RESUMEN
Physiological studies have revealed that rats perform spatial localization relying on grid cells and place cells in the entorhinal-hippocampal CA3 structure. The dynamic connection between the entorhinal-hippocampal structure and the prefrontal cortex is crucial for navigation. Based on these findings, this paper proposes a spatial navigation method based on the entorhinal-hippocampal-prefrontal information transmission circuit of the rat's brain, with the aim of endowing the mobile robot with strong spatial navigation capability. Using the hippocampal CA3-prefrontal spatial navigation model as a foundation, this paper constructed a dynamic self-organizing model with the hippocampal CA1 place cells as the basic unit to optimize the navigation path. The path information was then fed back to the impulse neural network via hippocampal CA3 place cells and prefrontal cortex action neurons, improving the convergence speed of the model and helping to establish long-term memory of navigation habits. To verify the validity of the method, two-dimensional simulation experiments and three-dimensional simulation robot experiments were designed in this paper. The experimental results showed that the method presented in this paper not only surpassed other algorithms in terms of navigation efficiency and convergence speed, but also exhibited good adaptability to dynamic navigation tasks. Furthermore, our method can be effectively applied to mobile robots.
Asunto(s)
Corteza Entorrinal , Navegación Espacial , Ratas , Animales , Corteza Entorrinal/fisiología , Navegación Espacial/fisiología , Hipocampo , Neuronas/fisiología , Corteza Prefrontal , Modelos NeurológicosRESUMEN
Physiological studies reveal that rats rely on multiple spatial cells for spatial navigation and memory. In this paper, we investigated the firing mechanism of spatial cells within the entorhinal-hippocampal structure of the rat brain and proposed a spatial localization model for mobile robot. Its characteristics were as follows: on the basis of the information transmission model from grid cells to place cells, the neural network model of place cells interaction was introduced to obtain the place cell plate with a single-peaked excitatory activity package. Then the solution to the robot's position was achieved by establishing a transformation relationship between the position of the excitatory activity package on the place cell plate and the robot's position in the physical environment. In this paper, simulation experiments and physical experiments were designed to verify the model. The experimental results showed that compared with RatSLAM and the model of grid cells to place cells, the positioning performance of the model in this paper was more accurate, and the cumulative error in the long-time path integration process of the robot was also smaller. The research results of this paper lay a foundation for the robot navigation method that mimics the cognitive mechanism of rat brain.
Asunto(s)
Células de Lugar , Robótica , Animales , Cognición , Hipocampo , Modelos Neurológicos , RatasRESUMEN
Biological studies show that place cells are the main basis for rats to know their current location in space. Since grid cells are the main input source of place cells, a mapping model from grid cells to place cells needs to be constructed. To solve this problem, a neural network mapping model of back propagation error from grid cells to place cells is proposed in this paper, which can accurately express the location in a given region. According to the physiological characteristics of border cells' specific discharge to the environment, the periodic resetting of the grid field phase by border cells is realized, and the position recognition in any space is completed by this model. In this paper, we designed a simulation experiment to compare the activity of the theoretical place cell plate, and then compared the time consumption of the competitive neural network model and the positioning error of RatSLAM pose cells plate. The experimental results showed that the proposed model could obtain a single place field, and the algorithm efficiency was improved by 85.94% compared with the competitive neural network model in the time-consuming experiment. In the localization experiment, the mean localization error was 41.35% lower than that of RatSLAM pose cells plate. Therefore, the location cognition model proposed in this paper can not only realize the efficient transfer of information between grid cells and place cells, but also realize the accurate location of its own location in any spatial area.
