without sub-windows. Driver navigation errors and visual glance data were gathered during the trials. The analytical results demonstrate no significant difference in driving performance between the 2D and 3D e-map conditions. However, use of a 3D e-map was associated with significantly more frequent glance behavior than the 2D display. Furthermore, subjects using the navigation display with a sub-window made significantly fewer navigation errors (50% less) compared to those using the navigation display without a sub-window. This investigation suggests that performance improves when using sub-windows. Finally, this study discusses wider implications in the design and use of navigation displays. Relevance to industry We found that the e-map format is related to driver glance behavior when using an in-vehicle navigation display. The sub-window also provides substantial influence on driving performance and glance behavior. The results of our study will assist in designing in-vehicle navigation systems and improving the performance of navigation e-maps for path-finding tasks.

Inferring branching pathways in genome-scale metabolic networks

BackgroundA central problem in computational metabolic modelling is how to find biochemically plausible pathways between metabolites in a metabolic network. Two general, complementary frameworks have been utilized to find metabolic pathways: constraint-based modelling and graph-theoretical path finding approaches. In constraint-based modelling, one aims to find pathways where metabolites are balanced in a pseudo steady-state. Constraint-based methods, such as elementary flux mode analysis, have typically a high computational cost stemming from a large number of steady-state pathways in a typical metabolic network. On the other hand, graph-theoretical approaches avoid the computational complexity of constraint-based methods by solving a simpler problem of finding shortest paths. However, while scaling well with network size, graph-theoretic methods generally tend to return more false positive pathways than constraint-based methods.ResultsIn this paper, we introduce a computational method, ReTrace, for finding biochemically relevant, branching metabolic pathways in an atom-level representation of metabolic networks. The method finds compact pathways which transfer a high fraction of atoms from source to target metabolites by considering combinations of linear shortest paths. In contrast to current steady-state pathway analysis methods, our method scales up well and is able to operate on genome-scale models. Further, we show that the pathways produced are biochemically meaningful by an example involving the biosynthesis of inosine 5'-monophosphate (IMP). In particular, the method is able to avoid typical problems associated with graph-theoretic approaches such as the need to define side metabolites or pathways not carrying any net carbon flux appearing in results. Finally, we discuss an application involving reconstruction of amino acid pathways of a recently sequenced organism demonstrating how measurement data can be easily incorporated into ReTrace analysis. ReTrace is licensed under GPL and is freely available for academic use at http://www.cs.helsinki.fi/group/sysfys/software/retrace/.ConclusionReTrace is a useful method in metabolic path finding tasks, combining some of the best aspects in constraint-based and graph-theoretic methods. It finds use in a multitude of tasks ranging from metabolic engineering to metabolic reconstruction of recently sequenced organisms.