Asunto(s)
Cognición , Hipocampo/citología , Modelos Neurológicos , Células de Lugar , Animales , Simulación por Computador , RatasRESUMEN
The method of directly using speed information and angle information to drive attractors model of grid cells to encode environment has poor anti-interference ability and is not bionic. In response to the problem, this paper proposes a grid field calculation model based on perceived speed and perceived angle. The model has the following characteristics. Firstly, visual stream is decoded to obtain visual speed, and speed cell is modeled and decoded to obtain body speed. Visual speed and body speed are integrated to obtain perceived speed information. Secondly, a one-dimensional circularly connected cell model with excitatory connection is used to simulate the firing mechanism of head direction cells, so that the robot obtains current perception angle information in a biomimetic manner. Finally, the two kinds of perceptual information of speed and angle are combined to realize the driving of grid cell attractors model. The proposed model was experimentally verified. The results showed that this model could realize periodic hexagonal firing field mode of grid cells and precise path integration function. The proposed algorithm may provide a foundation for the research on construction method of robot cognitive map based on hippocampal cognition mechanism.
Asunto(s)
Células de Red , Potenciales de Acción , Simulación por Computador , Sistemas de Computación , Corteza Entorrinal , Hipocampo , Modelos NeurológicosRESUMEN
Noise and constant empirical motion constraints affect the extraction of distinctive spatiotemporal features from one or a few samples per gesture class. To tackle these problems, an adaptive local spatiotemporal feature (ALSTF) using fused RGB-D data is proposed. First, motion regions of interest (MRoIs) are adaptively extracted using grayscale and depth velocity variance information to greatly reduce the impact of noise. Then, corners are used as keypoints if their depth, and velocities of grayscale and of depth meet several adaptive local constraints in each MRoI. With further filtering of noise, an accurate and sufficient number of keypoints is obtained within the desired moving body parts (MBPs). Finally, four kinds of multiple descriptors are calculated and combined in extended gradient and motion spaces to represent the appearance and motion features of gestures. The experimental results on the ChaLearn gesture, CAD-60 and MSRDailyActivity3D datasets demonstrate that the proposed feature achieves higher performance compared with published state-of-the-art approaches under the one-shot learning setting and comparable accuracy under the leave-one-out cross validation.
RESUMEN
It has been found that in biological studies,the simple linear superposition mathematical model cannot be used to express the feature mapping relationship from multiple activated grid cells' grid fields to a single place cell's place field output in the hippocampus of the cerebral cortex of rodents.To solve this problem,people introduced the Gauss distribution activation function into the area.We in this paper use the localization properties of the function to deal with the linear superposition output of grid cells' input and the connection weights between grid cells and place cells,which filters out the low activation rate place fields.We then obtained a single place cell field which is consistent with biological studies.Compared to the existing competitive learning algorithm place cell model,independent component analysis method place cell model,Bayesian positon reconstruction method place cell model,our experimental results showed that the model on the neurophysiological basis can not only express the feature mapping relationship between multiple activated grid cells grid fields and a single place cell's place field output in the hippocampus of the cerebral cortex of rodents,but also make the algorithm simpler,the required grid cells input less and the accuracy rate of the output of a single place field higher.
Asunto(s)
Corteza Cerebral/citología , Células de Red/citología , Hipocampo/citología , Modelos Neurológicos , Células de Lugar/citología , Potenciales de Acción , Algoritmos , Animales , Teorema de Bayes , Simulación por Computador , Modelos Lineales , Red Nerviosa/fisiología , Neuronas/fisiologíaRESUMEN
Rats possess exceptional navigational abilities, allowing them to adaptively adjust their navigation paths based on the environmental structure. This remarkable ability is attributed to the interactions and regulatory mechanisms among various spatial cells within the rat's brain. Based on these, this paper proposes a navigation path search and optimization method for mobile robots based on the rat brain's cognitive mechanism. The aim is to enhance the navigation efficiency of mobile robots. The mechanism of this method is based on developing a navigation habit. Firstly, the robot explores the environment to search for the navigation goal. Then, with the assistance of boundary vector cells, the greedy strategy is used to guide the robot in generating a locally optimal path. Once the navigation path is generated, a dynamic self-organizing model based on the hippocampal CA1 place cells is constructed to further optimize the navigation path. To validate the effectiveness of the method, this paper designs several 2D simulation experiments and 3D robot simulation experiments, and compares the proposed method with various algorithms. The experimental results demonstrate that the proposed method not only surpasses other algorithms in terms of path planning efficiency but also yields the shortest navigation path. Moreover, the method exhibits good adaptability to dynamic navigation tasks.
RESUMEN
The semiconductor manufacturing industry relies heavily on wafer surface defect detection for yield enhancement. Machine learning and digital image processing technologies have been used in the development of various detection algorithms. However, most wafer surface inspection algorithms are not be applied in industrial environments due to the difficulty in obtaining training samples, high computational requirements, and poor generalization. In order to overcome these difficulties, this paper introduces a full-flow inspection method based on machine vision to detect wafer surface defects. Starting with the die image segmentation stage, where a die segmentation algorithm based on candidate frame fitting and coordinate interpolation is proposed for die sample missing matching segmentation. The method can segment all the dies in the wafer, avoiding the problem of missing dies splitting. After that, in the defect detection stage, we propose a die defect anomaly detection method based on defect feature clustering by region, which can reduce the impact of noise in other regions when extracting defect features in a single region. The experiments show that the proposed inspection method can precisely position and segment die images, and find defective dies with an accuracy of more than 97%. The defect detection method proposed in this paper can be applied to inspect wafer manufacturing.
RESUMEN
Physiological studies have shown that the hippocampal structure of rats develops at different stages, in which the place cells continue to develop during the whole juvenile period of rats and mature after the juvenile period. As the main information source of place cells, grid cells should mature earlier than place cells. In order to make better use of the biological information exhibited by the rat brain hippocampus in the environment, we propose a position cognition model based on the spatial cell development mechanism of rat hippocampus. The model uses a recurrent neural network with parametric bias (RNNPB) to simulate changes in the discharge characteristics during the development of a single stripe cell. The oscillatory interference mechanism is able to fuse the developing stripe waves, thus indirectly simulating the developmental process of the grid cells. The output of the grid cells is then used as the information input of the place cells, whose development process is simulated by BP neural network. After the place cells matured, the position matrix generated by the place cell group was used to realize the position cognition of rats in a given spatial region. The experimental results show that this model can simulate the development process of grid cells and place cells, and it can realize high precision positioning in the given space area. Moreover, the experimental effect of cognitive map construction using this model is basically consistent with the effect of RatSLAM, which verifies the validity and accuracy of the model.
Asunto(s)
Hipocampo , Modelos Neurológicos , Animales , Cognición , Redes Neurales de la Computación , RatasRESUMEN
Developing artificial intelligence (AI) agents is challenging for efficient exploration in visually rich and complex environments. In this study, we formulate the exploration question as a reinforcement learning problem and rely on intrinsic motivation to guide exploration behavior. Such intrinsic motivation is driven by curiosity and is calculated based on episode memory. To distribute the intrinsic motivation, we use a count-based method and temporal distance to generate it synchronously. We tested our approach in 3D maze-like environments and validated its performance in exploration tasks through extensive experiments. The experimental results show that our agent can learn exploration ability from raw sensory input and accomplish autonomous exploration across different mazes. In addition, the learned policy is not biased by stochastic objects. We also analyze the effects of different training methods and driving forces on exploration policy.
Asunto(s)
Inteligencia Artificial , Motivación , Conducta Exploratoria , Aprendizaje , Refuerzo en PsicologíaRESUMEN
Associative learning, including classical conditioning and operant conditioning, is regarded as the most fundamental type of learning for animals and human beings. Many models have been proposed surrounding classical conditioning or operant conditioning. However, a unified and integrated model to explain the two types of conditioning is much less studied. Here, a model based on neuromodulated synaptic plasticity is presented. The model is bioinspired including multistored memory module and simulated VTA dopaminergic neurons to produce reward signal. The synaptic weights are modified according to the reward signal, which simulates the change of associative strengths in associative learning. The experiment results in real robots prove the suitability and validity of the proposed model.